more gpt-neox long ctx fixes

.github/workflows/base.yml

@@ -12,19 +12,28 @@ jobs:
     # this job needs to be run on self-hosted GPU runners...
     runs-on: self-hosted
     strategy:
-      fail-fast: false
       matrix:
         include:
           - cuda: "118"
             cuda_version: 11.8.0
             python_version: "3.9"
-            pytorch: 2.0.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
+            pytorch: 2.0.0
+            axolotl_extras:
           - cuda: "118"
             cuda_version: 11.8.0
             python_version: "3.10"
-            pytorch: 2.0.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
+            pytorch: 2.0.0
+            axolotl_extras:
+          - cuda: "117"
+            cuda_version: 11.7.0
+            python_version: "3.9"
+            pytorch: 1.13.1
+            axolotl_extras:
+          - cuda: "118"
+            cuda_version: 11.8.0
+            python_version: "3.9"
+            pytorch: 2.0.0
+            axolotl_extras: gptq
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -48,9 +57,11 @@ jobs:
           push: ${{ github.event_name != 'pull_request' }}
           tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
           labels: ${{ steps.metadata.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
           build-args: |
             CUDA_VERSION=${{ matrix.cuda_version }}
             CUDA=${{ matrix.cuda }}
             PYTHON_VERSION=${{ matrix.python_version }}
             PYTORCH_VERSION=${{ matrix.pytorch }}
-            TORCH_CUDA_ARCH_LIST=${{ matrix.torch_cuda_arch_list }}
+            AXOLOTL_EXTRAS=${{ matrix.axolotl_extras }}

.github/workflows/main.yml

@@ -11,24 +11,28 @@ jobs:
     if: github.repository_owner == 'OpenAccess-AI-Collective'
     # this job needs to be run on self-hosted GPU runners...
     strategy:
-      fail-fast: false
       matrix:
         include:
           - cuda: cu118
             cuda_version: 11.8.0
             python_version: "3.9"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
             axolotl_extras:
           - cuda: cu118
             cuda_version: 11.8.0
             python_version: "3.10"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
             axolotl_extras:
           - cuda: cu118
             cuda_version: 11.8.0
             python_version: "3.9"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
             axolotl_extras: gptq
+          - cuda: cu117
+            cuda_version: 11.7.0
+            python_version: "3.9"
+            pytorch: 1.13.1
+            axolotl_extras:
     runs-on: self-hosted
     steps:
       - name: Checkout
@@ -50,11 +54,13 @@ jobs:
         with:
           context: .
           build-args: |
-            BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}
+            BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
           file: ./docker/Dockerfile
           push: ${{ github.event_name != 'pull_request' }}
           tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
           labels: ${{ steps.metadata.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
   build-axolotl-runpod:
     needs: build-axolotl
     if: github.repository_owner == 'OpenAccess-AI-Collective'
@@ -62,21 +68,26 @@ jobs:
     strategy:
       matrix:
         include:
-          - cuda: 118
+          - cuda: cu118
             cuda_version: 11.8.0
             python_version: "3.9"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
             axolotl_extras:
-          - cuda: 118
+          - cuda: cu118
             cuda_version: 11.8.0
             python_version: "3.10"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
             axolotl_extras:
-          - cuda: 118
+          - cuda: cu118
             cuda_version: 11.8.0
             python_version: "3.9"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
             axolotl_extras: gptq
+          - cuda: cu117
+            cuda_version: 11.7.0
+            python_version: "3.9"
+            pytorch: 1.13.1
+            axolotl_extras:
     runs-on: self-hosted
     steps:
       - name: Checkout
@@ -98,9 +109,10 @@ jobs:
         with:
           context: .
           build-args: |
-            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
-            CUDA=${{ matrix.cuda }}
+            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
           file: ./docker/Dockerfile-runpod
           push: ${{ github.event_name != 'pull_request' }}
-          tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+          tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
           labels: ${{ steps.metadata.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/tests.yml

@@ -7,7 +7,6 @@ jobs:
   test:
     runs-on: ubuntu-latest
     strategy:
-      fail-fast: false
       matrix:
         python_version: ["3.9", "3.10"]
     timeout-minutes: 10

.pre-commit-config.yaml

@@ -1,5 +1,5 @@
 default_language_version:
-    python: python3
+    python: python3.9
 
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks

FAQS.md

@@ -2,6 +2,3 @@
 
 - Can you train StableLM with this? Yes, but only with a single GPU atm. Multi GPU support is coming soon! Just waiting on this [PR](https://github.com/huggingface/transformers/pull/22874)
 - Will this work with Deepspeed? That's still a WIP, but setting `export ACCELERATE_USE_DEEPSPEED=true` should work in some cases
-- `Error invalid argument at line 359 in file /workspace/bitsandbytes/csrc/pythonInterface.c`
-`/arrow/cpp/src/arrow/filesystem/s3fs.cc:2598:  arrow::fs::FinalizeS3 was not called even though S3 was initialized.`
-This could lead to a segmentation fault at exit. Try reinstalling bitsandbytes and transformers from source.

LICENSE

@@ -1,202 +0,0 @@
-
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.

README.md

@@ -16,32 +16,31 @@
 
 ## Axolotl supports
 
-|          | fp16/fp32 | lora | qlora | gptq | gptq w/ lora | gptq w/flash attn | flash attn | xformers attn |
-|----------|:----------|:-----|-------|------|:-------------|-------------------|------------|---------------|
-| llama    | ✅         | ✅    | ✅     | ✅    | ✅             | ✅                 | ✅          | ✅             |
-| Pythia   | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❌          | ❓             |
-| cerebras | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❌          | ✅             |
-| mpt      | ✅         | ❌    | ❓     | ❌    | ❓            | ❌                 | ❌          | ❓             |
-| falcon   | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❌          | ✅             |
-| gpt-j    | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❓          | ✅             |
-| XGen     | ✅         | ❓    | ✅     | ❓    | ❓            | ❓                 | ❓          | ✅
+|         | fp16/fp32 | fp16/fp32 w/ lora | qlora | 4bit-quant | 4bit-quant w/flash attention | flash attention | xformers attention |
+|---------|:----------|:------------------|------|------------|------------------------------|-----------------|--------------------|
+| llama   | ✅         | ✅                 | ✅  | ✅          | ✅                            | ✅               | ✅                  |
+| Pythia  | ✅         | ✅                 | ❓  | ❌          | ❌                            | ❌               | ❓                  |
+| cerebras | ✅         | ✅                 | ❓  | ❌          | ❌                            | ❌               | ❓                  |
+| mpt     | ✅         | ❌                 | ❓  | ❌          | ❌                            | ❌               | ❓                  |
+| falcon  | ✅         | ❌                 | ❌  | ❌          | ❌                            | ❌               | ❓                  |
 
 
 ## Quickstart ⚡
 
-**Requirements**: Python >=3.9 and Pytorch >=2.0.
+**Requirements**: Python 3.9 and Pytorch 2.0.
 
 ```bash
 git clone https://github.com/OpenAccess-AI-Collective/axolotl
 
 pip3 install -e .
-pip3 install -U git+https://github.com/huggingface/peft.git
+
+accelerate config
 
 # finetune lora
-accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml
+accelerate launch scripts/finetune.py examples/lora-openllama-3b/config.yml
 
 # inference
-accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml \
+accelerate launch scripts/finetune.py examples/lora-openllama-3b/config.yml \
     --inference --lora_model_dir="./lora-out"
 ```
 
@@ -51,16 +50,10 @@ accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml \
 
 - Docker
   ```bash
-  docker run --gpus '"all"' --rm -it winglian/axolotl:main-py3.10-cu118-2.0.1
-  ```
-  - `winglian/axolotl-runpod:main-py3.10-cu118-2.0.1`: for runpod
-  - `winglian/axolotl-runpod:main-py3.9-cu118-2.0.1-gptq`: for gptq
-
-  Or run on the current files for development:
-
-  ```sh
-  docker compose up -d
+  docker run --gpus '"all"' --rm -it winglian/axolotl:main
   ```
+  - `winglian/axolotl:dev`: dev branch
+  - `winglian/axolotl-runpod:main`: for runpod
 
 - Conda/Pip venv
   1. Install python **3.9**
@@ -68,65 +61,9 @@ accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml \
   2. Install pytorch stable https://pytorch.org/get-started/locally/
 
   3. Install python dependencies with ONE of the following:
-      - Recommended, supports QLoRA, NO gptq/int4 support
-        ```bash
-        pip3 install -e .
-        pip3 install -U git+https://github.com/huggingface/peft.git
-        ```
-      - gptq/int4 support, NO QLoRA
-        ```bash
-        pip3 install -e .[gptq]
-        ```
-      - same as above but not recommended
-        ```bash
-        pip3 install -e .[gptq_triton]
-        ```
-
-- LambdaLabs
-  <details>
-
-  <summary>Click to Expand</summary>
-
-  1. Install python
-  ```bash
-  sudo apt update
-  sudo apt install -y python3.9
-
-  sudo update-alternatives --install /usr/bin/python python /usr/bin/python3.9 1
-  sudo update-alternatives --config python # pick 3.9 if given option
-  python -V # should be 3.9
-
-  ```
-
-  2. Install pip
-  ```bash
-  wget https://bootstrap.pypa.io/get-pip.py
-  python get-pip.py
-  ```
-
-  3. Install torch
-  ```bash
-  pip3 install -U torch --index-url https://download.pytorch.org/whl/cu118
-  ```
-
-  4. Axolotl
-  ```bash
-  git clone https://github.com/OpenAccess-AI-Collective/axolotl
-  cd axolotl
-
-  pip3 install -e . # change depend on needs
-  pip3 install protobuf==3.20.3
-  pip3 install -U requests
-  pip3 install -U --ignore-installed psutil
-  pip3 install -U scipy
-  pip3 install git+https://github.com/huggingface/peft.git # not for gptq
-  ```
-
-  5. Set path
-  ```bash
-  export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
-  ```
-  </details>
+      - `pip3 install -e .` (recommended, supports QLoRA, no gptq/int4 support)
+      - `pip3 install -e .[gptq]` (next best if you don't need QLoRA, but want to use gptq)
+      - `pip3 install -e .[gptq_triton]`
 
 ### Dataset
 
@@ -136,7 +73,7 @@ Have dataset(s) in one of the following format (JSONL recommended):
   ```json
   {"instruction": "...", "input": "...", "output": "..."}
   ```
-- `sharegpt:chat`: conversations
+- `sharegpt`: conversations
   ```json
   {"conversations": [{"from": "...", "value": "..."}]}
   ```
@@ -177,73 +114,16 @@ Have dataset(s) in one of the following format (JSONL recommended):
   ```json
   {"article": "...", "summary": "..."}
   ```
-- `alpaca_chat`: basic instruct for alpaca chat
-  ```json
-  {"instruction": "...", "input": "...", "response": "..."}
-  ```
-- `alpaca_chat.load_qa`: question and answer for alpaca chat
-  ```json
-  {"question": "...", "answer": "..."}
-  ```
-- `alpaca_chat.load_concise`: question and answer for alpaca chat, for concise answers
-  ```json
-  {"instruction": "...", "input": "...", "response": "..."}
-  ```
-- `alpaca_chat.load_camel_ai`: question and answer for alpaca chat, for load_camel_ai
-  ```json
-  {"message_1": "...", "message_2": "..."}
-  ```
-- `alpaca_w_system.load_open_orca`: support for open orca datasets with included system prompts, instruct
-  ```json
-  {"system_prompt": "...", "question": "...", "response": "..."}
-  ```
-- `context_qa`: in context question answering from an article
-  ```json
-  {"article": "...", "question": "...", "answer": "..."}
-  ```
-- `context_qa.load_404`: in context question answering from an article, with default response for no answer from context
-  ```json
-  {"article": "...", "unanswerable_question": "..."}
-  ```
-- `creative_acr.load_answer`: instruction and revision
-  ```json
-  {"instruction": "...", "revision": "..."}
-  ```
-- `creative_acr.load_critique`: critique
-  ```json
-  {"scores": "...", "critiques": "...", "instruction": "...", "answer": "..."}
-  ```
-- `creative_acr.load_revise`: critique and revise
-  ```json
-  {"scores": "...", "critiques": "...", "instruction": "...", "answer": "...", "revision": "..."}
-  ```
-- `pygmalion`: pygmalion
-  ```json
-  {"conversations": [{"role": "...", "value": "..."}]}
-  ```
-- `sharegpt_simple.load_role`: conversations where `role` is used instead of `from`
-  ```json
-  {"conversations": [{"role": "...", "value": "..."}]}
-  ```
-- `sharegpt_jokes`: creates a chat where bot is asked to tell a joke, then explain why the joke is funny
-  ```json
-  {"conversations": [{"title": "...", "text": "...", "explanation": "..."}]}
-  ```
+
+> Have some new format to propose? Check if it's already defined in [data.py](src/axolotl/utils/data.py) in `dev` branch!
 
 </details>
 
-#### How to add custom prompts
-
-  1. Add your method to a file in [prompt_strategies](src/axolotl/prompt_strategies). Please see other files as example.
-  2. Use your custom file name as the dataset type `<prompt_strategies_file>.load_<load_fn>`.
-
 Optionally, download some datasets, see [data/README.md](data/README.md)
 
-
-
 ### Config
 
-See [examples](examples) for quick start. It is recommended to duplicate and modify to your needs. The most important options are:
+See sample configs in [configs](configs) folder or [examples](examples) for quick start. It is recommended to duplicate and modify to your needs. The most important options are:
 
 - model
   ```yaml
@@ -253,24 +133,10 @@ See [examples](examples) for quick start. It is recommended to duplicate and mod
 
 - dataset
   ```yaml
-  sequence_len: 2048 # max token length for prompt
-
-  # huggingface repo
   datasets:
-    - path: vicgalle/alpaca-gpt4
-      type: alpaca # format from earlier
-
-  # huggingface repo with specific configuration/subset
-  datasets:
-    - path: EleutherAI/pile
-      name: enron_emails
-      type: completion # format from earlier
-
-  # local
-  datasets:
-    - path: json
-      data_files: data.jsonl # or json
+    - path: vicgalle/alpaca-gpt4 # local or huggingface repo
       type: alpaca # format from earlier
+  sequence_len: 2048 # max token length / prompt
   ```
 
 - loading
@@ -280,8 +146,6 @@ See [examples](examples) for quick start. It is recommended to duplicate and mod
   bf16: true # require >=ampere
   fp16: true
   tf32: true # require >=ampere
-  bfloat16: true # require >=ampere, use instead of bf16 when you don't want AMP (automatic mixed precision)
-  float16: true # use instead of fp16 when you don't want AMP
   ```
   Note: Repo does not do 4-bit quantization.
 
@@ -309,8 +173,6 @@ base_model_ignore_patterns:
 # if the base_model repo on hf hub doesn't include configuration .json files,
 # you can set that here, or leave this empty to default to base_model
 base_model_config: ./llama-7b-hf
-# you can specify to choose a specific model revision from huggingface hub
-model_revision:
 # Optional tokenizer configuration override in case you want to use a different tokenizer
 # than the one defined in the base model
 tokenizer_config:
@@ -320,11 +182,6 @@ model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
 # Trust remote code for untrusted source
 trust_remote_code:
-# use_fast option for tokenizer loading from_pretrained, default to True
-tokenizer_use_fast:
-# resize the model embeddings when new tokens are added to multiples of 32
-# this is reported to improve training speed on some models
-resize_token_embeddings_to_32x:
 
 # whether you are training a 4-bit GPTQ quantized model
 gptq: true
@@ -345,21 +202,18 @@ tf32: true # require >=ampere
 
 # a list of one or more datasets to finetune the model with
 datasets:
-  # hf dataset repo | "json" for local dataset, make sure to fill data_files
+  # this can be either a hf dataset, or relative path
   - path: vicgalle/alpaca-gpt4
   # The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection]
-    type: alpaca # format | format:<prompt_style> (chat/instruct) | <prompt_strategies>.load_<load_fn>
+    type: alpaca # format OR format:prompt_style (chat/instruct)
     data_files: # path to source data files
     shards: # number of shards to split data into
-    name: # name of dataset configuration to load
 
 # axolotl attempts to save the dataset as an arrow after packing the data together so
 # subsequent training attempts load faster, relative path
 dataset_prepared_path: data/last_run_prepared
 # push prepared dataset to hub
 push_dataset_to_hub: # repo path
-# push checkpoints to hub
-hub_model_id: # repo path to push finetuned model
 # whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
 # required to be true when used in combination with `push_dataset_to_hub`
 hf_use_auth_token: # boolean
@@ -375,10 +229,7 @@ dataset_shard_idx:
 sequence_len: 2048
 # max sequence length to concatenate training samples together up to
 # inspired by StackLLaMA. see https://huggingface.co/blog/stackllama#supervised-fine-tuning
-# soon to be DEPRECATED
 max_packed_sequence_len: 1024
-# use efficient multi-packing with block diagonal attention and per sequence position_ids
-sample_packing:
 
 # if you want to use 'lora' or 'qlora' or leave blank to train all parameters in original model
 adapter: lora
@@ -421,18 +272,13 @@ num_epochs: 3
 warmup_steps: 100
 learning_rate: 0.00003
 logging_steps:
-save_steps:
-eval_steps:
-
-# save model as safetensors (require safetensors package)
-save_safetensors:
 
 # whether to mask out or include the human's prompt from the training labels
 train_on_inputs: false
 # don't use this, leads to wonky training (according to someone on the internet)
 group_by_length: false
 
-# Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing
+# does not work with current implementation of 4-bit LoRA
 gradient_checkpointing: false
 
 # stop training after this many evaluation losses have increased in a row
@@ -454,15 +300,7 @@ log_sweep_max_lr:
 optimizer:
 # specify weight decay
 weight_decay:
-# adamw hyperparams
-adam_beta1:
-adam_beta2:
-adam_epsilon:
-# Gradient clipping max norm
-max_grad_norm:
 
-# whether to bettertransformers
-flash_optimum:
 # whether to use xformers attention patch https://github.com/facebookresearch/xformers:
 xformers_attention:
 # whether to use flash attention patch https://github.com/HazyResearch/flash-attention:
@@ -470,11 +308,6 @@ flash_attention:  # require a100 for llama
 # whether to use scaled-dot-product attention
 # https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html
 sdp_attention:
-# Landmark attention (only llama)
-landmark_attention:
-# xpos RoPE see https://github.com/kaiokendev/cutoff-len-is-context-len/blob/main/util/xpos_rope_llama_monkey_patch.py
-# llama only
-xpos_rope:
 
 # resume from a specific checkpoint dir
 resume_from_checkpoint:
@@ -518,6 +351,17 @@ strict:
 
 </details>
 
+### Accelerate
+
+Configure accelerate
+
+```bash
+accelerate config
+
+# Edit manually
+# nano ~/.cache/huggingface/accelerate/default_config.yaml
+```
+
 ### Train
 
 Run
@@ -525,37 +369,17 @@ Run
 accelerate launch scripts/finetune.py configs/your_config.yml
 ```
 
-#### Multi-GPU Config
-
-- llama FSDP
-```yaml
-fsdp:
-  - full_shard
-  - auto_wrap
-fsdp_config:
-  fsdp_offload_params: true
-  fsdp_state_dict_type: FULL_STATE_DICT
-  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
-```
-
-- llama Deepspeed: append `ACCELERATE_USE_DEEPSPEED=true` in front of finetune command
-
 ### Inference
 
 Pass the appropriate flag to the train command:
 
 - Pretrained LORA:
   ```bash
-  --inference --lora_model_dir="./lora-output-dir"
+  --inference --lora_model_dir ./completed-model
   ```
 - Full weights finetune:
   ```bash
-  --inference --base_model="./completed-model"
-  ```
-- Full weights finetune w/ a prompt from a text file:
-  ```bash
-  cat /tmp/prompt.txt | python scripts/finetune.py configs/your_config.yml \
-    --base_model="./completed-model" --inference --prompter=None --load_in_8bit=True
+  --inference --base_model ./completed-model
   ```
 
 ### Merge LORA to base
@@ -566,12 +390,6 @@ Add below flag to train command above
 --merge_lora --lora_model_dir="./completed-model" --load_in_8bit=False --load_in_4bit=False
 ```
 
-If you run out of CUDA memory, you can try to merge in system RAM with
-
-```bash
-CUDA_VISIBLE_DEVICES="" python3 scripts/finetune.py ...
-```
-
 ## Common Errors 🧰
 
 > Cuda out of memory
@@ -579,7 +397,6 @@ CUDA_VISIBLE_DEVICES="" python3 scripts/finetune.py ...
 Please reduce any below
   - `micro_batch_size`
   - `eval_batch_size`
-  - `gradient_accumulation_steps`
   - `sequence_len`
 
 > RuntimeError: expected scalar type Float but found Half
@@ -590,11 +407,7 @@ Try set `fp16: true`
 
 Try to turn off xformers.
 
-> accelerate config missing
-
-It's safe to ignore it.
-
-## Need help? 🙋♂️
+## Need help? 🙋‍♂️
 
 Join our [Discord server](https://discord.gg/HhrNrHJPRb) where we can help you
 
@@ -608,16 +421,6 @@ Building something cool with Axolotl? Consider adding a badge to your model card
 
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 
-## Community Showcase
-
-Open Access AI Collective
-- [Minotaur 13b](https://huggingface.co/openaccess-ai-collective/minotaur-13b)
-- [Manticore 13b](https://huggingface.co/openaccess-ai-collective/manticore-13b)
-- [Hippogriff 30b](https://huggingface.co/openaccess-ai-collective/hippogriff-30b-chat)
-
-PocketDoc Labs
-- [Dan's PersonalityEngine 13b LoRA](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-13b-LoRA)
-
 ## Contributing 🤝
 
 Bugs? Please check for open issue else create a new [Issue](https://github.com/OpenAccess-AI-Collective/axolotl/issues/new).

configs/accelerate/default_config.yaml

@@ -0,0 +1,15 @@
+compute_environment: LOCAL_MACHINE
+distributed_type: 'NO'
+downcast_bf16: 'no'
+gpu_ids: all
+machine_rank: 0
+main_training_function: main
+mixed_precision: bf16
+num_machines: 1
+num_processes: 1
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

configs/cerebras_1_3B_alpaca.yml

@@ -0,0 +1,40 @@
+base_model: cerebras/Cerebras-GPT-1.3B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+load_in_8bit: true
+datasets:
+  - path: data/alpaca_data_gpt4.jsonl
+    type: alpaca
+  - path: data/vicuna_cleaned.jsonl
+    type: sharegpt
+  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
+    type: gpteacher
+  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
+    type: gpteacher
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.05
+adapter: lora
+sequence_len: 2048
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - c_attn
+lora_fan_in_fan_out: false
+wandb_project: pythia-1.4b-lora
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./lora-alpaca
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 5
+learning_rate: 0.0003
+train_on_inputs: false
+group_by_length: false
+bf16: True
+tf32: True
+gradient_checkpointing:
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:

configs/galactica_1_3B.yml

@@ -0,0 +1,41 @@
+base_model: facebook/galactica-1.3b
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+load_in_8bit: false
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+adapter:
+lora_model_dir:
+sequence_len: 1024
+max_packed_sequence_len: 1024
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+lora_fan_in_fan_out: false
+wandb_project:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./lora-llama-alpaca
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+num_epochs: 3
+learning_rate: 0.00003
+train_on_inputs: false
+group_by_length: false
+bf16: false
+tf32: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+tokens:
+  pad_token: "[PAD]"
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

configs/llama_13B_alpaca.yml

@@ -0,0 +1,39 @@
+base_model: huggyllama/llama-13b
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: true
+datasets:
+  - path: anon8231489123/ShareGPT_Vicuna_unfiltered
+    data_files: ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json
+    type: sharegpt
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.002
+adapter:
+lora_model_dir:
+sequence_len: 2048
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+lora_fan_in_fan_out: false
+wandb_project:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./llama-13b-sharegpt
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+warmup_steps: 1000
+save_steps:
+eval_steps:
+num_epochs: 5
+learning_rate: 0.00003
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+early_stopping_patience: 5
+resume_from_checkpoint:
+local_rank:

configs/llama_65B_alpaca.yml

@@ -0,0 +1,44 @@
+base_model: huggyllama/llama-65b
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: true
+datasets:
+  - path: data/alpaca_data_gpt4.jsonl
+    type: alpaca
+  - path: anon8231489123/ShareGPT_Vicuna_unfiltered
+    data_files: ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json
+    type: sharegpt
+  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
+    type: gpteacher
+  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
+    type: gpteacher
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.04
+adapter: lora
+lora_model_dir:
+sequence_len: 2048
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+lora_fan_in_fan_out: false
+wandb_project: llama-65b-lora
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./lora-llama-alpaca
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+warmup_steps: 1000
+save_steps:
+num_epochs: 5
+learning_rate: 0.00003
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:

configs/llama_7B_4bit.yml

@@ -0,0 +1,45 @@
+base_model: decapoda-research/llama-7b-hf-int4
+base_model_config: decapoda-research/llama-7b-hf
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: true
+datasets:
+  - path: tatsu-lab/alpaca  # original alpaca dataset
+    type: alpaca
+dataset_prepared_path: data/last_run_prepared
+val_set_size: 0.04
+adapter: lora
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len: 1024
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+#  - k_proj
+#  - o_proj
+lora_fan_in_fan_out: false
+wandb_project:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./lora-test
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+num_epochs: 3
+warmup_steps: 100
+learning_rate: 0.00003
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+gradient_checkpointing: false
+early_stopping_patience: 3
+resume_from_checkpoint:
+auto_resume_from_checkpoints: true
+local_rank:
+load_4bit: true
+xformers_attention: true
+flash_attention:

configs/llama_7B_alpaca.yml

@@ -0,0 +1,41 @@
+base_model: huggyllama/llama-7b
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: true
+datasets:
+  - path: data/alpaca_data_gpt4.jsonl
+    type: alpaca
+  - path: data/vicuna_cleaned.jsonl
+    type: sharegpt
+  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
+    type: gpteacher
+  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
+    type: gpteacher
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.04
+adapter: lora
+lora_model_dir:
+sequence_len: 2048
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+lora_fan_in_fan_out: false
+wandb_project: llama-7b-lora
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./lora-llama-alpaca
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+num_epochs: 5
+learning_rate: 0.00003
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:

configs/llama_7B_jeopardy.yml

@@ -7,28 +7,30 @@ datasets:
   - path: openaccess-ai-collective/jeopardy
     type: jeopardy
 dataset_prepared_path: last_run_prepared
-val_set_size: 0.02
+val_set_size: 0.01
 adapter:
 lora_model_dir:
-sequence_len: 512
-max_packed_sequence_len:
-lora_r:
-lora_alpha:
-lora_dropout:
+sequence_len: 2048
+max_packed_sequence_len: 2048
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
 lora_target_modules:
+  - q_proj
+  - v_proj
 lora_fan_in_fan_out: false
-wandb_project:
+wandb_project: jeopardy-bot-7b
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
 output_dir: ./jeopardy-bot-7b
-gradient_accumulation_steps: 1
+gradient_accumulation_steps: 2
 micro_batch_size: 1
-num_epochs: 3
+num_epochs: 2
 optimizer: adamw_bnb_8bit
 torchdistx_path:
 lr_scheduler: cosine
-learning_rate: 0.00003
+learning_rate: 0.0000002
 train_on_inputs: false
 group_by_length: false
 bf16: true
@@ -46,10 +48,11 @@ eval_steps: 110
 save_steps: 660
 debug:
 deepspeed:
-weight_decay: 0.1
+weight_decay: 0.0001
 fsdp:
 fsdp_config:
 tokens:
+  pad_token: "[PAD]"
   bos_token: "<s>"
   eos_token: "</s>"
   unk_token: "<unk>"

configs/pythia_1_2B_alpaca.yml

@@ -1,29 +1,36 @@
 base_model: EleutherAI/pythia-1.4b-deduped
-base_model_config: EleutherAI/pythia-1.4b-deduped
+model_type: GPTNeoXForCausalLM
+tokenizer_type: AutoTokenizer
 load_in_8bit: true
 datasets:
-  - path: teknium/GPT4-LLM-Cleaned
+  - path: data/alpaca_data_gpt4.jsonl
     type: alpaca
+  - path: data/vicuna_cleaned.jsonl
+    type: sharegpt
+  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
+    type: gpteacher
+  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
+    type: gpteacher
 dataset_prepared_path: last_run_prepared
 val_set_size: 0.05
 adapter: lora
 lora_model_dir:
-sequence_len: 512
-lora_r: 16
+sequence_len: 2048
+lora_r: 8
 lora_alpha: 32
 lora_dropout: 0.05
 lora_target_modules:
   - query_key_value
-lora_target_linear:
+#  - xxx
 lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
-wandb_project:
+wandb_project: pythia-1.4b-lora
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
-output_dir: ./lora-alpaca-pythia
+output_dir: ./lora-alpaca
 gradient_accumulation_steps: 1
 micro_batch_size: 4
-num_epochs: 3
+num_epochs: 5
 learning_rate: 0.00001
 train_on_inputs: false
 group_by_length: false
@@ -32,6 +39,3 @@ tf32: True
 early_stopping_patience:
 resume_from_checkpoint:
 local_rank:
-weight_decay: 0.1
-eval_steps: 20
-logging_steps: 1

configs/quickstart.yml

@@ -0,0 +1,45 @@
+base_model: decapoda-research/llama-7b-hf-int4
+base_model_config: decapoda-research/llama-7b-hf
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: true
+datasets:
+  - path: tatsu-lab/alpaca  # original alpaca dataset
+    type: alpaca
+dataset_prepared_path: data/last_run_prepared
+val_set_size: 0.04
+adapter: lora
+lora_model_dir:
+sequence_len: 1024
+max_packed_sequence_len: 1024
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+#  - k_proj
+#  - o_proj
+lora_fan_in_fan_out: false
+wandb_project:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./lora-test
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 3
+warmup_steps: 100
+learning_rate: 0.00003
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+gradient_checkpointing: false
+early_stopping_patience: 3
+resume_from_checkpoint:
+auto_resume_from_checkpoints: true
+local_rank:
+gptq: true
+xformers_attention: true
+flash_attention:

configs/sample.yml

@@ -0,0 +1,87 @@
+# this is the huggingface model that contains *.pt, *.safetensors, or *.bin files
+# this can also be a relative path to a model on disk
+base_model: decapoda-research/llama-7b-hf-int4
+# you can specify an ignore pattern if the model repo contains more than 1 model type (*.pt, etc)
+base_model_ignore_patterns:
+# if the base_model repo on hf hub doesn't include configuration .json files,
+# you can set that here, or leave this empty to default to base_model
+base_model_config: decapoda-research/llama-7b-hf
+# If you want to specify the type of model to load, AutoModelForCausalLM is a good choice too
+model_type: AutoModelForCausalLM
+# Corresponding tokenizer for the model AutoTokenizer is a good choice
+tokenizer_type: AutoTokenizer
+# whether you are training a 4-bit quantized model
+load_4bit: true
+# this will attempt to quantize the model down to 8 bits and use adam 8 bit optimizer
+load_in_8bit: true
+# a list of one or more datasets to finetune the model with
+datasets:
+  # this can be either a hf dataset, or relative path
+  - path: vicgalle/alpaca-gpt4
+  # The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection]
+    type: alpaca
+# axolotl attempts to save the dataset as an arrow after packing the data together so
+# subsequent training attempts load faster, relative path
+dataset_prepared_path: data/last_run_prepared
+# How much of the dataset to set aside as evaluation. 1 = 100%, 0.50 = 50%, etc
+val_set_size: 0.04
+# if you want to use lora, leave blank to train all parameters in original model
+adapter: lora
+# if you already have a lora model trained that you want to load, put that here
+lora_model_dir:
+# the maximum length of an input to train with, this should typically be less than 2048
+# as most models have a token/context limit of 2048
+sequence_len: 2048
+# max sequence length to concatenate training samples together up to
+# inspired by StackLLaMA. see https://huggingface.co/blog/stackllama#supervised-fine-tuning
+max_packed_sequence_len: 1024
+# lora hyperparameters
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+#  - k_proj
+#  - o_proj
+lora_fan_in_fan_out: false
+# wandb configuration if your're using it
+wandb_project:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+# where to save the finsihed model to
+output_dir: ./completed-model
+# training hyperparameters
+gradient_accumulation_steps: 1
+batch_size:
+micro_batch_size: 2
+num_epochs: 3
+warmup_steps: 100
+learning_rate: 0.00003
+# whether to mask out or include the human's prompt from the training labels
+train_on_inputs: false
+# don't use this, leads to wonky training (according to someone on the internet)
+group_by_length: false
+# Use CUDA bf16
+bf16: true
+# Use CUDA tf32
+tf32: true
+# does not work with current implementation of 4-bit LoRA
+gradient_checkpointing: false
+# stop training after this many evaluation losses have increased in a row
+# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback
+early_stopping_patience: 3
+# specify a scheduler to use with the optimizer. only one_cycle is supported currently
+lr_scheduler:
+# whether to use xformers attention patch https://github.com/facebookresearch/xformers:
+xformers_attention:
+# whether to use flash attention patch https://github.com/HazyResearch/flash-attention:
+flash_attention:
+# resume from a specific checkpoint dir
+resume_from_checkpoint:
+# if resume_from_checkpoint isn't set and you simply want it to start where it left off
+# be careful with this being turned on between different models
+auto_resume_from_checkpoints: false
+# don't mess with this, it's here for accelerate and torchrun
+local_rank:

configs/stability_3b.yml

@@ -0,0 +1,56 @@
+base_model: stabilityai/stablelm-base-alpha-3b
+base_model_config: stabilityai/stablelm-base-alpha-3b
+load_in_8bit: false
+datasets:
+  - path: vicgalle/alpaca-gpt4
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.04
+adapter:
+lora_model_dir:
+sequence_len: 4096
+max_packed_sequence_len: 4096
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+lora_fan_in_fan_out: false
+wandb_project: stable-alpaca-3b
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./stable-alpaca-3b
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0000002
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention: true
+flash_attention:
+gptq_groupsize:
+gptq_model_v1:
+warmup_steps: 100
+eval_steps: 50
+save_steps: 200
+debug:
+deepspeed:
+weight_decay: 0.01
+fsdp:
+fsdp_config:
+#tokens:
+#  pad_token: "[PAD]"
+#  bos_token: "<s>"
+#  eos_token: "</s>"
+#  unk_token: "<unk>"

configs/vicuna_13B_4bit_reflect.yml

@@ -0,0 +1,45 @@
+base_model: anon8231489123/vicuna-13b-GPTQ-4bit-128g
+base_model_config: anon8231489123/vicuna-13b-GPTQ-4bit-128g
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: false
+load_4bit: true
+gptq_groupsize: 128
+gptq_model_v1: false
+datasets:
+# https://github.com/vaguenebula/AlpacaDataReflect/blob/main/alpaca_reflect_pruned.json
+  - path: data/alpaca_reflect_pruned.jsonl
+    type: reflection
+dataset_prepared_path: data/last_run_prepared
+val_set_size: 0.04
+adapter: lora
+lora_model_dir:
+sequence_len: 2048
+max_packed_sequence_len: 2048
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+#  - k_proj
+#  - o_proj
+lora_fan_in_fan_out: false
+wandb_project:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+output_dir: ./lora-reflect
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+num_epochs: 3
+learning_rate: 0.00003
+train_on_inputs: false
+group_by_length: false
+bf16: true
+tf32: true
+gradient_checkpointing: false
+early_stopping_patience: 3
+resume_from_checkpoint:
+local_rank:
+flash_attention: true

data/README.md

@@ -10,10 +10,10 @@ curl https://github.com/teknium1/GPTeacher/blob/main/Roleplay/roleplay-similarit
 ## Convert the JSON data files to JSONL.
 
 ```shell
-python3 ./scripts/alpaca_json_to_jsonl.py --file data/alpaca_data_gpt4.json --output data/alpaca_data_gpt4.jsonl
-python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/vicuna_cleaned.json --output data/vicuna_cleaned.jsonl
-python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/roleplay-similarity_0.6-instruct-dataset.json --output data/roleplay-similarity_0.6-instruct-dataset.jsonl
-python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/gpt4-instruct-similarity-0.6-dataset.json --output data/gpt4-instruct-similarity-0.6-dataset.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --input data/alpaca_data_gpt4.json > data/alpaca_data_gpt4.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/vicuna_cleaned.json > data/vicuna_cleaned.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/roleplay-similarity_0.6-instruct-dataset.json > data/roleplay-similarity_0.6-instruct-dataset.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/gpt4-instruct-similarity-0.6-dataset.json > data/gpt4-instruct-similarity-0.6-dataset.jsonl
 ```
 ---
 

docker-compose.yaml

@@ -1,20 +0,0 @@
-# version: '3.8'
-services:
-  axolotl:
-    build:
-      context: .
-      dockerfile: ./docker/Dockerfile
-    volumes:
-      - .:/workspace/axolotl
-      - ~/.cache/huggingface/:/root/.cache/huggingface/
-    # set environment variables
-    environment:
-      - WANDB_API_KEY=${WANDB_API_KEY}
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              # count: 1
-              capabilities: [gpu]
-    command: tail -f /dev/null

docker/Dockerfile

@@ -3,16 +3,18 @@ FROM winglian/axolotl-base:$BASE_TAG
 
 ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
 ARG AXOLOTL_EXTRAS=""
-ARG CUDA="118"
-ENV BNB_CUDA_VERSION=$CUDA
 
 RUN apt-get update && \
     apt-get install -y vim curl
 
 WORKDIR /workspace
 
-RUN pip3 install --force-reinstall "peft @ git+https://github.com/huggingface/peft.git@main"
-RUN git clone --depth=1 https://github.com/OpenAccess-AI-Collective/axolotl.git
+RUN pip3 install --force-reinstall "peft @ git+https://github.com/huggingface/peft.git@main" \
+            "accelerate @ git+https://github.com/huggingface/accelerate.git@main" \
+            "transformers @ git+https://github.com/huggingface/transformers.git@main"
+
+RUN mkdir axolotl
+COPY . axolotl/
 # If AXOLOTL_EXTRAS is set, append it in brackets
 RUN cd axolotl && \
     if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
@@ -21,10 +23,5 @@ RUN cd axolotl && \
         pip install -e .; \
     fi
 
-# fix so that git fetch/pull from remote works
-RUN cd axolotl && \
-    git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
-    git config --get remote.origin.fetch
-
 # helper for huggingface-login cli
 RUN git config --global credential.helper store

docker/Dockerfile-base

@@ -8,7 +8,7 @@ FROM nvidia/cuda:$CUDA_VERSION-cudnn$CUDNN_VERSION-devel-ubuntu$UBUNTU_VERSION a
 ENV PATH="/root/miniconda3/bin:${PATH}"
 
 ARG PYTHON_VERSION="3.9"
-ARG PYTORCH_VERSION="2.0.1"
+ARG PYTORCH="2.0.0"
 ARG CUDA="118"
 
 ENV PYTHON_VERSION=$PYTHON_VERSION
@@ -29,18 +29,17 @@ ENV PATH="/root/miniconda3/envs/py${PYTHON_VERSION}/bin:${PATH}"
 WORKDIR /workspace
 
 RUN python3 -m pip install --upgrade pip && pip3 install packaging && \
-    python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} --extra-index-url https://download.pytorch.org/whl/cu$CUDA
+    python3 -m pip install --no-cache-dir -U torch==${PYTORCH} torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu$CUDA
 
 
 FROM base-builder AS flash-attn-builder
 
 WORKDIR /workspace
 
-ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
+ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
 
-RUN git clone https://github.com/Dao-AILab/flash-attention.git && \
+RUN git clone https://github.com/HazyResearch/flash-attention.git && \
     cd flash-attention && \
-    git checkout v2.0.1  && \
     python3 setup.py bdist_wheel && \
     cd csrc/fused_dense_lib && \
     python3 setup.py bdist_wheel && \
@@ -53,7 +52,7 @@ RUN git clone https://github.com/Dao-AILab/flash-attention.git && \
 
 FROM base-builder AS deepspeed-builder
 
-ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
+ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
 
 WORKDIR /workspace
 
@@ -74,14 +73,11 @@ RUN git clone https://github.com/TimDettmers/bitsandbytes.git && \
 
 FROM base-builder
 
-ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
-ENV TORCH_CUDA_ARCH_LIST=$TORCH_CUDA_ARCH_LIST
-
 # recompile apex
 RUN python3 -m pip uninstall -y apex
 RUN git clone https://github.com/NVIDIA/apex
 #  `MAX_JOBS=1` disables parallel building to avoid cpu memory OOM when building image on GitHub Action (standard) runners
-RUN cd apex && MAX_JOBS=1 python3 -m pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./
+RUN cd apex && MAX_JOBS=1 python3 -m pip install --global-option="--cpp_ext" --global-option="--cuda_ext" --no-cache -v --disable-pip-version-check .
 
 RUN mkdir -p /workspace/builds
 COPY --from=bnb-builder /workspace/bitsandbytes /workspace/builds/bitsandbytes
@@ -101,4 +97,4 @@ RUN cd /workspace/builds/bitsandbytes && python3 setup.py install
 RUN git lfs install --skip-repo
 RUN pip3 install awscli && \
     # The base image ships with `pydantic==1.8.2` which is not working
-    pip3 install -U --no-cache-dir pydantic==1.10.10
+    pip3 install -U --no-cache-dir pydantic

docker/Dockerfile-runpod

@@ -1,10 +1,6 @@
 ARG BASE_TAG=main
 FROM winglian/axolotl:$BASE_TAG
 
-ENV HF_DATASETS_CACHE="/workspace/data/huggingface-cache/datasets"
-ENV HUGGINGFACE_HUB_CACHE="/workspace/data/huggingface-cache/hub"
-ENV TRANSFORMERS_CACHE="/workspace/data/huggingface-cache/hub"
-
 COPY scripts/runpod-entrypoint.sh /root/runpod-entrypoint.sh
 
 RUN apt install --yes --no-install-recommends openssh-server tmux && \

ds_config.json

@@ -37,18 +37,18 @@
       "lr": "auto",
       "betas": [
         0.9,
-        0.95
+        0.999
       ],
       "eps": 1e-8,
       "weight_decay": "auto"
     }
   },
   "scheduler": {
-    "type": "WarmupLR",
+    "type": "OneCycle",
     "params": {
-      "warmup_min_lr": "auto",
-      "warmup_max_lr": "auto",
-      "warmup_num_steps": "auto"
+      "cycle_min_lr": 0.00001,
+      "cycle_max_lr": 0.00003,
+      "cycle_first_step_size": 120
     }
   },
   "train_batch_size": "auto",

examples/cerebras/qlora.yml

@@ -1,60 +0,0 @@
-base_model: cerebras/Cerebras-GPT-1.3B
-base_model_config: cerebras/Cerebras-GPT-1.3B
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-push_dataset_to_hub:
-datasets:
-  - path: teknium/GPT4-LLM-Cleaned
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-adapter: qlora
-lora_model_dir:
-sequence_len: 2048
-max_packed_sequence_len: 2048
-lora_r: 16
-lora_alpha: 32
-lora_dropout: 0.05
-lora_target_modules:
-  - c_fc
-  - c_attn
-  - c_proj
-lora_target_linear:
-lora_fan_in_fan_out:
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./qlora-out
-batch_size: 4
-micro_batch_size: 4
-num_epochs: 2
-optimizer: paged_adamw_8bit
-torchdistx_path:
-lr_scheduler: cosine
-learning_rate: 0.0002
-train_on_inputs: false
-group_by_length: true
-bf16: true
-fp16: false
-tf32: true
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention: true
-flash_attention:
-gptq_groupsize:
-gptq_model_v1:
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.1
-fsdp:
-fsdp_config:
-special_tokens:
-  pad_token: "<|endoftext|>"

examples/falcon/config-7b-lora.yml

@@ -23,7 +23,7 @@ lora_dropout: 0.0
 lora_target_modules:
 lora_target_linear: true
 lora_fan_in_fan_out:
-wandb_project:
+wandb_project: falcon-7b
 wandb_watch:
 wandb_run_id:
 wandb_log_model:

examples/falcon/config-7b-qlora.yml

@@ -1,92 +0,0 @@
-# 1b: tiiuae/falcon-rw-1b
-# 40b: tiiuae/falcon-40b
-base_model: tiiuae/falcon-7b
-base_model_config: tiiuae/falcon-7b
-# required by falcon custom model code: https://huggingface.co/tiiuae/falcon-7b/tree/main
-trust_remote_code: true
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-load_in_8bit: false
-# enable 4bit for QLoRA
-load_in_4bit: true
-gptq: false
-strict: false
-push_dataset_to_hub:
-datasets:
-  - path: QingyiSi/Alpaca-CoT
-    data_files:
-      - Chain-of-Thought/formatted_cot_data/gsm8k_train.json
-    type: "alpaca:chat"
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-# enable QLoRA
-adapter: qlora
-lora_model_dir:
-sequence_len: 2048
-max_packed_sequence_len:
-
-# hyperparameters from QLoRA paper Appendix B.2
-# "We find hyperparameters to be largely robust across datasets"
-lora_r: 64
-lora_alpha: 16
-# 0.1 for models up to 13B
-# 0.05 for 33B and 65B models
-lora_dropout: 0.05
-# add LoRA modules on all linear layers of the base model
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./qlora-out
-
-# QLoRA paper Table 9
-# - 16 for 7b & 13b
-# - 32 for 33b, 64 for 64b
-# Max size tested on A6000
-# - 7b: 40
-# - 40b: 4
-# decrease if OOM, increase for max VRAM utilization
-micro_batch_size: 1
-gradient_accumulation_steps: 2
-num_epochs: 3
-# Optimizer for QLoRA
-optimizer: paged_adamw_32bit
-torchdistx_path:
-lr_scheduler: cosine
-# QLoRA paper Table 9
-# - 2e-4 for 7b & 13b
-# - 1e-4 for 33b & 64b
-learning_rate: 0.0002
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: true
-gradient_checkpointing: true
-# stop training after this many evaluation losses have increased in a row
-# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback
-early_stopping_patience: 3
-resume_from_checkpoint:
-auto_resume_from_checkpoints: true
-local_rank:
-logging_steps: 1
-xformers_attention: true
-flash_attention:
-gptq_groupsize:
-gptq_model_v1:
-warmup_steps: 10
-eval_steps: 5
-save_steps: 10
-debug:
-deepspeed:
-weight_decay: 0.000001
-fsdp:
-fsdp_config:
-special_tokens:
-  pad_token: "<|endoftext|>"
-  bos_token: ">>ABSTRACT<<"
-  eos_token: "<|endoftext|>"

examples/falcon/config-7b.yml

@@ -23,7 +23,7 @@ lora_dropout: 0.0
 lora_target_modules:
 lora_target_linear: true
 lora_fan_in_fan_out:
-wandb_project:
+wandb_project: falcon-7b
 wandb_watch:
 wandb_run_id:
 wandb_log_model:

examples/gptj/qlora.yml

@@ -1,57 +0,0 @@
-base_model: EleutherAI/gpt-j-6b
-base_model_config: EleutherAI/gpt-j-6b
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-push_dataset_to_hub:
-datasets:
-  - path: teknium/GPT4-LLM-Cleaned
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-adapter: qlora
-lora_model_dir:
-sequence_len: 2048
-max_packed_sequence_len:
-lora_r: 8
-lora_alpha: 32
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./qlora-out
-gradient_accumulation_steps: 2
-micro_batch_size: 2
-num_epochs: 2
-optimizer: paged_adamw_8bit
-torchdistx_path:
-lr_scheduler: cosine
-learning_rate: 0.0001
-train_on_inputs: false
-group_by_length: true
-bf16: true
-fp16: false
-tf32: true
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention: true
-flash_attention:
-gptq_groupsize:
-gptq_model_v1:
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.1
-fsdp:
-fsdp_config:
-special_tokens:
-  pad_token: "<|endoftext|>"

examples/gptq-lora-7b/README.md

@@ -3,6 +3,6 @@
 This is a good place to start for beginners. This will run on an NVIDIA RTX4090 with no other changes needed.
 
 ```shell
-accelerate launch scripts/finetune.py examples/gptq-lora-7b/config.yml
+accelerate launch scripts/finetune.py examples/4bit-lora-7b/config.yml
 
 ```

examples/llama-2/README.md

@@ -1,20 +0,0 @@
-# Overview
-
-This is an example of a llama-2 configuration for 7b and 13b. The yaml file contains configuration for the 7b variant, but you can just aswell use the same settings for 13b.
-
-The 7b variant fits on any 24GB VRAM GPU and will take up about 17 GB of VRAM during training if using qlora and 20 GB if using lora. On a RTX 4090 it trains 3 epochs of the default dataset in about 15 minutes.
-
-The 13b variant will fit if you change these settings to these values:
-gradient_accumulation_steps: 2
-micro_batch_size: 1
-
-```shell
-accelerate launch scripts/finetune.py examples/llama-2/qlora.yml
-
-```
-or
-
-```shell
-accelerate launch scripts/finetune.py examples/llama-2/lora.yml
-
-```

examples/llama-2/lora.yml

@@ -1,66 +0,0 @@
-base_model: meta-llama/Llama-2-7b-hf
-base_model_config: meta-llama/Llama-2-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./lora-out
-
-sequence_len: 4096
-max_packed_sequence_len: 4096
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: true
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention: true
-flash_attention:
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
-  pad_token: "<pad>"

examples/llama-2/qlora.yml

@@ -1,67 +0,0 @@
-base_model: meta-llama/Llama-2-7b-hf
-base_model_config: meta-llama/Llama-2-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 4096
-max_packed_sequence_len: 4096
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: true
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention: true
-flash_attention:
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
-  pad_token: "<pad>"

examples/lora-openllama-3b/config.yml

@@ -1,5 +1,5 @@
-base_model: openlm-research/open_llama_3b
-base_model_config: openlm-research/open_llama_3b
+base_model: openlm-research/open_llama_3b_600bt_preview
+base_model_config: openlm-research/open_llama_3b_600bt_preview
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 load_in_8bit: true
@@ -49,7 +49,7 @@ early_stopping_patience:
 resume_from_checkpoint:
 local_rank:
 logging_steps: 1
-xformers_attention: true
+xformers_attention:
 flash_attention:
 gptq_groupsize:
 gptq_model_v1:

examples/openllama-3b/README.md

@@ -1,16 +0,0 @@
-# openllama-3b
-
-Basic full tune
-```shell
-accelerate launch scripts/finetune.py examples/openllama-3b/config.yml
-```
-
-LoRA
-```shell
-accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml
-```
-
-QLoRA
-```shell
-accelerate launch scripts/finetune.py examples/openllama-3b/qlora.yml
-```

examples/openllama-3b/config.yml

@@ -1,62 +0,0 @@
-base_model: openlm-research/open_llama_3b
-base_model_config: openlm-research/open_llama_3b
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-push_dataset_to_hub:
-datasets:
-  - path: teknium/GPT4-LLM-Cleaned
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.02
-adapter:
-lora_model_dir:
-sequence_len: 256
-max_packed_sequence_len:
-lora_r:
-lora_alpha:
-lora_dropout:
-lora_target_modules:
-lora_target_linear:
-lora_fan_in_fan_out:
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./openllama-out
-gradient_accumulation_steps: 1
-micro_batch_size: 1
-num_epochs: 3
-optimizer: adamw_bnb_8bit
-torchdistx_path:
-lr_scheduler: cosine
-learning_rate: 0.00001
-train_on_inputs: false
-group_by_length: false
-float16: true
-bf16: false
-fp16: false
-tf32: false
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention: true
-flash_attention:
-gptq_groupsize:
-gptq_model_v1:
-warmup_steps: 10
-eval_steps: 50
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.1
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"

examples/pythia-12b/README.md

@@ -1,4 +1,4 @@
-# Pythia 12B
+# Python 12B
 
 - Single-GPU A100 only (?)
 
@@ -7,3 +7,4 @@ python scripts/finetune.py examples/pythia-12b/config.yml
 ```
 
 ⚠️ Multiple-GPU A100 - Doesn't seem to work with multi-gpu without causing OOM! ⚠️
+

examples/pythia-12b/config.yml

@@ -22,7 +22,7 @@ lora_dropout: 0.0
 lora_target_modules:
 lora_target_linear: true
 lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
-wandb_project:
+wandb_project: pythia-12b
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
@@ -45,5 +45,5 @@ resume_from_checkpoint:
 local_rank:
 gradient_checkpointing: true
 fsdp:
-fsdp_config:
+fsdp_transformer_layer_cls_to_wrap:
 collator_pad_to_longest: true

examples/qlora-openllama-3b/README.md

@@ -0,0 +1,6 @@
+# qlora-openllama-3b
+
+```shell
+accelerate launch scripts/finetune.py examples/qlora-openllama-3b/config.yml
+
+```

examples/qlora-openllama-3b/config.yml

@@ -1,5 +1,5 @@
-base_model: openlm-research/open_llama_3b
-base_model_config: openlm-research/open_llama_3b
+base_model: openlm-research/open_llama_3b_600bt_preview
+base_model_config: openlm-research/open_llama_3b_600bt_preview
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 load_in_8bit: false

examples/redpajama/config-3b.yml

@@ -1,7 +1,7 @@
 base_model: togethercomputer/RedPajama-INCITE-Chat-3B-v1
 base_model_config: togethercomputer/RedPajama-INCITE-Chat-3B-v1
 model_type: GPTNeoXForCausalLM
-tokenizer_type: AutoTokenizer
+tokenizer_type: GPTNeoXTokenizer
 trust_remote_code:
 load_in_8bit: false
 datasets:

examples/xgen-7b/xgen-7b-8k-qlora.yml

@@ -1,90 +0,0 @@
-# An example finetuning Saleforce's XGen-7b model with 8k context using qlora
-# on Tim Dettmer's Guanaco dataset.
-base_model: Salesforce/xgen-7b-8k-base
-base_model_config: Salesforce/xgen-7b-8k-base
-trust_remote_code: true
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-load_in_8bit: false
-# enable 4bit for QLoRA
-load_in_4bit: true
-gptq: false
-strict: false
-push_dataset_to_hub:
-datasets:
-  - path: timdettmers/openassistant-guanaco
-    data_files:
-      - openassistant_best_replies_train.jsonl
-    type: "completion"
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-# enable QLoRA
-adapter: qlora
-lora_model_dir:
-sequence_len: 8192
-max_packed_sequence_len:
-
-# hyperparameters from QLoRA paper Appendix B.2
-# "We find hyperparameters to be largely robust across datasets"
-lora_r: 64
-lora_alpha: 16
-# 0.1 for models up to 13B
-# 0.05 for 33B and 65B models
-lora_dropout: 0.05
-# add LoRA modules on all linear layers of the base model
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./qlora-out
-
-# QLoRA paper Table 9
-# - 16 for 7b & 13b
-# - 32 for 33b, 64 for 64b
-# Max size tested on A6000
-# - 7b: 40
-# - 40b: 4
-# decrease if OOM, increase for max VRAM utilization
-micro_batch_size: 1
-gradient_accumulation_steps: 1
-num_epochs: 3
-# Optimizer for QLoRA
-optimizer: paged_adamw_32bit
-torchdistx_path:
-lr_scheduler: cosine
-# QLoRA paper Table 9
-# - 2e-4 for 7b & 13b
-# - 1e-4 for 33b & 64b
-learning_rate: 0.00002
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-gradient_checkpointing: true
-# stop training after this many evaluation losses have increased in a row
-# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback
-early_stopping_patience: 3
-resume_from_checkpoint:
-auto_resume_from_checkpoints: true
-local_rank:
-logging_steps: 1
-xformers_attention: true
-flash_attention:
-gptq_groupsize:
-gptq_model_v1:
-warmup_steps: 10
-eval_steps: 50
-save_steps: 50
-debug:
-deepspeed:
-weight_decay: 0.0
-special_tokens:
-  eos_token: "<|endoftext|>"
-  bos_token: "<|endoftext|>"
-  unk_token: "<|endoftext|>"
-  pad_token: "<|endoftext|>"

requirements.txt

@@ -1,7 +1,7 @@
 peft @ git+https://github.com/huggingface/peft.git
 transformers @ git+https://github.com/huggingface/transformers.git
 bitsandbytes>=0.39.0
-accelerate @ git+https://github.com/huggingface/accelerate@2a289f6108e77a77a4efffb3f6316bc98538413b
+accelerate
 addict
 fire
 PyYAML==6.0
@@ -12,9 +12,6 @@ wandb
 einops
 xformers
 optimum
-hf_transfer
-numba
-numpy==1.24.4
 # qlora things
 bert-score==0.3.13
 evaluate==0.4.0

scripts/alpaca_json_to_jsonl.py

@@ -15,9 +15,6 @@ from axolotl.convert import (
     JsonToJsonlConverter,
     StdoutWriter,
 )
-from axolotl.logging_config import configure_logging
-
-configure_logging()
 
 # add src to the pythonpath so we don't need to pip install this
 project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))

scripts/finetune.py

@@ -14,20 +14,15 @@ import torch
 import yaml
 
 # add src to the pythonpath so we don't need to pip install this
+from datasets import Dataset
 from optimum.bettertransformer import BetterTransformer
-from transformers import GenerationConfig, TextStreamer
+from transformers import GenerationConfig
 
-from axolotl.logging_config import configure_logging
 from axolotl.utils.data import load_prepare_datasets, load_pretraining_dataset
 from axolotl.utils.dict import DictDefault
-from axolotl.utils.distributed import barrier, is_main_process
 from axolotl.utils.models import load_model, load_tokenizer
 from axolotl.utils.tokenization import check_dataset_labels
-from axolotl.utils.trainer import (
-    calculate_total_num_steps,
-    process_datasets_for_packing,
-    setup_trainer,
-)
+from axolotl.utils.trainer import setup_trainer
 from axolotl.utils.validation import validate_config
 from axolotl.utils.wandb import setup_wandb_env_vars
 
@@ -35,12 +30,9 @@ project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 src_dir = os.path.join(project_root, "src")
 sys.path.insert(0, src_dir)
 
-configure_logging()
-LOG = logging.getLogger("axolotl.scripts")
-
 
+logging.basicConfig(level=os.getenv("LOG_LEVEL", "INFO"))
 DEFAULT_DATASET_PREPARED_PATH = "last_run_prepared"
-os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
 
 
 def choose_device(cfg):
@@ -58,7 +50,7 @@ def choose_device(cfg):
 
     cfg.device = get_device()
     if cfg.device_map != "auto":
-        if cfg.device.startswith("cuda"):
+        if cfg.device == "cuda":
             cfg.device_map = {"": cfg.local_rank}
         else:
             cfg.device_map = {"": cfg.device}
@@ -73,43 +65,23 @@ def get_multi_line_input() -> Optional[str]:
     return instruction
 
 
-def do_inference(cfg, model, tokenizer, prompter: Optional[str]):
-    default_tokens = {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>"}
+def do_inference(cfg, model, tokenizer, prompter="AlpacaPrompter"):
+    tokenizer.add_special_tokens({"unk_token": "<unk>"})
+    tokenizer.add_special_tokens({"bos_token": "<s>"})
+    tokenizer.add_special_tokens({"eos_token": "</s>"})
 
-    for token, symbol in default_tokens.items():
-        # If the token isn't already specified in the config, add it
-        if not (cfg.special_tokens and token in cfg.special_tokens):
-            tokenizer.add_special_tokens({token: symbol})
-
-    prompter_module = None
-    if prompter:
-        prompter_module = getattr(
-            importlib.import_module("axolotl.prompters"), prompter
-        )
-
-    if cfg.landmark_attention:
-        from axolotl.monkeypatch.llama_landmark_attn import set_model_mem_id
-
-        set_model_mem_id(model, tokenizer)
-        model.set_mem_cache_args(
-            max_seq_len=255, mem_freq=50, top_k=5, max_cache_size=None
-        )
+    prompter_module = getattr(importlib.import_module("axolotl.prompters"), prompter)
 
     while True:
-        print("=" * 80)
         # support for multiline inputs
         instruction = get_multi_line_input()
         if not instruction:
             return
-        if prompter_module:
-            prompt: str = next(
-                prompter_module().build_prompt(instruction=instruction.strip("\n"))
-            )
-        else:
-            prompt = instruction.strip()
+        prompt: str = next(
+            prompter_module().build_prompt(instruction=instruction.strip("\n"))
+        )
         batch = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
 
-        print("=" * 40)
         model.eval()
         with torch.no_grad():
             generation_config = GenerationConfig(
@@ -128,13 +100,10 @@ def do_inference(cfg, model, tokenizer, prompter: Optional[str]):
                 output_hidden_states=False,
                 output_scores=False,
             )
-            streamer = TextStreamer(tokenizer)
             generated = model.generate(
                 inputs=batch["input_ids"].to(cfg.device),
                 generation_config=generation_config,
-                streamer=streamer,
             )
-        print("=" * 40)
         print(tokenizer.decode(generated["sequences"].cpu().tolist()[0]))
 
 
@@ -184,7 +153,7 @@ def train(
     cfg_keys = cfg.keys()
     for k, _ in kwargs.items():
         # if not strict, allow writing to cfg even if it's not in the yml already
-        if k in cfg_keys or not cfg.strict:
+        if k in cfg_keys or cfg.strict is False:
             # handle booleans
             if isinstance(cfg[k], bool):
                 cfg[k] = bool(kwargs[k])
@@ -216,47 +185,31 @@ def train(
             cfg.fp16 = True
         cfg.bf16 = False
 
-    if cfg.tf32:
-        torch.backends.cuda.matmul.allow_tf32 = True
-
     # load the tokenizer first
     tokenizer_config = cfg.tokenizer_config or cfg.base_model_config
-    LOG.info(f"loading tokenizer... {tokenizer_config}")
+    logging.info(f"loading tokenizer... {tokenizer_config}")
     tokenizer = load_tokenizer(tokenizer_config, cfg.tokenizer_type, cfg)
 
-    if (
-        check_not_in(["shard", "merge_lora"], kwargs) and not cfg.inference
+    if check_not_in(
+        ["inference", "shard", "merge_lora"], kwargs
     ):  # don't need to load dataset for these
         if not cfg.pretraining_dataset:
             train_dataset, eval_dataset = load_prepare_datasets(
                 tokenizer, cfg, DEFAULT_DATASET_PREPARED_PATH
             )
         else:
+            if cfg.pretraining_dataset is True:
+                pretraining_dataset = "togethercomputer/RedPajama-Data-1T"
+            else:
+                pretraining_dataset = cfg.pretraining_dataset
             train_dataset = load_pretraining_dataset(
-                cfg.pretraining_dataset,
-                tokenizer,
-                max_tokens=cfg.sequence_len,
-                seed=cfg.seed or 42,
+                pretraining_dataset, tokenizer, max_tokens=cfg.sequence_len
             )
-            # https://discuss.huggingface.co/t/how-to-use-huggingface-trainer-streaming-datasets-without-wrapping-it-with-torchdatas-iterablewrapper/25230
-            train_dataset = train_dataset.with_format("torch")
+            train_dataset = Dataset.from_list(list(train_dataset))
             eval_dataset = None
 
-        if is_main_process():
-            # process on rank 0 first so it gets cached so other ranks load from cache
-            train_dataset, eval_dataset = process_datasets_for_packing(
-                cfg, train_dataset, eval_dataset
-            )
-        barrier()
-        if not is_main_process():
-            train_dataset, eval_dataset = process_datasets_for_packing(
-                cfg, train_dataset, eval_dataset
-            )
-        barrier()
-        total_num_steps = calculate_total_num_steps(cfg, train_dataset, tokenizer)
-
     if cfg.debug or "debug" in kwargs:
-        LOG.info("check_dataset_labels...")
+        logging.info("check_dataset_labels...")
         check_dataset_labels(
             train_dataset.select(
                 [random.randrange(0, len(train_dataset) - 1) for _ in range(5)]  # nosec
@@ -265,11 +218,11 @@ def train(
         )
 
     if prepare_ds_only:
-        LOG.info("Finished preparing dataset. Exiting...")
+        logging.info("Finished preparing dataset. Exiting...")
         return
 
     # Load the model and tokenizer
-    LOG.info("loading model and peft_config...")
+    logging.info("loading model and peft_config...")
     model, peft_config = load_model(
         cfg.base_model,
         cfg.base_model_config,
@@ -277,46 +230,54 @@ def train(
         tokenizer,
         cfg,
         adapter=cfg.adapter,
+        inference=("inference" in kwargs),
     )
 
     if "merge_lora" in kwargs and cfg.adapter is not None:
-        LOG.info("running merge of LoRA with base model")
+        logging.info("running merge of LoRA with base model")
         model = model.merge_and_unload()
         model.to(dtype=torch.float16)
 
         if cfg.local_rank == 0:
-            LOG.info("saving merged model")
+            logging.info("saving merged model")
             model.save_pretrained(str(Path(cfg.output_dir) / "merged"))
         return
 
-    if cfg.inference:
-        LOG.info("calling do_inference function")
-        prompter: Optional[str] = "AlpacaPrompter"
-        if "prompter" in kwargs:
-            if kwargs["prompter"] == "None":
-                prompter = None
-            else:
-                prompter = kwargs["prompter"]
-        do_inference(cfg, model, tokenizer, prompter=prompter)
+    if "inference" in kwargs:
+        logging.info("calling do_inference function")
+        do_inference(cfg, model, tokenizer)
         return
 
     if "shard" in kwargs:
         model.save_pretrained(cfg.output_dir)
         return
 
-    trainer = setup_trainer(
-        cfg, train_dataset, eval_dataset, model, tokenizer, total_num_steps
-    )
+    if cfg.debug:
+        logging.info("check_dataset_labels...")
+        check_dataset_labels(
+            train_dataset.select(
+                [random.randrange(0, len(train_dataset) - 1) for i in range(5)]  # nosec
+            ),
+            tokenizer,
+        )
+
+    if prepare_ds_only:
+        logging.info("Finished preparing dataset. Exiting...")
+        return
+
+    model.train()
+
+    trainer = setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer)
 
     model.config.use_cache = False
 
     if torch.__version__ >= "2" and sys.platform != "win32":
-        LOG.info("Compiling torch model")
+        logging.info("Compiling torch model")
         model = torch.compile(model)
 
     # go ahead and presave, so we have the adapter config available to inspect
     if peft_config:
-        LOG.info(f"Pre-saving adapter config to {cfg.output_dir}")
+        logging.info(f"Pre-saving adapter config to {cfg.output_dir}")
         peft_config.save_pretrained(cfg.output_dir)
 
     # In case we want to stop early with ctrl+c, this is a nice to have to save the pretrained model
@@ -332,9 +293,9 @@ def train(
             signal.SIGINT, lambda signum, frame: terminate_handler(signum, frame, model)
         )
 
-    LOG.info("Starting trainer...")
+    logging.info("Starting trainer...")
     if cfg.group_by_length:
-        LOG.info("hang tight... sorting dataset for group_by_length")
+        logging.info("hang tight... sorting dataset for group_by_length")
     resume_from_checkpoint = cfg.resume_from_checkpoint
     if cfg.resume_from_checkpoint is None and cfg.auto_resume_from_checkpoints:
         possible_checkpoints = [
@@ -346,12 +307,10 @@ def train(
                 key=lambda path: int(path.split("-")[-1]),
             )
             resume_from_checkpoint = sorted_paths[-1]
-            LOG.info(
+            logging.info(
                 f"Using Auto-resume functionality to start with checkpoint at {resume_from_checkpoint}"
             )
 
-    if not Path(cfg.output_dir).is_dir():
-        os.makedirs(cfg.output_dir, exist_ok=True)
     if cfg.flash_optimum:
         with torch.backends.cuda.sdp_kernel(
             enable_flash=True, enable_math=True, enable_mem_efficient=True
@@ -360,17 +319,17 @@ def train(
     else:
         trainer.train(resume_from_checkpoint=resume_from_checkpoint)
 
-    LOG.info(f"Training Completed!!! Saving pre-trained model to {cfg.output_dir}")
+    logging.info(f"Training Completed!!! Saving pre-trained model to {cfg.output_dir}")
 
     # TODO do we need this fix? https://huggingface.co/docs/accelerate/usage_guides/fsdp#saving-and-loading
     # only save on rank 0, otherwise it corrupts output on multi-GPU when multiple processes attempt to write the same file
-    if cfg.fsdp:
-        trainer.save_model(cfg.output_dir)
-    elif cfg.local_rank == 0:
+    if cfg.local_rank == 0:
         if cfg.flash_optimum:
             model = BetterTransformer.reverse(model)
         model.save_pretrained(cfg.output_dir)
 
+    # trainer.save_model(cfg.output_dir)  # TODO this may be needed for deepspeed to work? need to review another time
+
 
 if __name__ == "__main__":
     fire.Fire(train)

scripts/runpod-entrypoint.sh

@@ -1,21 +1,10 @@
 #!/bin/bash
 
-# Export specific ENV variables to /etc/rp_environment
-echo "Exporting environment variables..."
-printenv | grep -E '^RUNPOD_|^PATH=|^_=' | sed 's/^\(.*\)=\(.*\)$/export \1="\2"/' >> /etc/rp_environment
-echo 'source /etc/rp_environment' >> ~/.bashrc
+echo $PUBLIC_KEY >> ~/.ssh/authorized_keys
+chmod 700 -R ~/.ssh
 
-if [[ $PUBLIC_KEY ]]
-then
-    mkdir -p ~/.ssh
-    chmod 700 ~/.ssh
-    echo $PUBLIC_KEY >> ~/.ssh/authorized_keys
-    chmod 700 -R ~/.ssh
-    # Start the SSH service in the background
-    service ssh start
-else
-    echo "No PUBLIC_KEY ENV variable provided, not starting openSSH daemon"
-fi
+# Start the SSH service in the background
+service ssh start
 
 # Execute the passed arguments (CMD)
 exec "$@"

src/axolotl/datasets.py

@@ -1,13 +1,12 @@
 """Module containing Dataset functionality"""
 
 import logging
-import os
 from typing import List
 
 import torch
 from datasets import IterableDataset
 
-from .prompt_tokenizers import PromptTokenizingStrategy
+from .prompt_tokenizers import InvalidDataException, PromptTokenizingStrategy
 
 # We want this to be a wrapper for an existing dataset that we have loaded
 # lets use the concept of middlewares to wrap each dataset, for example
@@ -15,8 +14,6 @@ from .prompt_tokenizers import PromptTokenizingStrategy
 # let's check to ensure we don't truncate an item in the middle, we'll use
 # the collators later on to pad the datasets
 
-LOG = logging.getLogger("axolotl")
-
 
 class TokenizedPromptDataset(IterableDataset):
     """
@@ -35,15 +32,13 @@ class TokenizedPromptDataset(IterableDataset):
         self.dataset = dataset
 
     def __iter__(self):
-        features = self.dataset.features.keys()
-        num_proc = os.cpu_count()
-        return iter(
-            self.dataset.map(
-                self.prompt_tokenizer.tokenize_prompt,
-                num_proc=num_proc,
-                remove_columns=features,
-            )
-        )
+        iterator = iter(self.dataset)
+        # Loop through the entire dataset
+        for example in iterator:
+            try:
+                yield self.prompt_tokenizer.tokenize_prompt(example)
+            except InvalidDataException:
+                pass
 
 
 # TODO this isn't the best since it can't interleave datasets
@@ -77,21 +72,14 @@ class ConstantLengthDataset(IterableDataset):
             self.tokens_dtype = torch.int64
 
     def __iter__(self):
-        buffer = {
-            "input_ids": [],
-            "attention_mask": [],
-            "labels": [],
-            "position_ids": [],
-        }
+        buffer = {"input_ids": [], "attention_mask": [], "labels": []}
         buffer_len = 0
         for dataset in self.datasets:
-            idx = 0
             iterator = iter(dataset)
             more_examples = True
             while more_examples:
                 try:
                     example = next(iterator)
-                    idx += 1
                 except StopIteration:
                     more_examples = False
                     example = None
@@ -113,9 +101,6 @@ class ConstantLengthDataset(IterableDataset):
                         attention_mask = torch.cat(buffer["attention_mask"], dim=-1)[
                             : self.seq_length
                         ]
-                        position_ids = torch.cat(buffer["position_ids"], dim=-1)[
-                            : self.seq_length
-                        ]
                         labels = torch.cat(buffer["labels"], dim=-1)[: self.seq_length]
                         if labels.size() == input_ids.size() and (
                             attention_mask.size() == input_ids.size()
@@ -124,28 +109,29 @@ class ConstantLengthDataset(IterableDataset):
                                 "input_ids": input_ids,
                                 "labels": labels,
                                 "attention_mask": attention_mask,
-                                "position_ids": position_ids,
                             }
                         else:
-                            LOG.warning(
+                            logging.warning(
                                 f"dropping batch due to tensor size mismatch input_ids: {input_ids.size()}, labels: {labels.size()}, attention_mask: {attention_mask.size()}"
                             )
                     buffer = {
                         "input_ids": [],
                         "attention_mask": [],
                         "labels": [],
-                        "position_ids": [],
                     }
                     buffer_len = 0
-                    idx = 1
 
                 if example:
-                    # FIXME
                     # just going to drop data points that are too long
                     if len(example["input_ids"]) <= self.seq_length:
                         input_ids = example["input_ids"]
                         attention_mask = example["attention_mask"]
                         labels = example["labels"]
+                        if (
+                            buffer["input_ids"]
+                            and input_ids[0] == self.tokenizer.bos_token_id
+                        ):
+                            attention_mask[0] = 0
 
                         if add_concat_token:
                             input_ids.append(self.concat_token_id)
@@ -156,17 +142,13 @@ class ConstantLengthDataset(IterableDataset):
                             input_ids, dtype=self.tokens_dtype
                         )
                         attention_mask_with_concat = torch.tensor(
-                            [idx * m for m in attention_mask], dtype=torch.int16
+                            attention_mask, dtype=self.tokens_dtype
                         )
                         labels_with_concat = torch.tensor(
                             labels, dtype=self.tokens_dtype
                         )
-                        position_ids = torch.arange(
-                            len(input_ids), dtype=self.tokens_dtype
-                        )
 
                         buffer["input_ids"].append(input_ids_with_concat)
                         buffer["attention_mask"].append(attention_mask_with_concat)
                         buffer["labels"].append(labels_with_concat)
-                        buffer["position_ids"].append(position_ids)
                         buffer_len += len(input_ids)

src/axolotl/flash_attn.py

@@ -7,18 +7,10 @@ from typing import Optional, Tuple
 import torch
 import transformers
 from einops import rearrange
-
-try:
-    from flash_attn.flash_attn_interface import flash_attn_varlen_qkvpacked_func
-except ImportError:
-    from flash_attn.flash_attn_interface import (
-        flash_attn_unpadded_qkvpacked_func as flash_attn_varlen_qkvpacked_func,
-    )
-
+from flash_attn.bert_padding import pad_input, unpad_input
+from flash_attn.flash_attn_interface import flash_attn_unpadded_qkvpacked_func
 from transformers.models.llama.modeling_llama import apply_rotary_pos_emb
 
-from axolotl.monkeypatch.utils import get_cu_seqlens_from_pos_ids
-
 
 def forward(
     self,
@@ -87,20 +79,40 @@ def forward(
             dtype=torch.int32,
             device=qkv.device,
         )
-        output = flash_attn_varlen_qkvpacked_func(
+        output = flash_attn_unpadded_qkvpacked_func(
             qkv, cu_q_lens, max_s, 0.0, softmax_scale=None, causal=True
         )
         output = rearrange(output, "(b s) ... -> b s ...", b=bsz)
     else:
-        qkv = rearrange(qkv, "b s ... -> (b s) ...")
-        cu_q_lens, max_s = get_cu_seqlens_from_pos_ids(position_ids)
-        cu_q_lens = cu_q_lens.squeeze()
+        nheads = qkv.shape[-2]
 
-        output = flash_attn_varlen_qkvpacked_func(
-            qkv, cu_q_lens, max_s, 0.0, softmax_scale=None, causal=True
+        # pylint: disable=invalid-name
+        x = rearrange(qkv, "b s three h d -> b s (three h d)")
+        x_unpad, indices, cu_q_lens, max_s = unpad_input(x, key_padding_mask)
+        x_unpad = rearrange(
+            x_unpad,
+            "nnz (three h d) -> nnz three h d",
+            three=3,
+            h=nheads,
+        )
+        output_unpad = flash_attn_unpadded_qkvpacked_func(
+            x_unpad,
+            cu_q_lens,
+            max_s,
+            0.0,
+            softmax_scale=None,
+            causal=True,
+        )
+        output = rearrange(
+            pad_input(
+                rearrange(output_unpad, "nnz h d -> nnz (h d)"),
+                indices,
+                bsz,
+                q_len,
+            ),
+            "b s (h d) -> b s h d",
+            h=nheads,
         )
-        output = rearrange(output, "(b s) ... -> b s ...", b=bsz)
-
     return (
         self.o_proj(rearrange(output, "b s h d -> b s (h d)")),
         None,

src/axolotl/logging_config.py

@@ -1,33 +0,0 @@
-"""Logging configuration settings"""
-
-import os
-import sys
-from logging.config import dictConfig
-from typing import Any, Dict
-
-DEFAULT_LOGGING_CONFIG: Dict[str, Any] = {
-    "version": 1,
-    "formatters": {
-        "simple": {
-            "format": "[%(asctime)s] [%(levelname)s] [%(name)s.%(funcName)s:%(lineno)d] [PID:%(process)d] %(message)s",
-        },
-    },
-    "filters": {},
-    "handlers": {
-        "console": {
-            "class": "logging.StreamHandler",
-            "formatter": "simple",
-            "filters": [],
-            "stream": sys.stdout,
-        },
-    },
-    "root": {"handlers": ["console"], "level": os.getenv("LOG_LEVEL", "INFO")},
-    "loggers": {
-        "axolotl": {"handlers": ["console"], "level": "DEBUG", "propagate": False},
-    },
-}
-
-
-def configure_logging():
-    """Configure with default logging"""
-    dictConfig(DEFAULT_LOGGING_CONFIG)

src/axolotl/monkeypatch/llama_attn_hijack_xformers.py

@@ -7,7 +7,6 @@ import math
 from typing import Optional, Tuple
 
 import torch
-import torch.nn.functional as F
 import transformers.models.llama.modeling_llama
 from torch import nn
 
@@ -39,48 +38,21 @@ def xformers_forward(
     # pylint: disable=duplicate-code
     bsz, q_len, _ = hidden_states.size()
 
-    if not hasattr(self, "pretraining_tp"):
-        self.pretraining_tp = 1
-
-    if self.pretraining_tp > 1:
-        key_value_slicing = (
-            self.num_key_value_heads * self.head_dim
-        ) // self.pretraining_tp
-        query_slices = self.q_proj.weight.split(
-            (self.num_heads * self.head_dim) // self.pretraining_tp, dim=0
-        )
-        key_slices = self.k_proj.weight.split(key_value_slicing, dim=0)
-        value_slices = self.v_proj.weight.split(key_value_slicing, dim=0)
-
-        query_states = [
-            F.linear(hidden_states, query_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        query_states = torch.cat(query_states, dim=-1)
-
-        key_states = [
-            F.linear(hidden_states, key_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        key_states = torch.cat(key_states, dim=-1)
-
-        value_states = [
-            F.linear(hidden_states, value_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        value_states = torch.cat(value_states, dim=-1)
-
-    else:
-        query_states = self.q_proj(hidden_states)
-        key_states = self.k_proj(hidden_states)
-        value_states = self.v_proj(hidden_states)
-
-    query_states = query_states.view(
-        bsz, q_len, self.num_heads, self.head_dim
-    ).transpose(1, 2)
-    key_states = key_states.view(
-        bsz, q_len, self.num_key_value_heads, self.head_dim
-    ).transpose(1, 2)
-    value_states = value_states.view(
-        bsz, q_len, self.num_key_value_heads, self.head_dim
-    ).transpose(1, 2)
+    query_states = (
+        self.q_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+    key_states = (
+        self.k_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+    value_states = (
+        self.v_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
 
     kv_seq_len = key_states.shape[-2]
     if past_key_value is not None:
@@ -101,14 +73,6 @@ def xformers_forward(
 
     past_key_value = (key_states, value_states) if use_cache else None
 
-    # repeat k/v heads if n_kv_heads < n_heads
-    key_states = transformers.models.llama.modeling_llama.repeat_kv(
-        key_states, self.num_key_value_groups
-    )
-    value_states = transformers.models.llama.modeling_llama.repeat_kv(
-        value_states, self.num_key_value_groups
-    )
-
     # We only apply xformers optimizations if we don't need to output the whole attention matrix
     if not output_attentions:
         query_states = query_states.transpose(1, 2)
@@ -128,7 +92,6 @@ def xformers_forward(
                 query_states,
                 key_states,
                 value_states,
-                # attn_bias=attention_mask,
                 attn_bias=xformers.ops.LowerTriangularMask(),
             )
         attn_weights = None
@@ -165,23 +128,10 @@ def xformers_forward(
                 f" {attn_output.size()}"
             )
 
-        attn_output = attn_output.transpose(1, 2).contiguous()
-        # end x-formers vs. not x-formers if-else block
+        attn_output = attn_output.transpose(1, 2)
 
     attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)
-
-    if self.pretraining_tp > 1:
-        attn_output = attn_output.split(self.hidden_size // self.pretraining_tp, dim=2)
-        o_proj_slices = self.o_proj.weight.split(
-            self.hidden_size // self.pretraining_tp, dim=1
-        )
-        attn_output = sum(
-            F.linear(attn_output[i], o_proj_slices[i])
-            for i in range(self.pretraining_tp)
-        )
-    else:
-        attn_output = self.o_proj(attn_output)
-
+    attn_output = self.o_proj(attn_output)
     return attn_output, attn_weights, past_key_value
 
 
@@ -234,15 +184,14 @@ def sdp_attention_forward(
 
     # We only apply sdp attention if we don't need to output the whole attention matrix
     if not output_attentions:
-        with torch.backends.cuda.sdp_kernel():
-            attn_output = torch.nn.functional.scaled_dot_product_attention(
-                query_states,
-                key_states,
-                value_states,
-                attn_mask=attention_mask,
-                is_causal=False,
-            )
-            attn_weights = None
+        attn_output = torch.nn.functional.scaled_dot_product_attention(
+            query_states,
+            key_states,
+            value_states,
+            attn_mask=attention_mask,
+            is_causal=False,
+        )
+        attn_weights = None
     else:
         attn_weights = torch.matmul(
             query_states, key_states.transpose(2, 3)

src/axolotl/monkeypatch/llama_expand_mask.py

@@ -1,52 +0,0 @@
-"""
-expands the binary attention mask per 3.2.2 of https://arxiv.org/pdf/2107.02027.pdf
-"""
-from typing import Optional
-
-import torch
-
-
-def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None):
-    """
-    Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
-    This expansion handles packed sequences so that sequences share the same attention mask integer value
-    when they attend to each other within that sequence.
-    This expansion transforms the mask to lower triangular form to prevent future peeking.
-    """
-    bsz, src_len = mask.size()
-    tgt_len = tgt_len if tgt_len is not None else src_len
-
-    mask = mask.unsqueeze(1).unsqueeze(2)
-    mask = mask.expand(bsz, 1, tgt_len, src_len)
-
-    # Create a binary mask from the original mask where zeros remain zeros and all other values are set to one
-    binary_mask = torch.where(
-        mask != 0,
-        torch.tensor(1).to(dtype),
-        torch.tensor(0).to(dtype),
-    )
-
-    # Create a block-diagonal mask.
-    # we multiply by the binary mask so that 0's in the original mask are correctly excluded
-    zero_one_mask = torch.eq(mask, mask.transpose(-1, -2)).int() * binary_mask
-
-    # Now let's create a lower triangular mask of ones that will zero out the upper triangular part
-    lower_triangular_ones = torch.tril(torch.ones((tgt_len, src_len), dtype=dtype)).to(
-        mask.device
-    )
-
-    # Use the lower triangular mask to zero out the upper triangular part of the zero_one_mask
-    masked_zero_one_mask = zero_one_mask * lower_triangular_ones
-    inverted_mask = 1.0 - masked_zero_one_mask
-
-    return inverted_mask.masked_fill(
-        inverted_mask.to(torch.bool), torch.finfo(dtype).min
-    )
-
-
-def hijack_expand_mask():
-    import transformers
-
-    transformers.models.llama.modeling_llama._expand_mask = (  # pylint: disable=protected-access
-        _expand_mask
-    )

src/axolotl/monkeypatch/utils.py

@@ -1,103 +0,0 @@
-"""
-Shared utils for the monkeypatches
-"""
-import torch
-
-
-def get_cu_seqlens(attn_mask):
-    """generate a cumulative sequence length mask for flash attention using attn mask"""
-    if len(attn_mask.shape) == 1:
-        attn_mask = attn_mask.unsqueeze(0)
-
-    device = attn_mask.device
-    results = []
-    max_seq_lens = []
-
-    for row in attn_mask:
-        # Exclude zeros to avoid adding their positions to the mask
-        t_non_zeros = row[row != 0]
-        # Find where the sequence number changes (including the first position)
-        seq_change = torch.cat(
-            [
-                torch.tensor([1], dtype=torch.int32, device=device),
-                t_non_zeros[1:] != t_non_zeros[:-1],
-            ]
-        )
-        # Get the indices where the sequence changes
-        change_indices = torch.cat(
-            [
-                (seq_change == 1).nonzero(as_tuple=True)[0],
-                torch.tensor([len(t_non_zeros)], dtype=torch.int32, device=device),
-            ]
-        )
-        # Calculate the sequence lengths
-        seq_lengths = change_indices[1:] - change_indices[:-1]
-        # Calculate the length of the final sequence or padding
-        final_seq_length = len(row) - change_indices[-1]
-        # Append the length of the final sequence or padding to seq_lengths
-        if final_seq_length.item():
-            seq_lengths = torch.cat(
-                [
-                    seq_lengths,
-                    torch.tensor(
-                        [final_seq_length.item()], dtype=torch.int32, device=device
-                    ),
-                ]
-            )
-        # Calculate the cumulative sequence lengths
-        cu_seqlens = torch.cat(
-            [torch.tensor([0], dtype=torch.int32, device=device), seq_lengths.cumsum(0)]
-        )
-        max_seq_len = (cu_seqlens[1:] - cu_seqlens[:-1]).max()
-        results.append(cu_seqlens)
-        max_seq_lens.append(max_seq_len)
-
-    return torch.stack(results).to(dtype=torch.int32), torch.stack(max_seq_lens)
-
-
-def get_cu_seqlens_from_pos_ids(position_ids):
-    """generate a cumulative sequence length mask for flash attention using pos ids"""
-    if len(position_ids.shape) == 1:
-        position_ids = position_ids.unsqueeze(0)
-
-    device = position_ids.device
-    results = []
-    max_seq_lens = []
-
-    for row in position_ids:
-        # Count the number of consecutive zeros from the right side
-        padding_length = (row == 0).int().flip(dims=[0]).cumprod(dim=0).sum().item()
-
-        # Adjust the row to exclude padding
-        adjusted_row = row[:-padding_length] if padding_length else row.clone()
-
-        # Find where the position resets to 0 (indicating a new sequence)
-        seq_starts = torch.cat(
-            [
-                torch.tensor([True], dtype=torch.bool, device=device),
-                adjusted_row[1:] == 0,
-            ]
-        )
-        # Get the indices where the sequence starts
-        start_indices = torch.cat(
-            [
-                (seq_starts).nonzero(as_tuple=True)[0],
-                torch.tensor([len(adjusted_row)], dtype=torch.int32, device=device),
-            ]
-        )
-        # Calculate the sequence lengths
-        seq_lengths = start_indices[1:] - start_indices[:-1]
-        # Calculate the cumulative sequence lengths
-        cu_seqlens = torch.cat(
-            [torch.tensor([0], dtype=torch.int32, device=device), seq_lengths.cumsum(0)]
-        )
-        # Append the padding length to the cumulative sequence lengths
-        if padding_length:
-            cu_seqlens = torch.cat(
-                [cu_seqlens, torch.tensor([len(row)], dtype=torch.int32, device=device)]
-            )
-        max_seq_len = (cu_seqlens[1:] - cu_seqlens[:-1]).max()
-        results.append(cu_seqlens)
-        max_seq_lens.append(max_seq_len)
-
-    return torch.stack(results).to(dtype=torch.int32), torch.stack(max_seq_lens)

src/axolotl/monkeypatch/xpos_rope_llama_monkey_patch.py

@@ -1,94 +0,0 @@
-# pylint: skip-file
-"""
-Copied from https://github.com/kaiokendev/cutoff-len-is-context-len/blob/main/util/xpos_rope_llama_monkey_patch.py
-"""
-import torch
-import transformers
-import transformers.models.llama.modeling_llama
-from einops import rearrange
-
-
-class XposRotaryEmbedding(torch.nn.Module):
-    def __init__(
-        self,
-        dim,
-        max_position_embeddings=2048,
-        base=10000,
-        device=None,
-        scale_base=2048,
-        use_xpos=True,
-    ):
-        super().__init__()
-        self.max_seq_len_cached = max_position_embeddings
-        self.scale_base = scale_base
-
-        inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float() / dim))
-        t = torch.arange(self.max_seq_len_cached, device=device).type_as(inv_freq)
-        freqs = torch.einsum("i , j -> i j", t, inv_freq)
-        freqs = torch.cat((freqs, freqs), dim=-1)
-
-        self.register_buffer("inv_freq", inv_freq, persistent=False)
-        self.register_buffer("freqs_cached", freqs, persistent=False)
-
-        if not use_xpos:
-            self.register_buffer("scale", None)
-            self.register_buffer("scale_cached", torch.ones(1))
-            return
-
-        scale = (torch.arange(0, dim, 2) + 0.4 * dim) / (1.4 * dim)
-        power = (t - (self.max_seq_len_cached // 2)) / self.scale_base
-        scale_cached = scale ** rearrange(power, "n -> n 1")
-        scale_cached = torch.cat((scale_cached, scale_cached), dim=-1)
-
-        self.register_buffer("scale", scale, persistent=False)
-        self.register_buffer("scale_cached", scale_cached, persistent=False)
-
-    def forward(
-        self,
-        x,
-        seq_len,
-    ):
-        if seq_len > self.max_seq_len_cached:
-            self.max_seq_len_cached = seq_len
-            t = torch.arange(self.max_seq_len_cached, device=x.device).type_as(
-                self.inv_freq
-            )
-            freqs = torch.einsum("i , j -> i j", t, self.inv_freq)
-            freqs = torch.cat((freqs, freqs), dim=-1).to(dtype=x.dtype)
-
-            self.register_buffer("freqs_cached", freqs)
-
-            if self.scale is None:
-                self.register_buffer(
-                    "scale_cached", torch.ones(1, device=x.device).to(dtype=x.dtype)
-                )
-
-                return self.freqs_cached.to(dtype=x.dtype), self.scale_cached
-
-            power = (t - (seq_len // 2)) / self.scale_base
-            scale = self.scale ** rearrange(power, "n -> n 1")
-            scale = torch.cat((scale, scale), dim=-1).to(dtype=x.dtype)
-            self.register_buffer("scale_cached", scale)
-
-        return self.freqs_cached.to(dtype=x.dtype), self.scale_cached.to(dtype=x.dtype)
-
-
-def rotate_half(x):
-    x1, x2 = x.chunk(2, dim=-1)
-    return torch.cat((-x2, x1), dim=-1)
-
-
-def apply_rotary_pos_emb(q, k, freqs, scale=1, position_ids=None):
-    freqs = freqs[position_ids, :]
-    if scale.shape[-1] != 1:
-        scale = scale[position_ids, :]
-
-    q_embed = (q * freqs.cos() * scale) + (rotate_half(q) * freqs.sin() * scale)
-    k_embed = (k * freqs.cos() * 1 / scale) + (rotate_half(k) * freqs.sin() * 1 / scale)
-
-    return q_embed, k_embed
-
-
-def replace_llama_rope_with_xpos_rope():
-    transformers.models.llama.modeling_llama.LlamaRotaryEmbedding = XposRotaryEmbedding
-    transformers.models.llama.modeling_llama.apply_rotary_pos_emb = apply_rotary_pos_emb

src/axolotl/prompt_strategies/alpaca_chat.py

@@ -6,7 +6,7 @@ from axolotl.prompt_tokenizers import (
     AlpacaPromptTokenizingStrategy,
     InstructionPromptTokenizingStrategy,
 )
-from axolotl.prompters import AlpacaPrompter, PromptStyle, UnpromptedPrompter
+from axolotl.prompters import AlpacaPrompter, PromptStyle
 
 
 def load(tokenizer, cfg):
@@ -18,42 +18,6 @@ def load(tokenizer, cfg):
     )
 
 
-class AlpacaConcisePrompter(AlpacaPrompter):
-    """
-    Alpaca Prompter extending the system prompt to ask for concise chat-instruct answers
-    """
-
-    system_prompt = "Below is an instruction from a USER that describes a task, paired with an input that provides further context. The ASSISTANT writes a response that concisely and appropriately completes the request.\n\n"
-    system_no_input_prompt = "Below is an instruction from a USER that describes a task. The ASSISTANT writes a response that appropriately and concisely completes the request.\n\n"
-
-
-class AlpacaChatPrompter(AlpacaPrompter):
-    """
-    Alpaca Chat Prompter extending the system prompt to for chat-instruct answers
-    """
-
-    system_prompt = "Below is an instruction from a USER that describes a task, paired with an input that provides further context. The ASSISTANT writes a response that concisely and appropriately completes the request.\n\n"
-    system_no_input_prompt = "Below is an instruction from a USER that describes a task. The ASSISTANT writes a response that appropriately and concisely completes the request.\n\n"
-
-    def __init__(self):  # pylint: disable=super-init-not-called
-        self.prompt_style = PromptStyle.CHAT.value
-        self.match_prompt_style()
-
-
-class NoSystemPrompter(AlpacaPrompter):
-    """
-    Null Prompter with no system prompts
-    """
-
-    system_prompt = ""
-    system_no_input_prompt = ""
-    turn_format = "{instruction} {input} "
-    turn_no_input_format = "{instruction} "
-
-    def __init__(self):  # pylint: disable=super-init-not-called
-        pass
-
-
 class AlpacaQAPromptTokenizingStrategy(InstructionPromptTokenizingStrategy):
     """
     Tokenizing strategy for AlpacaQA
@@ -67,49 +31,9 @@ class AlpacaQAPromptTokenizingStrategy(InstructionPromptTokenizingStrategy):
         )
 
 
-class CamelAIPromptTokenizingStrategy(InstructionPromptTokenizingStrategy):
-    """
-    Tokenizing strategy for CamelAI datasets
-    """
-
-    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str]:
-        return (
-            prompt["message_1"],
-            "",
-            prompt["message_2"],
-        )
-
-
-def load_concise(tokenizer, cfg):
-    return AlpacaPromptTokenizingStrategy(
-        AlpacaConcisePrompter(PromptStyle.CHAT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
 def load_qa(tokenizer, cfg):
     return AlpacaQAPromptTokenizingStrategy(
-        AlpacaChatPrompter(),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-def load_camel_ai(tokenizer, cfg):
-    return CamelAIPromptTokenizingStrategy(
-        AlpacaChatPrompter(),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-def load_no_prompt(tokenizer, cfg):
-    return AlpacaPromptTokenizingStrategy(
-        UnpromptedPrompter(PromptStyle.CHAT.value),
+        AlpacaPrompter(PromptStyle.CHAT.value),
         tokenizer,
         cfg.train_on_inputs,
         cfg.sequence_len,

src/axolotl/prompt_strategies/alpaca_instruct.py

@@ -1,7 +1,7 @@
 """Module loading the AlpacaInstructPromptTokenizingStrategy class"""
 
 from axolotl.prompt_tokenizers import AlpacaPromptTokenizingStrategy
-from axolotl.prompters import AlpacaPrompter, PromptStyle, UnpromptedPrompter
+from axolotl.prompters import AlpacaPrompter, PromptStyle
 
 
 def load(tokenizer, cfg):
@@ -11,12 +11,3 @@ def load(tokenizer, cfg):
         cfg.train_on_inputs,
         cfg.sequence_len,
     )
-
-
-def load_no_prompt(tokenizer, cfg):
-    return AlpacaPromptTokenizingStrategy(
-        UnpromptedPrompter(PromptStyle.INSTRUCT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )

src/axolotl/prompt_strategies/alpaca_w_system.py

@@ -1,160 +0,0 @@
-"""
-Prompt strategies loader for alpaca instruction datasets with system prompts
-"""
-from typing import Generator, Tuple, Union
-
-from axolotl.prompt_tokenizers import PromptTokenizingStrategy
-from axolotl.prompters import AlpacaPrompter, PromptStyle
-
-
-class InstructionWSystemPromptTokenizingStrategy(PromptTokenizingStrategy):
-    """
-    Tokenizing strategy for instruction-based prompts.
-    """
-
-    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str, str]:
-        return (
-            prompt["instruction"],
-            prompt["input"] if "input" in prompt else "",
-            prompt["output"],
-            prompt["system"],
-        )
-
-    def tokenize_prompt(self, prompt):
-        # pylint: disable=duplicate-code
-        (
-            instruction,
-            input,  # pylint: disable=redefined-builtin
-            response,
-            system,
-        ) = self.parse_instruction_fields(prompt)
-        user_prompt = next(
-            iter(
-                self.prompter.build_prompt_w_system(
-                    system,
-                    instruction,
-                    input,
-                )
-            )
-        )
-        tokenized_prompt = self._tokenize(user_prompt, add_eos_token=False)
-        if not self.train_on_inputs:
-            user_prompt_len = len(tokenized_prompt["input_ids"])
-            # TODO this could be sped up using numpy array slicing
-            tokenized_prompt["labels"] = [-100] * user_prompt_len
-        tokenized_res_prompt = self._tokenize(
-            response, strip_bos_token=True, add_eos_token=True
-        )
-        tokenized_prompt["input_ids"] += tokenized_res_prompt["input_ids"]
-        tokenized_prompt["attention_mask"] += tokenized_res_prompt["attention_mask"]
-        tokenized_prompt["labels"] += tokenized_res_prompt["input_ids"]
-
-        return tokenized_prompt
-
-
-class SystemDataPrompter(AlpacaPrompter):
-    """
-    Alpaca Style Prompter that uses system prompts from the dataset
-    """
-
-    def build_prompt_w_system(
-        self,
-        system: str,
-        instruction: str,
-        input: Union[None, str] = None,  # pylint: disable=redefined-builtin
-        output: Union[None, str] = None,
-    ) -> Generator[str, None, None]:
-        # returns the full prompt from instruction and optional input
-        # if a label (=response, =output) is provided, it's also appended.
-        formatted_sys_prompt = (
-            self.system_format.format(system=system)
-            if system and self.system_format
-            else ""
-        )
-        if input:
-            res = formatted_sys_prompt + self.turn_format.format(
-                instruction=instruction, input=input
-            )
-        else:
-            res = formatted_sys_prompt + self.turn_no_input_format.format(
-                instruction=instruction
-            )
-        if output:
-            res = f"{res}{output}"
-        yield res
-
-
-class OpenOrcaSystemDataPrompter(SystemDataPrompter):
-    """
-    Alpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts
-    """
-
-    def match_prompt_style(self):
-        # pylint: disable=duplicate-code
-        if self.prompt_style == PromptStyle.INSTRUCT.value:
-            self.turn_format = "### User:\n{instruction}\n\n### Additional Context:\n{input}\n\n### Assistant:\n"
-            self.turn_no_input_format = "### User:\n{instruction}\n\n### Assistant:\n"
-        if self.prompt_style == PromptStyle.CHAT.value:
-            self.turn_format = "User: {instruction}\n{input}\nAssistant:"
-            self.turn_no_input_format = "User: {instruction}\nAssistant:"
-            self.system_format = "System: {system}\n"
-        if self.prompt_style == PromptStyle.CHATML.value:
-            self.turn_format = "<|im_start|>user\n{instruction}\n{input}<|im_end|>\n<|im_start|>assistant\n"
-            self.turn_no_input_format = (
-                "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
-            )
-            self.system_format = "<|im_start|>system\n{system}<|im_end|>\n"
-
-
-class OpenOrcaPromptTokenizingStrategy(InstructionWSystemPromptTokenizingStrategy):
-    """
-    Tokenizing strategy for OpenOrca datasets
-    """
-
-    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str, str]:
-        return (
-            prompt["question"],
-            "",
-            prompt["response"],
-            prompt["system_prompt"],
-        )
-
-
-def load(tokenizer, cfg):
-    return load_chat(tokenizer, cfg)
-
-
-def load_instruct(tokenizer, cfg):
-    return InstructionWSystemPromptTokenizingStrategy(
-        SystemDataPrompter(PromptStyle.INSTRUCT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-def load_chat(tokenizer, cfg):
-    return InstructionWSystemPromptTokenizingStrategy(
-        SystemDataPrompter(PromptStyle.CHAT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-def load_open_orca(tokenizer, cfg):
-    return OpenOrcaPromptTokenizingStrategy(
-        OpenOrcaSystemDataPrompter(PromptStyle.INSTRUCT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-def load_open_orca_chatml(tokenizer, cfg):
-    return OpenOrcaPromptTokenizingStrategy(
-        OpenOrcaSystemDataPrompter(PromptStyle.CHATML.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )

src/axolotl/prompt_strategies/context_qa.py

@@ -1,67 +0,0 @@
-"""Module containing the classes for Context QA Prompt Tokenization Strategies"""
-from typing import Tuple
-
-from axolotl.prompt_tokenizers import InstructionPromptTokenizingStrategy
-from axolotl.prompters import AlpacaPrompter, PromptStyle
-
-
-# article, unanswerable_question, question, answer
-def load_404(tokenizer, cfg):
-    return AlpacaMissingInfoContextPromptTokenizingStrategy(
-        AlpacaContextPrompter(PromptStyle.CHAT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-def load(tokenizer, cfg):
-    return AlpacaContextPromptTokenizingStrategy(
-        AlpacaContextPrompter(PromptStyle.CHAT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-class AlpacaContextPrompter(AlpacaPrompter):
-    """
-    Customized system prompted for concise QA
-    """
-
-    system_prompt = (
-        "Use the following contextual information to concisely answer the question.\n"
-    )
-    system_no_input_prompt = (
-        "Use the following contextual information to concisely answer the question.\n"
-    )
-
-
-class AlpacaContextPromptTokenizingStrategy(InstructionPromptTokenizingStrategy):
-    """
-    Tokenization Strategy to combine in-context article with a question and answer
-    """
-
-    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str]:
-        return (
-            prompt["article"] + "\n===\n" + prompt["question"],
-            "",
-            prompt["answer"],
-        )
-
-
-class AlpacaMissingInfoContextPromptTokenizingStrategy(
-    InstructionPromptTokenizingStrategy
-):
-    """
-    Tokenization Strategy to combine in-context article with a question that can't be answered
-    from the context and a default response to that effect
-    """
-
-    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str]:
-        return (
-            prompt["article"] + "\n===\n" + prompt["unanswerable_question"],
-            "",
-            "The context provided does not contain any information about your inquiry. "
-            "Therefore, I'm unable to answer your question based on the given context.",
-        )

src/axolotl/prompt_strategies/llama2_chat.py

@@ -1,205 +0,0 @@
-"""
-Prompt Strategy for finetuning Llama2 chat models
-see also https://github.com/facebookresearch/llama/blob/6c7fe276574e78057f917549435a2554000a876d/llama/generation.py#L213 for ma reference implementation.
-
-This implementation is based on the Vicuna PR and the fastchat repo, see also:
-https://github.com/lm-sys/FastChat/blob/cdd7730686cb1bf9ae2b768ee171bdf7d1ff04f3/fastchat/conversation.py#L847
-
-Use dataset type: "llama2_chat" in conig.yml to use this prompt style.
-
-E.g. in the config.yml:
-```
-datasets:
-  - path: llama_finetune_train.jsonl
-    type: llama2_chat
-```
-
-The dataset itself should look like this:
-```
-{'conversations':[{"from": "human", "value": "Who are you?"}, {"from": "gpt", "value": "I am Vicuna"},...]}
-```
-in a jsonl file. The first message should be from the human, the second from gpt.
-For a custom system message, the first "from" can be "system" (followed by alternating "human" and "gpt" turns).
-
-Important: Don't use "special_tokens:" in your config.yml if you are not sure what you are doing!
-"""
-
-import logging
-from dataclasses import dataclass, field
-from typing import Generator, List, Sequence
-
-from axolotl.prompt_tokenizers import PromptTokenizingStrategy
-from axolotl.prompters import IGNORE_TOKEN_ID
-
-
-@dataclass
-class Llama2ChatConversation:
-    """A class that manages prompt templates and keeps all conversation history.
-    copied from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py"""
-
-    name: str = "llama2"
-    # The system prompt
-    system: str = (
-        "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. "
-        "Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. "
-        "Please ensure that your responses are socially unbiased and positive in nature.\n\n"
-        "If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. "
-        "If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n"
-    )
-    roles: Sequence[str] = ("[INST]", "[/INST]")
-    messages: List[List[str]] = field(default_factory=list)
-    offset: int = 0
-    sep = " "
-    sep2 = " </s><s>"
-    stop_token_ids = [2]
-
-    def get_prompt(self) -> str:
-        """Get the prompt for generation."""
-        seps = [self.sep, self.sep2]
-        ret = ""
-        for i, (role, message) in enumerate(self.messages):
-            if (i == len(self.messages) - 1) and (role == self.roles[0]):
-                # last message is from user (due to length),
-                #  return prompt without it for training
-                return ret
-            if i == 0:
-                ret += self.system + message.strip()
-            else:
-                ret += role + " " + message.strip() + seps[i % 2]
-        return ret
-
-    def append_message(self, role: str, message: str):
-        """Append a new message."""
-        self.messages.append([role, message])
-
-
-class LLama2ChatTokenizingStrategy(PromptTokenizingStrategy):
-    """
-    Tokenizing strategy for ShareGPT prompts.
-    adapted from https://github.com/lm-sys/FastChat/blob/main/fastchat/train/train.py
-    """
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.sequence_len = 4096
-        self.tokenizer.add_special_tokens({"pad_token": "<pad>"})
-        # https://huggingface.co/meta-llama/Llama-2-7b-chat-hf/blob/main/added_tokens.json
-
-    def tokenize_prompt(self, prompt):
-        conv = next(self.prompter.build_prompt(prompt))
-        conversation_str = conv.get_prompt()
-
-        # Tokenize conversations
-        input_ids = self.tokenizer(
-            conversation_str,
-            return_tensors="pt",
-            padding="max_length",
-            max_length=self.sequence_len,
-            truncation=True,
-        ).input_ids[0]
-        target = input_ids.clone()
-
-        # Mask targets. Only compute loss on the assistant outputs.
-        sep = conv.roles[1]
-
-        total_len = int(target.ne(self.tokenizer.pad_token_id).sum())
-
-        turns = conversation_str.split(conv.sep2)
-        cur_len = 1
-        target[:cur_len] = IGNORE_TOKEN_ID
-        for turn in turns:
-            if turn == "":
-                break
-            turn_len = len(self.tokenizer(turn).input_ids)
-
-            parts = turn.split(sep)
-            if len(parts) != 2:
-                break
-            parts[0] += sep
-            # "-1" is hardcoded for the LLaMA tokenizer to make the offset correct.
-            instruction_len = len(self.tokenizer(parts[0]).input_ids) - 1
-
-            # Ignore the user instructions
-            target[cur_len - 1 : cur_len + instruction_len] = IGNORE_TOKEN_ID
-            cur_len += turn_len + 2  # due to length of role token
-
-        target[cur_len:] = IGNORE_TOKEN_ID
-
-        if cur_len < self.sequence_len:
-            if cur_len != total_len:
-                target[:] = IGNORE_TOKEN_ID
-                logging.warning(
-                    f"WARNING: tokenization mismatch: {cur_len} vs. {total_len}."
-                    f" (ignored)"
-                )
-
-        attention_mask = input_ids.ne(self.tokenizer.pad_token_id).tolist()
-        input_ids = input_ids.tolist()
-        target = target.tolist()
-        # this is a fix for the tokenizer which tokenizes [ differently with eos tokens and
-        # follows the original llama implementation
-        for i in range(2, total_len - 2):
-            if input_ids[i] == 29961:
-                input_ids[i] = 518
-            if target[i] == 29961:
-                target[i] = 518
-        return {
-            "input_ids": input_ids,
-            "labels": target,
-            "attention_mask": attention_mask,
-        }
-
-
-class Llama2ChatPrompter:  # pylint: disable=too-few-public-methods
-    """
-    A prompter that generates prompts for Llama2 models.
-    """
-
-    system_prompt = (
-        "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. "
-        "Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. "
-        "Please ensure that your responses are socially unbiased and positive in nature.\n\n"
-        "If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. "
-        "If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n"
-    )
-
-    def build_prompt(self, source) -> Generator[Llama2ChatConversation, None, None]:
-        # see https://github.com/lm-sys/FastChat/blob/da0641e567cf93756b0978ab5a6b092e96f06240/fastchat/train/train.py#L78
-        source = source["conversations"]  # fix data structure for datasets
-
-        # if system prompt provided, use it
-        if source[0]["from"] == "system":
-            system = f"[INST] <<SYS>>\n{source[0]['value']}\n<</SYS>>\n\n"
-            source = source[1:]
-        else:
-            system = self.system_prompt
-
-        conv = Llama2ChatConversation(system=system)
-
-        if len(source) < 2:
-            # If there isn't a back and forth conversation, ignore it
-            # also happens on the data splitting leaving empty conversations
-            raise IndexError
-
-        roles = {"human": conv.roles[0], "gpt": conv.roles[1]}
-
-        if roles[source[0]["from"]] != conv.roles[0]:
-            # Skip the first one if it is not from human
-            source = source[1:]
-
-        conv.messages = []  # pylint: disable=R0801
-        for j, sentence in enumerate(source):
-            role = roles[sentence["from"]]
-            assert role == conv.roles[j % 2]
-            if sentence["value"]:
-                conv.append_message(role, sentence["value"])
-        yield conv
-
-
-def load(tokenizer, cfg) -> LLama2ChatTokenizingStrategy:
-    return LLama2ChatTokenizingStrategy(
-        Llama2ChatPrompter(),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )

src/axolotl/prompt_strategies/orcamini.py

@@ -1,46 +0,0 @@
-"""
-Prompt Strategy for finetuning Orca Mini (v2) models
-see also https://huggingface.co/psmathur/orca_mini_v2_7b for more information
-
-Use dataset type: orcamini in conig.yml to use this prompt style.
-
-Compared to the alpaca_w_system.open_orca dataset type,
-this one specifies the system prompt with "### System:".
-
-Not suited/tested for multiple-turn conversations without further adjustments.
-"""
-from typing import Generator, Union
-
-from axolotl.prompt_strategies.alpaca_w_system import OpenOrcaPromptTokenizingStrategy
-from axolotl.prompters import AlpacaPrompter
-
-
-class OrcaMiniPrompter(AlpacaPrompter):
-    """Adjusted Prompter for Orca Mini (v2) datasets"""
-
-    def match_prompt_style(self):
-        self.turn_no_input_format = (
-            "### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:\n"
-        )
-
-    def build_prompt_w_system(
-        self,
-        system: str,
-        instruction: str,
-        output: Union[None, str] = None,
-    ) -> Generator[str, None, None]:
-        # returns the full prompt from instruction and optional input
-        # if a label (=response, =output) is provided, it's also appended.
-        res = self.turn_no_input_format.format(system=system, instruction=instruction)
-        if output:
-            res = f"{res}{output}"
-        yield res
-
-
-def load(tokenizer, cfg):
-    return OpenOrcaPromptTokenizingStrategy(
-        OrcaMiniPrompter(),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )

src/axolotl/prompt_strategies/pygmalion.py

@@ -11,8 +11,6 @@ from axolotl.prompt_tokenizers import (
     tokenize_prompt_default,
 )
 
-LOG = logging.getLogger("axolotl")
-
 IGNORE_TOKEN_ID = -100
 
 
@@ -66,7 +64,7 @@ class PygmalionPromptTokenizingStrategy(PromptTokenizingStrategy):
                     *copy.deepcopy(res["input_ids"])
                 ][len(self.bot_prefix_token_ids) :]
             else:
-                LOG.warning(f"unknown role in conversation: {role}")
+                logging.warning(f"unknown role in conversation: {role}")
                 res = defaultdict(lambda: [])
 
             # pylint: disable=duplicate-code

src/axolotl/prompt_strategies/sharegpt_jokes.py

@@ -1,28 +0,0 @@
-"""Module for Jokes prompts using sharegpt style """
-from axolotl.prompt_tokenizers import ShareGPTPromptTokenizingStrategy
-from axolotl.prompters import PromptStyle, ShareGPTPrompter
-
-
-def load(tokenizer, cfg):
-    return SimpleJokesShareGPTPromptTokenizingStrategy(
-        ShareGPTPrompter(PromptStyle.CHAT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-class SimpleJokesShareGPTPromptTokenizingStrategy(ShareGPTPromptTokenizingStrategy):
-    """
-    Tokenization strategy for asking bot to tell a joke and then explain why its funny
-    """
-
-    # title, text, explanation
-    def get_conversation_thread(self, prompt):
-        title = "" if not prompt["title"] else prompt["title"] + " "
-        return [
-            {"from": "human", "value": "Tell me a joke."},
-            {"from": "gpt", "value": title + prompt["text"]},
-            {"from": "human", "value": "Why is that joke funny?"},
-            {"from": "gpt", "value": prompt["explanation"]},
-        ]

src/axolotl/prompt_strategies/sharegpt_simple.py

@@ -1,67 +0,0 @@
-"""Module containing the SimpleShareGPTPromptTokenizingStrategy class"""
-
-from axolotl.prompt_tokenizers import ShareGPTPromptTokenizingStrategy
-from axolotl.prompters import PromptStyle, ShareGPTPrompter
-
-
-def load(tokenizer, cfg):
-    return SimpleShareGPTPromptTokenizingStrategy(
-        ShareGPTPrompter(PromptStyle.CHAT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-def load_role(tokenizer, cfg):
-    return SimpleRoleShareGPTPromptTokenizingStrategy(
-        ShareGPTPrompter(PromptStyle.CHAT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-def load_guanaco(tokenizer, cfg):
-    return GuanacoShareGPTPromptTokenizingStrategy(
-        ShareGPTPrompter(PromptStyle.CHAT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-class SimpleShareGPTPromptTokenizingStrategy(ShareGPTPromptTokenizingStrategy):
-    """
-    basic sharegpt strategy to grab conversations from the sample row
-    """
-
-    def get_conversation_thread(self, prompt):
-        return prompt["conversations"]
-
-
-class SimpleRoleShareGPTPromptTokenizingStrategy(ShareGPTPromptTokenizingStrategy):
-    """
-    basic sharegpt strategy to grab conversations from the sample row, but uses role instead of from
-    """
-
-    def get_conversation_thread(self, prompt):
-        conversations = prompt["conversations"]
-        # remap role: prompter/assistant, text: ... => from: human/gpt, value: ...
-        turns = [{"from": t["role"], "value": t["value"]} for t in conversations]
-        return turns
-
-
-class GuanacoShareGPTPromptTokenizingStrategy(ShareGPTPromptTokenizingStrategy):
-    """
-    sharegpt strategy that remaps oasst data to sharegpt format
-    """
-
-    def get_conversation_thread(self, prompt):
-        conversations = prompt["conversations"]
-        # remap role: prompter/assistant, text: ... => from: human/gpt, value: ...
-        role_map = {"prompter": "human", "assistant": "gpt"}
-        turns = [
-            {"from": role_map[t["role"]], "value": t["text"]} for t in conversations
-        ]
-        return turns

src/axolotl/prompt_tokenizers.py

@@ -10,8 +10,6 @@ from transformers import PreTrainedTokenizer
 
 from axolotl.prompters import IGNORE_TOKEN_ID
 
-LOG = logging.getLogger("axolotl")
-
 IGNORE_INDEX = -100
 LLAMA_DEFAULT_PAD_TOKEN = "[PAD]"  # nosec
 LLAMA_DEFAULT_EOS_TOKEN = "</s>"  # nosec
@@ -48,22 +46,16 @@ class PromptTokenizingStrategy(abc.ABC):
 
     @functools.lru_cache(maxsize=128)
     def _get_user_token(self):
-        try:
-            id_or_ids = self.tokenizer.convert_tokens_to_ids("<|USER|>")
-            if isinstance(id_or_ids, (int,)):
-                return id_or_ids
-        except KeyError:
-            pass
+        id_or_ids = self.tokenizer.convert_tokens_to_ids("<|USER|>")
+        if isinstance(id_or_ids, (int,)):
+            return id_or_ids
         return False
 
     @functools.lru_cache(maxsize=128)
     def _get_assistant_token(self):
-        try:
-            id_or_ids = self.tokenizer.convert_tokens_to_ids("<|ASSISTANT|>")
-            if isinstance(id_or_ids, (int,)):
-                return id_or_ids
-        except KeyError:
-            pass
+        id_or_ids = self.tokenizer.convert_tokens_to_ids("<|ASSISTANT|>")
+        if isinstance(id_or_ids, (int,)):
+            return id_or_ids
         return False
 
     def _tokenize(self, prompt: str, add_eos_token=True, strip_bos_token=False):
@@ -95,9 +87,7 @@ class InstructionPromptTokenizingStrategy(PromptTokenizingStrategy):
     Tokenizing strategy for instruction-based prompts.
     """
 
-    def parse_instruction_fields(
-        self, prompt
-    ) -> Union[Tuple[str, str, str], Tuple[str, str, str, str]]:
+    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str]:
         raise NotImplementedError
 
     def tokenize_prompt(self, prompt):
@@ -106,27 +96,25 @@ class InstructionPromptTokenizingStrategy(PromptTokenizingStrategy):
             input,  # pylint: disable=redefined-builtin
             response,
         ) = self.parse_instruction_fields(prompt)
-        user_prompt = next(
-            iter(
-                self.prompter.build_prompt(
-                    instruction,
-                    input,
+        full_prompt = self._build_full_prompt(instruction, input, response)
+        tokenized_full_prompt = self._tokenize(full_prompt)
+        if not self.train_on_inputs:
+            user_prompt = next(
+                iter(
+                    self.prompter.build_prompt(
+                        instruction,
+                        input,
+                    )
                 )
             )
-        )
-        tokenized_prompt = self._tokenize(user_prompt, add_eos_token=False)
-        if not self.train_on_inputs:
-            user_prompt_len = len(tokenized_prompt["input_ids"])
+            tokenized_user_prompt = self._tokenize(user_prompt, add_eos_token=False)
+            user_prompt_len = len(tokenized_user_prompt["input_ids"])
             # TODO this could be sped up using numpy array slicing
-            tokenized_prompt["labels"] = [-100] * user_prompt_len
-        tokenized_res_prompt = self._tokenize(
-            response, strip_bos_token=True, add_eos_token=True
-        )
-        tokenized_prompt["input_ids"] += tokenized_res_prompt["input_ids"]
-        tokenized_prompt["attention_mask"] += tokenized_res_prompt["attention_mask"]
-        tokenized_prompt["labels"] += tokenized_res_prompt["input_ids"]
+            tokenized_full_prompt["labels"] = [
+                -100
+            ] * user_prompt_len + tokenized_full_prompt["labels"][user_prompt_len:]
 
-        return tokenized_prompt
+        return tokenized_full_prompt
 
     def _build_full_prompt(
         self, instruction, input, response  # pylint: disable=redefined-builtin
@@ -392,7 +380,7 @@ class ShareGPTPromptTokenizingStrategy(PromptTokenizingStrategy):
                         # everything from this is masked out from the labels
                         labels = [IGNORE_TOKEN_ID] * len(res["input_ids"])
                     else:
-                        LOG.warning(f"unhandled role: {part[0]}")
+                        logging.warning(f"unhandled role: {part[0]}")
 
                 # pylint: disable=duplicate-code
                 result, current_len = parse_tokenized_to_result(
@@ -448,7 +436,7 @@ def parse_tokenized_to_result(
     result: Dict[str, List[int]],
     current_len: int,
     res: Dict[str, List[int]],
-    labels: List[int],
+    labels: list[int],
     pad_token_id: Union[int, None] = None,
 ) -> Tuple[Dict[str, List[int]], int]:
     """

src/axolotl/prompters.py

@@ -5,7 +5,6 @@ import logging
 from enum import Enum, auto
 from typing import Generator, List, Optional, Tuple, Union
 
-LOG = logging.getLogger("axolotl")
 IGNORE_TOKEN_ID = -100
 
 
@@ -16,7 +15,6 @@ class PromptStyle(Enum):
 
     INSTRUCT = "instruct"
     CHAT = "chat"
-    CHATML = "chatml"
 
 
 class AlpacaPrompter:
@@ -26,9 +24,6 @@ class AlpacaPrompter:
 
     system_prompt = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n"
     system_no_input_prompt = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n"
-    system_format: str
-    turn_format: str
-    turn_no_input_format: str
     prompt_style: Optional[PromptStyle] = None
 
     def __init__(self, prompt_style=PromptStyle.INSTRUCT.value):
@@ -36,23 +31,24 @@ class AlpacaPrompter:
         self.match_prompt_style()
 
     def match_prompt_style(self):
-        # pylint: disable=duplicate-code
         if self.prompt_style == PromptStyle.INSTRUCT.value:
-            self.turn_format = "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
-            self.turn_no_input_format = (
-                "### Instruction:\n{instruction}\n\n### Response:\n"
+            self.prompt_input = (
+                self.system_prompt
+                + "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
             )
-            self.system_format = "### System:\n{system}\n\n"
+            self.prompt_no_input = (
+                self.system_no_input_prompt
+                + "### Instruction:\n{instruction}\n\n### Response:\n"
+            )
+            self.response_split = "### Response:"
         if self.prompt_style == PromptStyle.CHAT.value:
-            self.turn_format = "USER: {instruction}\n{input}\nASSISTANT:"
-            self.turn_no_input_format = "USER: {instruction}\nASSISTANT:"
-            self.system_format = "SYSTEM: {system}\n"
-        if self.prompt_style == PromptStyle.CHATML.value:
-            self.turn_format = "<|im_start|>user\n{instruction}\n{input}<|im_end|>\n<|im_start|>assistant\n"
-            self.turn_no_input_format = (
-                "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
+            self.prompt_input = (
+                self.system_prompt + "USER: {instruction}\n{input}\nASSISTANT:"
             )
-            self.system_format = "<|im_start|>system\n{system}<|im_end|>\n"
+            self.prompt_no_input = (
+                self.system_no_input_prompt + "USER: {instruction}\nASSISTANT:"
+            )
+            self.response_split = "ASSISTANT:"
 
     def build_prompt(
         self,
@@ -63,17 +59,16 @@ class AlpacaPrompter:
         # returns the full prompt from instruction and optional input
         # if a label (=response, =output) is provided, it's also appended.
         if input:
-            res = self.system_prompt + self.turn_format.format(
-                instruction=instruction, input=input
-            )
+            res = self.prompt_input.format(instruction=instruction, input=input)
         else:
-            res = self.system_no_input_prompt + self.turn_no_input_format.format(
-                instruction=instruction
-            )
+            res = self.prompt_no_input.format(instruction=instruction)
         if output:
             res = f"{res}{output}"
         yield res
 
+    def get_response(self, output: str) -> str:
+        return output.split(self.response_split)[1].strip()
+
 
 class UnpromptedPrompter(AlpacaPrompter):
     """
@@ -98,10 +93,7 @@ class MultipleChoiceExplainPrompter(AlpacaPrompter):
     """
 
     system_prompt = (
-        "Choose the answer that best answers the question. Explain your reasoning.\n"
-    )
-    system_no_input_prompt = (
-        "Choose the answer that best answers the question. Explain your reasoning.\n"
+        "Choose the answer that best answers the question. Explain your reasoning."
     )
 
 
@@ -110,12 +102,7 @@ class MultipleChoiceConcisePrompter(AlpacaPrompter):
     Prompter for multiple choice concise
     """
 
-    system_prompt = "Choose the answer that best answers the question. Be concise in your response.\n\n"
-    system_no_input_prompt = "Choose the answer that best answers the question. Be concise in your response.\n\n"
-
-    def match_prompt_style(self):
-        self.turn_format = "USER: {instruction}\n{input}\nASSISTANT:"
-        self.turn_no_input_format = "USER: {instruction}\nASSISTANT:"
+    prompt_input = "Choose the answer that best answers the question. Be concise in your response.\n\nUSER: {instruction}\n{input}\nASSISTANT:\n"
 
 
 class SummarizeTLDRPrompter(AlpacaPrompter):
@@ -123,12 +110,9 @@ class SummarizeTLDRPrompter(AlpacaPrompter):
     Prompter for summarize TLDR
     """
 
-    system_prompt = ""
-    system_no_input_prompt = ""
-
-    def match_prompt_style(self):
-        self.turn_format = "USER: Summarize the following article as a TL;DR.\n{instruction}\n{input}\nASSISTANT:"
-        self.turn_no_input_format = "USER: Summarize the following article as a TL;DR.\n{instruction}\nASSISTANT:"
+    prompt_no_input = (
+        "USER: Summarize the following article as a TL;DR.\n{instruction}\nASSISTANT:"
+    )
 
 
 class CompletionPrompter:
@@ -144,6 +128,9 @@ class CompletionPrompter:
     ) -> Generator[str, None, None]:
         yield instruction
 
+    def get_response(self, output: str) -> str:
+        return output.strip()
+
 
 class GPTeacherPrompter(AlpacaPrompter):
     """
@@ -223,6 +210,9 @@ class ReflectAlpacaPrompter:
             res = f"{res}{label}"
         yield res
 
+    def get_response(self, output: str) -> str:
+        return output.split(self.response_split)[1].strip()
+
 
 class SeparatorStyle(Enum):
     """Different separator style."""
@@ -253,7 +243,7 @@ class Conversation:
             if message:
                 yield (role + ":", " " + message)
             else:
-                LOG.warning(f"role with empty message: {role}")
+                logging.warning(f"role with empty message: {role}")
                 yield (role + ":", "")
 
     def copy(self):
@@ -271,33 +261,34 @@ class Conversation:
         self.messages.append([role, message])
 
 
+conv_vicuna_v1_1 = Conversation(
+    system="A chat between a curious user and an artificial intelligence assistant. "
+    "The assistant gives helpful, detailed, and polite answers to the user's questions.",
+    roles=["USER", "ASSISTANT"],
+    messages=[],
+    offset=0,
+    sep_style=SeparatorStyle.TWO,
+    sep=" ",
+    sep2=" ",
+)
+
+
 class ShareGPTPrompter:  # pylint: disable=too-few-public-methods
     """
     A prompter that generates prompts for the ShareGPT
     """
 
-    def __init__(self, prompt_style=None, system_prompt: Optional[str] = None):
+    def __init__(self, prompt_style=None):
         if prompt_style != PromptStyle.CHAT.value:
             raise ValueError(
                 f"unsupported prompt_style for ShareGPTPrompter({prompt_style})"
             )
-        system: str = (
-            system_prompt
-            if system_prompt
-            else (
-                "A chat between a curious user and an artificial intelligence assistant. "
-                "The assistant gives helpful, detailed, and polite answers to the user's questions."
-            )
-        )
-        self._conversation = Conversation(
-            system=system,
-            roles=["USER", "ASSISTANT"],
-            messages=[],
-            offset=0,
-            sep_style=SeparatorStyle.TWO,
-            sep=" ",
-            sep2=" ",
-        )
+
+    # def match_prompt_style(self):
+    #     if self.prompt_style == PromptStyle.chat.value:
+    #         self.prompt_input = self.system_prompt + "USER: {instruction}\n{input}\nASSISTANT:"
+    #         self.prompt_no_input = self.system_no_input_prompt + "USER: {instruction}\nASSISTANT:"
+    #         self.response_split = "ASSISTANT:"
 
     def build_prompt(self, source) -> Generator[str, None, None]:
         # ignore the system prompt if provided
@@ -309,7 +300,7 @@ class ShareGPTPrompter:  # pylint: disable=too-few-public-methods
             # also happens on the data splitting leaving empty conversations
             raise IndexError
 
-        conv = self._conversation.copy()
+        conv = conv_vicuna_v1_1.copy()
         roles = {"human": conv.roles[0], "gpt": conv.roles[1]}
 
         try:

src/axolotl/utils/collators.py

@@ -1,121 +0,0 @@
-"""
-DataCollator for axolotl to pad labels and position_ids for packed sequences
-"""
-from dataclasses import dataclass
-from typing import Any, Optional, Union
-
-import numpy as np
-from transformers import PreTrainedTokenizerBase
-from transformers.utils import PaddingStrategy
-
-
-@dataclass
-class DataCollatorForSeq2Seq:
-    """
-    Data collator that will dynamically pad the inputs received, as well as the labels and position_ids
-
-    Args:
-        tokenizer ([`PreTrainedTokenizer`] or [`PreTrainedTokenizerFast`]):
-            The tokenizer used for encoding the data.
-        model ([`PreTrainedModel`]):
-            The model that is being trained. If set and has the *prepare_decoder_input_ids_from_labels*, use it to
-            prepare the *decoder_input_ids*
-
-            This is useful when using *label_smoothing* to avoid calculating loss twice.
-        padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`):
-            Select a strategy to pad the returned sequences (according to the model's padding side and padding index)
-            among:
-
-            - `True` or `'longest'` (default): Pad to the longest sequence in the batch (or no padding if only a single
-              sequence is provided).
-            - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
-              acceptable input length for the model if that argument is not provided.
-            - `False` or `'do_not_pad'`: No padding (i.e., can output a batch with sequences of different lengths).
-        max_length (`int`, *optional*):
-            Maximum length of the returned list and optionally padding length (see above).
-        pad_to_multiple_of (`int`, *optional*):
-            If set will pad the sequence to a multiple of the provided value.
-
-            This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >=
-            7.5 (Volta).
-        label_pad_token_id (`int`, *optional*, defaults to -100):
-            The id to use when padding the labels (-100 will be automatically ignored by PyTorch loss functions).
-        return_tensors (`str`):
-            The type of Tensor to return. Allowable values are "np", "pt" and "tf".
-    """
-
-    tokenizer: PreTrainedTokenizerBase
-    model: Optional[Any] = None
-    padding: Union[bool, str, PaddingStrategy] = True
-    max_length: Optional[int] = None
-    pad_to_multiple_of: Optional[int] = None
-    label_pad_token_id: int = -100
-    position_pad_token_id: int = 0
-    return_tensors: str = "pt"
-
-    def __call__(self, features, return_tensors=None):
-        labels = None
-        if return_tensors is None:
-            return_tensors = self.return_tensors
-
-        for feature_name, pad_token_id in [
-            ("labels", self.label_pad_token_id),
-            ("position_ids", self.position_pad_token_id),
-        ]:
-            feat = (
-                [feature[feature_name] for feature in features]
-                if feature_name in features[0].keys()
-                else None
-            )
-            labels = feat if feat and feature_name == "labels" else labels
-            # We have to pad the labels before calling `tokenizer.pad` as this method won't pad them and needs them of the
-            # same length to return tensors.
-            if feat is not None:
-                max_feature_length = max(len(l) for l in feat)  # noqa: E741
-                if self.pad_to_multiple_of is not None:
-                    max_feature_length = (
-                        (max_feature_length + self.pad_to_multiple_of - 1)
-                        // self.pad_to_multiple_of
-                        * self.pad_to_multiple_of
-                    )
-
-                padding_side = self.tokenizer.padding_side
-                for feature in features:
-                    remainder = [pad_token_id] * (
-                        max_feature_length - len(feature[feature_name])
-                    )
-                    if isinstance(feature[feature_name], list):
-                        feature[feature_name] = (
-                            feature[feature_name] + remainder
-                            if padding_side == "right"
-                            else remainder + feature[feature_name]
-                        )
-                    elif padding_side == "right":
-                        feature[feature_name] = np.concatenate(
-                            [feature[feature_name], remainder]
-                        ).astype(np.int64)
-                    else:
-                        feature[feature_name] = np.concatenate(
-                            [remainder, feature[feature_name]]
-                        ).astype(np.int64)
-
-        features = self.tokenizer.pad(
-            features,
-            padding=self.padding,
-            max_length=self.max_length,
-            pad_to_multiple_of=self.pad_to_multiple_of,
-            return_tensors=return_tensors,
-        )
-
-        # prepare decoder_input_ids
-        if (
-            labels is not None
-            and self.model is not None
-            and hasattr(self.model, "prepare_decoder_input_ids_from_labels")
-        ):
-            decoder_input_ids = self.model.prepare_decoder_input_ids_from_labels(
-                labels=features["labels"]
-            )
-            features["decoder_input_ids"] = decoder_input_ids
-
-        return features

src/axolotl/utils/data.py

@@ -1,14 +1,12 @@
 """Module containing data utilities"""
-import functools
-import hashlib
-import itertools
+
 import logging
 from hashlib import md5
 from pathlib import Path
 from typing import List, Tuple, Union
 
 import torch
-from datasets import Dataset, DatasetDict, load_dataset, load_from_disk
+from datasets import Dataset, DatasetDict, IterableDataset, load_dataset, load_from_disk
 from huggingface_hub import hf_hub_download
 from transformers import PreTrainedTokenizerBase
 
@@ -36,9 +34,6 @@ from axolotl.prompters import (
     ShareGPTPrompter,
     SummarizeTLDRPrompter,
 )
-from axolotl.utils.distributed import barrier, is_main_process
-
-LOG = logging.getLogger("axolotl")
 
 
 def load_tokenized_prepared_datasets(
@@ -78,19 +73,12 @@ def load_tokenized_prepared_datasets(
     if dataset:
         ...
     elif any(prepared_ds_path.glob("*")):
-        LOG.info(f"Loading prepared dataset from disk at {prepared_ds_path}...")
+        logging.info(f"Loading prepared dataset from disk at {prepared_ds_path}...")
         dataset = load_from_disk(str(prepared_ds_path))
-        LOG.info("Prepared dataset loaded from disk...")
+        logging.info("Prepared dataset loaded from disk...")
     else:
-        LOG.info(f"Unable to find prepared dataset in {prepared_ds_path}")
-        LOG.info("Loading raw datasets...")
-
-        if cfg.seed:
-            seed = cfg.seed
-        else:
-            LOG.info("No seed provided, using default seed of 42")
-            seed = 42
-
+        logging.info(f"Unable to find prepared dataset in {prepared_ds_path}")
+        logging.info("Loading raw datasets...")
         datasets = []
         # pylint: disable=invalid-name
         for d in cfg.datasets:
@@ -99,7 +87,6 @@ def load_tokenized_prepared_datasets(
             try:
                 load_dataset(
                     d.path,
-                    name=d.name,
                     streaming=True,
                     use_auth_token=use_auth_token,
                 )
@@ -108,56 +95,44 @@ def load_tokenized_prepared_datasets(
                 pass
 
             # prefer local dataset, even if hub exists
-            local_path = Path(d.path)
-            if local_path.exists():
-                if local_path.is_dir():
-                    # TODO dirs with arrow or parquet files could be loaded with `load_from_disk`
+            if Path(d.path).exists():
+                ds = load_dataset(
+                    "json",
+                    data_files=d.path,
+                    streaming=False,
+                    split=None,
+                )
+            elif ds_from_hub:
+                if d.data_files:
                     ds = load_dataset(
                         d.path,
-                        name=d.name,
+                        streaming=False,
                         data_files=d.data_files,
-                        streaming=False,
-                        split=None,
-                    )
-                elif local_path.is_file():
-                    ds = load_dataset(
-                        "json",
-                        name=d.name,
-                        data_files=d.path,
-                        streaming=False,
-                        split=None,
+                        use_auth_token=use_auth_token,
                     )
                 else:
-                    raise ValueError(
-                        "unhandled dataset load: local path exists, but is neither a directory or a file"
+                    ds = load_dataset(
+                        d.path,
+                        streaming=False,
+                        use_auth_token=use_auth_token,
                     )
-            elif ds_from_hub:
-                ds = load_dataset(
-                    d.path,
-                    name=d.name,
-                    streaming=False,
-                    data_files=d.data_files,
-                    use_auth_token=use_auth_token,
-                )
             else:
                 fp = hf_hub_download(
                     repo_id=d.path,
                     repo_type="dataset",
                     filename=d.data_files,
                 )
-                ds = load_dataset(
-                    "json", name=d.name, data_files=fp, streaming=False, split=None
-                )
+                ds = load_dataset("json", data_files=fp, streaming=False, split=None)
             if not ds:
                 raise ValueError("unhandled dataset load")
             # support for using a subset of the data
             if d.shards:
                 if "train" in ds:
-                    ds = ds.shuffle(seed=seed)["train"].shard(
+                    ds = ds.shuffle(seed=42)["train"].shard(
                         num_shards=d.shards, index=0
                     )
                 else:
-                    ds = ds.shuffle(seed=seed).shard(num_shards=d.shards, index=0)
+                    ds = ds.shuffle(seed=42).shard(num_shards=d.shards, index=0)
             d_type = d.type
             d_type_split = d_type.split(":")
             d_base_type = d_type_split[0]
@@ -258,32 +233,21 @@ def load_tokenized_prepared_datasets(
                 ds_wrapper = TokenizedPromptDataset(ds_strategy, ds)
                 datasets.append(ds_wrapper)
             else:
-                suffix = ""
-                if ":load_" in d.type:
-                    suffix = f" Did you mean {d.type.replace(':load_', '.load_')}?"
-                LOG.error(f"unhandled prompt tokenization strategy: {d.type}. {suffix}")
-                raise ValueError(
-                    f"unhandled prompt tokenization strategy: {d.type} {suffix}"
-                )
-        LOG.info("tokenizing, merging, and shuffling master dataset")
+                logging.error(f"unhandled prompt tokenization strategy: {d.type}")
+                raise ValueError(f"unhandled prompt tokenization strategy: {d.type}")
+        logging.info("tokenizing, merging, and shuffling master dataset")
 
         samples: List[int] = []
-        chunk_size = 1000
         for d in datasets:
-            d_iter = iter(d)
-            while True:
-                chunk = list(itertools.islice(d_iter, chunk_size))
-                if not chunk:
-                    break
-                samples.extend(chunk)
-
-        LOG.info("shuffle")
-        dataset = Dataset.from_list(samples).shuffle(seed=seed)
+            samples = samples + list(d)
+        dataset = Dataset.from_list(samples).shuffle(seed=42)
         if cfg.local_rank == 0:
-            LOG.info(f"Saving merged prepared dataset to disk... {prepared_ds_path}")
+            logging.info(
+                f"Saving merged prepared dataset to disk... {prepared_ds_path}"
+            )
             dataset.save_to_disk(prepared_ds_path)
             if cfg.push_dataset_to_hub:
-                LOG.info(
+                logging.info(
                     f"Saving merged prepared dataset with push_to_hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                 )
                 dataset.push_to_hub(
@@ -334,7 +298,7 @@ def load_prepare_datasets(
         use_auth_token = cfg.hf_use_auth_token
         try:
             if cfg.push_dataset_to_hub:
-                LOG.info(
+                logging.info(
                     f"Checking for packed prepared dataset from hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                 )
                 dataset = load_dataset(
@@ -348,13 +312,13 @@ def load_prepare_datasets(
         if dataset:
             ...
         elif any(prepared_ds_path.glob("*")):
-            LOG.info(
+            logging.info(
                 f"Loading prepared packed dataset from disk at {prepared_ds_path}..."
             )
             dataset = load_from_disk(str(prepared_ds_path))
-            LOG.info("Prepared packed dataset loaded from disk...")
+            logging.info("Prepared packed dataset loaded from disk...")
             if cfg.push_dataset_to_hub:
-                LOG.info(
+                logging.info(
                     f"Saving packed prepared dataset with push_to_hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                 )
                 dataset.push_to_hub(
@@ -373,16 +337,17 @@ def load_prepare_datasets(
                 [dataset],
                 seq_length=max_packed_sequence_len,
             )
-            LOG.info(f"packing master dataset to len: {cfg.max_packed_sequence_len}")
+            logging.info(
+                f"packing master dataset to len: {cfg.max_packed_sequence_len}"
+            )
             dataset = Dataset.from_list(list(constant_len_dataset))
 
             # filter out bad data
-            # TODO convert to dataset.filter(...)
             dataset = Dataset.from_list(
                 [
                     d
                     for d in dataset
-                    if len(d["input_ids"]) <= cfg.sequence_len
+                    if len(d["input_ids"]) < cfg.sequence_len
                     and len(d["input_ids"]) > 0
                     and len(d["input_ids"]) == len(d["attention_mask"])
                     and len(d["input_ids"]) == len(d["labels"])
@@ -390,12 +355,12 @@ def load_prepare_datasets(
             )
 
             if cfg.local_rank == 0:
-                LOG.info(
+                logging.info(
                     f"Saving packed prepared dataset to disk... {prepared_ds_path}"
                 )
                 dataset.save_to_disk(prepared_ds_path)
                 if cfg.push_dataset_to_hub:
-                    LOG.info(
+                    logging.info(
                         f"Saving packed prepared dataset with push_to_hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                     )
                     dataset.push_to_hub(
@@ -408,7 +373,7 @@ def load_prepare_datasets(
         )
 
     if cfg.dataset_shard_num and cfg.dataset_shard_idx is not None:
-        LOG.info(
+        logging.info(
             f"Using index #{cfg.dataset_shard_idx} of {cfg.dataset_shard_num} shards"
         )
         dataset = dataset.shard(
@@ -417,51 +382,7 @@ def load_prepare_datasets(
         )
 
     if cfg.val_set_size:
-        # ensure we end up with the same fingerprint by doing rank0 first and being able to cache
-        to_hash_train = (
-            dataset._fingerprint  # pylint: disable=protected-access
-            + "|"
-            + str(cfg.val_set_size)
-            + "|"
-            + "train"
-            + "|"
-            + str(cfg.seed or 42)
-        )
-        to_hash_test = (
-            dataset._fingerprint  # pylint: disable=protected-access
-            + "|"
-            + str(cfg.val_set_size)
-            + "|"
-            + "test"
-            + "|"
-            + str(cfg.seed or 42)
-        )
-        train_fingerprint = hashlib.md5(
-            to_hash_train.encode(), usedforsecurity=False
-        ).hexdigest()
-        test_fingerprint = hashlib.md5(
-            to_hash_test.encode(), usedforsecurity=False
-        ).hexdigest()
-
-        if is_main_process():
-            dataset = dataset.train_test_split(
-                test_size=cfg.val_set_size,
-                shuffle=False,
-                seed=cfg.seed or 42,
-                train_new_fingerprint=train_fingerprint,
-                test_new_fingerprint=test_fingerprint,
-            )
-        barrier()
-        if not is_main_process():
-            dataset = dataset.train_test_split(
-                test_size=cfg.val_set_size,
-                shuffle=False,
-                seed=cfg.seed or 42,
-                train_new_fingerprint=train_fingerprint,
-                test_new_fingerprint=test_fingerprint,
-            )
-        barrier()
-
+        dataset = dataset.train_test_split(test_size=cfg.val_set_size, shuffle=False)
         train_dataset = dataset["train"]
         eval_dataset = dataset["test"]
     else:
@@ -471,116 +392,32 @@ def load_prepare_datasets(
     return train_dataset, eval_dataset
 
 
-def encode_pretraining(tokenizer, max_tokens, examples):
-    res = tokenizer(
-        examples["text"],
-        truncation=True,
-        max_length=max_tokens - 2,
-        add_special_tokens=True,
-    )
-    # Convert to PyTorch tensors
-    input_ids = [torch.tensor(seq) for seq in res["input_ids"]]
-    attention_mask = [torch.tensor(seq) for seq in res["attention_mask"]]
-    new_input_ids = []
-    new_attention_mask = []
-    # Append EOS and PAD tokens to input_ids, and correct attention_mask
-    for i, _ in enumerate(input_ids):
-        input_ids[i] = torch.cat(
-            (
-                input_ids[i],
-                torch.tensor([tokenizer.eos_token_id, tokenizer.pad_token_id]),
-            ),
-            dim=0,
-        )
-        attention_mask[i] = torch.cat((attention_mask[i], torch.tensor([1, 0])), dim=0)
+class PretrainingDatasetWrapper(IterableDataset):
+    """
+    Wrapper for pretraining dataset that avoids loading the dataset into memory
+    """
 
-    # Concatenate tokens so that their lengths are less than max_tokens
-    buffer_input_ids = torch.tensor([], dtype=torch.long)
-    buffer_attention_mask = torch.tensor([], dtype=torch.long)
+    def __init__(self, tokenizer, dataset_path, max_tokens=2048):
+        self.tokenizer = tokenizer
+        self.dataset_path = dataset_path
+        self.max_tokens = max_tokens
 
-    for ids, mask in zip(input_ids, attention_mask):
-        if buffer_input_ids.numel() == max_tokens:
-            new_input_ids.append(buffer_input_ids)
-            new_attention_mask.append(buffer_attention_mask)
-            buffer_input_ids = torch.tensor([], dtype=torch.long)
-            buffer_attention_mask = torch.tensor([], dtype=torch.long)
-            buffer_input_ids = torch.cat((buffer_input_ids, ids), dim=0)
-            buffer_attention_mask = torch.cat((buffer_attention_mask, mask), dim=0)
-        elif buffer_input_ids.numel() + ids.numel() <= max_tokens:
-            buffer_input_ids = torch.cat((buffer_input_ids, ids), dim=0)
-            buffer_attention_mask = torch.cat((buffer_attention_mask, mask), dim=0)
-        else:
-            buffer_input_ids = torch.cat(
-                (
-                    buffer_input_ids,
-                    torch.full(
-                        (max_tokens - buffer_input_ids.numel(),),
-                        tokenizer.pad_token_id,
-                        dtype=torch.long,
-                    ),
-                ),
-                dim=0,
-            )
-            buffer_attention_mask = torch.cat(
-                (
-                    buffer_attention_mask,
-                    torch.full(
-                        (max_tokens - buffer_attention_mask.numel(),),
-                        0,
-                        dtype=torch.long,
-                    ),
-                ),
-                dim=0,
-            )
-            new_input_ids.append(buffer_input_ids)
-            new_attention_mask.append(buffer_attention_mask)
-            buffer_input_ids = torch.tensor([], dtype=torch.long)
-            buffer_attention_mask = torch.tensor([], dtype=torch.long)
-
-            buffer_input_ids = torch.cat((buffer_input_ids, ids), dim=0)
-            buffer_attention_mask = torch.cat((buffer_attention_mask, mask), dim=0)
-
-    if buffer_input_ids.numel() > 0:  # for any leftover tokens
-        while buffer_input_ids.numel() < max_tokens:  # make all sequences equal in size
-            buffer_input_ids = torch.cat(
-                (
-                    buffer_input_ids,
-                    torch.full(
-                        (max_tokens - buffer_input_ids.numel(),),
-                        tokenizer.pad_token_id,
-                        dtype=torch.long,
-                    ),
-                ),
-                dim=0,
-            )
-            buffer_attention_mask = torch.cat(
-                (
-                    buffer_attention_mask,
-                    torch.full(
-                        (max_tokens - buffer_attention_mask.numel(),),
-                        0,
-                        dtype=torch.long,
-                    ),
-                ),
-                dim=0,
-            )
-        new_input_ids.append(buffer_input_ids)
-        new_attention_mask.append(buffer_attention_mask)
-
-    ret = {
-        "input_ids": [seq.tolist() for seq in new_input_ids],
-        "labels": [seq.tolist() for seq in new_input_ids],
-        "attention_mask": [seq.tolist() for seq in new_attention_mask],
-    }
-
-    LOG.debug(len(ret["input_ids"]))
-    return ret
+    def __iter__(self):
+        buffer = []
+        for sample in load_dataset(
+            self.dataset_path,
+        )["train"].shuffle():
+            buffer += self.tokenizer(sample["text"])["input_ids"]
+            buffer += [self.tokenizer.eos_token_id]
+            while len(buffer) > self.max_tokens:
+                input_ids = torch.tensor(buffer[: self.max_tokens])
+                yield {
+                    "input_ids": input_ids,
+                    "attention_mask": torch.ones(input_ids.size()),
+                    "labels": input_ids,
+                }
+                buffer = buffer[self.max_tokens :]
 
 
-def load_pretraining_dataset(path, tokenizer, max_tokens=2048, seed=42):
-    encode = functools.partial(encode_pretraining, tokenizer, max_tokens)
-    dataset = load_dataset(path, streaming=True, split="train")
-    dataset = dataset.shuffle(seed=seed, buffer_size=10_000)
-    # TODO dynamically figure out which columns/features to remove
-    dataset = dataset.map(encode, batched=True, remove_columns=["text", "meta"])
-    return dataset
+def load_pretraining_dataset(path, tokenizer, max_tokens=2048):
+    return PretrainingDatasetWrapper(tokenizer, path, max_tokens=max_tokens)

src/axolotl/utils/dataloader.py

@@ -1,310 +0,0 @@
-# pylint: skip-file
-import hashlib
-import itertools
-import logging
-import math
-import queue
-import threading
-from typing import Any, Callable, List, Optional, Union
-
-import numba
-import numpy as np
-from torch.utils.data import DistributedSampler, Sampler
-
-LOG = logging.getLogger("axolotl.utils.dataloader")
-
-
-@numba.njit
-def ffd_check(a: np.ndarray, c: int, n: int):
-    # First-fit-decreasing bin packing
-    # Check if a[] could fit in n bins with capacity c
-    # https://en.wikipedia.org/wiki/First-fit-decreasing_bin_packing
-
-    a = np.sort(a)[::-1]
-    bins = np.full((n,), c, dtype=a.dtype)
-    for size in a:
-        not_found = True
-        for idx in range(n):
-            if bins[idx] >= size:
-                bins[idx] -= size
-                not_found = False
-                break
-
-        if not_found:
-            return False
-
-    return True
-
-
-@numba.njit
-def ffd_with_result(a: np.ndarray, c: int, start_index: int):
-    # First-fit-decreasing bin packing (with result return)
-
-    indices = np.argsort(a)[::-1]
-    a = a[indices]
-
-    bins: List[Any] = []
-    bins_result: List[Any] = []
-    for a_id, size in enumerate(a):
-        add_new = True
-        for idx in range(len(bins)):
-            if bins[idx] >= size:
-                bins[idx] -= size
-                bins_result[idx].append(indices[a_id] + start_index)
-                add_new = False
-                break
-
-        if add_new:
-            bins.append(c - size)
-            bins_result.append([indices[a_id] + start_index])
-
-    return bins_result, len(a)
-
-
-@numba.njit
-def allocate(
-    lengths: np.ndarray, lengths_cumsum: np.ndarray, rank: int, c: int, n: int
-):
-    """
-    :param lengths: array of lengths of each sample
-    :param lengths_cumsum: cumulative sum of consecutive lengths
-    :param rank: rank for this process
-    :param c: length of tokens per batch
-    :param n: number of ranks
-    :return:
-    """
-    # Dynamic batch allocator, similar to Multifit
-    # https://en.wikipedia.org/wiki/Multifit_algorithm
-    # ~99.5% efficiency on OpenChat training set (12 * 2048 ctx len)
-
-    s = 0
-    start_index = 0
-    result = []
-
-    while True:
-        # binary search [left, right)
-        left = 1
-        right = 1 + np.searchsorted(lengths_cumsum[start_index:], s + c * n, "right")
-
-        while right - left > 1:
-            mid = (left + right) // 2
-            if ffd_check(lengths[start_index : start_index + mid], c, n):
-                left = mid
-            else:
-                right = mid
-
-        # use length left
-        batch, tot_seqs = ffd_with_result(
-            lengths[start_index : start_index + left], c, start_index
-        )
-        if len(batch) < n:
-            break
-
-        start_index += left
-        s = lengths_cumsum[start_index - 1]
-
-        # add local rank
-        result.append(batch[rank])
-
-        yield batch[rank], tot_seqs, s, len(result) * c * n
-
-
-def chunk(iterable, n):
-    """
-    Chunk data into tuples of length n
-    """
-    # batched('ABCDEFG', 3) --> ABC DEF G
-    if n < 1:
-        raise ValueError("n must be at least one")
-    it = iter(iterable)
-    while batch := tuple(itertools.islice(it, n)):
-        yield batch
-
-
-def hash_indices(lst: List[int]) -> str:
-    # Convert the list of integers to a string representation
-    concatenated = ",".join(map(str, lst))
-
-    # Generate the hash
-    sha256 = hashlib.sha256()
-    sha256.update(concatenated.encode())
-
-    return sha256.hexdigest()
-
-
-class MultipackDistributedDataloader:
-    """Unpadded data loading using Multipack.
-    Adapted from https://github.com/imoneoi/openchat/blob/v3_fix_mle_loss/ochat/training_deepspeed/multipack_dataloader.py
-    Approximate (at most ~1.22x) the optimal solution of the identical-machines scheduling problem, which is NP-hard.
-    """
-
-    def __init__(
-        self,
-        dataset: Any,
-        collate_fn: Callable,
-        seq_max_length: int = 2048,
-        batch_size: int = 1,
-        sampler: Union[Sampler, DistributedSampler] = None,
-        packing_efficiency_estimate: float = 1.0,
-        sample_packing_seq_len_multiplier: int = 1,
-        device_count: int = 1,
-        total_num_tokens: Optional[int] = None,
-    ):
-        # Dataset
-        self.dataset = dataset
-        lengths_series = (
-            dataset.data.column("position_ids").to_pandas().apply(lambda x: x[-1] + 1)
-        )
-        self.lengths: np.ndarray = lengths_series.values
-        assert isinstance(self.lengths, np.ndarray)
-        assert batch_size % sample_packing_seq_len_multiplier == 0
-        assert batch_size >= sample_packing_seq_len_multiplier
-        self.sampler = sampler
-        self.batch_size = batch_size
-        self.sample_packing_seq_len_multiplier = sample_packing_seq_len_multiplier
-        self.seq_max_length = seq_max_length
-        self.batch_max_length = batch_size * seq_max_length
-        self.collate_fn = collate_fn
-
-        self.num_replicas = 1
-        self.rank = 0
-
-        # statistics
-        self.total_num_tokens = total_num_tokens
-        self.eff_total_used = 0
-        self.eff_total_slots = 0
-        self.packing_efficiency_estimate = packing_efficiency_estimate or 1.0
-        self.device_count = device_count
-
-        # for non-blocking batch creation
-        self.batch_queue: queue.Queue = queue.Queue(
-            maxsize=10
-        )  # Adjust maxsize as needed
-
-    def generate_batches(self, set_stats=False):
-        LOG.info("generating packed batches")
-        if self.sampler:
-            indices = [idx for idx in self.sampler]
-        else:
-            indices = range(0, len(self.dataset))
-
-        LOG.info(hash_indices(indices))
-        lengths = self.lengths[indices]
-        lengths_cumsum = np.cumsum(lengths)
-
-        alloc_iter = iter(
-            allocate(
-                lengths=lengths,
-                lengths_cumsum=lengths_cumsum,
-                rank=self.rank,
-                # c=self.batch_max_length,
-                c=self.seq_max_length * self.sample_packing_seq_len_multiplier,
-                n=self.num_replicas,
-            )
-        )
-
-        for batch, tot_seqs, total_used, total_slots in alloc_iter:
-            self.batch_queue.put([indices[b_idx] for b_idx in batch])
-            # statistics
-            if set_stats:
-                self.eff_total_used = total_used
-                self.eff_total_slots = total_slots
-        self.batch_queue.put(None)  # Signal the end of batch generation
-
-    def _generate_batches_thread(self):
-        try:
-            self.generate_batches(set_stats=True)
-        except Exception as e:
-            LOG.error(f"Error in batch generation thread: {e}")
-            self.batch_queue.put(
-                None
-            )  # Signal the end of batch generation in case of error
-
-    def __iter__(self):
-        if hasattr(self.sampler, "set_epoch"):
-            new_epoch = self.sampler.epoch + 1
-            self.sampler.set_epoch(new_epoch)
-            LOG.info(f"calling sampler.set_epoch({new_epoch})")
-        # Start the batch generation in a separate thread
-        batch_gen_thread = threading.Thread(target=self._generate_batches_thread)
-        batch_gen_thread.start()
-
-        features = self.dataset.features.keys()
-        len_remaining = self._len_est()
-        while True:
-            batch = self.batch_queue.get()
-            if batch is None:  # Sentinel value received, stop iteration
-                break
-            chunked_data = []
-            attn_mask_cum_idx = 0
-            concatenated = {}
-            batched_data = [self.dataset[batch_idx] for batch_idx in batch]
-            for feature in features:
-                if feature == "attention_mask":
-                    arrays = [
-                        (attn_mask_cum_idx + idx + 1) * np.array(item[feature])
-                        for idx, item in enumerate(batched_data)
-                        if feature in item
-                    ]
-                    attn_mask_cum_idx += len(batched_data)
-                    concatenated[feature] = np.concatenate(arrays)
-                else:
-                    arrays = [
-                        np.array(item[feature])
-                        for item in batched_data
-                        if feature in item
-                    ]
-                    concatenated[feature] = np.concatenate(arrays)
-            chunked_data.append(concatenated)
-
-            yield self.collate_fn(chunked_data)
-            len_remaining -= 1
-            if not len_remaining:
-                break
-        # Wait for the batch generation thread to finish
-        batch_gen_thread.join(timeout=5)
-        LOG.info(f"actual packing efficiency: {self.efficiency()}")
-
-    def _len_est(self):
-        if not self.total_num_tokens:
-            self.total_num_tokens = np.sum(self.lengths)
-        lengths_sum_per_device = self.total_num_tokens // self.device_count
-        LOG.info(
-            f"packing_efficiency_estimate: {self.packing_efficiency_estimate} "
-            f"total_num_tokens per device: {lengths_sum_per_device}"
-        )
-
-        # shave off 1% + 1 for dealing with variance in packing from random sampler to sampler
-        return (
-            math.floor(
-                0.99
-                * lengths_sum_per_device
-                / self.packing_efficiency_estimate
-                // self.seq_max_length
-                // self.batch_size
-            )
-            - 1
-        )
-
-    def __len__(self):
-        # this doesn't return the actual length b/c with distributed samplers, not all dataloaders get
-        # the same share of total tokens
-        # if not self.eff_total_used:
-        #     batches, _ = self.generate_batches(set_stats=True)
-        # LOG.info(
-        #     f"packing_efficiency_estimate: {self.packing_efficiency_estimate} "
-        #     f"actual packing efficiency: {self.efficiency()}"
-        # )
-        return max(1, self._len_est())
-
-    def len_w_stats(self):
-        if not self.eff_total_used:
-            batches, _ = self.generate_batches(set_stats=True)
-        LOG.info(
-            f"packing_efficiency_estimate: {self.packing_efficiency_estimate} "
-            f"actual packing efficiency: {self.efficiency()}"
-        )
-        return max(1, self._len_est())
-
-    def efficiency(self):
-        return self.eff_total_used / self.eff_total_slots

src/axolotl/utils/distributed.py

@@ -1,41 +0,0 @@
-"""
-utility helpers for distributed checks
-"""
-import torch.distributed as dist
-from accelerate import Accelerator
-
-accelerate = None  # pylint: disable=invalid-name
-
-
-def load_accelerate():
-    global accelerate  # pylint: disable=global-statement
-    accelerate = Accelerator()
-
-
-def is_distributed():
-    """
-    Check if distributed training is initialized.
-    """
-    global accelerate  # pylint: disable=global-statement
-    if not accelerate:
-        accelerate = Accelerator()
-    return dist.is_available() and dist.is_initialized()
-
-
-def barrier():
-    """
-    Acts as a barrier to wait for all processes. This ensures that all processes
-    reach the barrier before proceeding further.
-    """
-    if is_distributed():
-        dist.barrier()
-
-
-def is_main_process():
-    """
-    Check if the current process is the main process.
-    If not in distributed mode, always return True.
-    """
-    if not is_distributed():
-        return True
-    return dist.get_rank() == 0

src/axolotl/utils/models.py

@@ -11,19 +11,23 @@ import bitsandbytes as bnb
 import torch
 import transformers
 from optimum.bettertransformer import BetterTransformer
-from transformers import (  # noqa: F401
+from transformers import PreTrainedModel  # noqa: F401
+from transformers import (
     AutoConfig,
     AutoModelForCausalLM,
     AutoTokenizer,
     BitsAndBytesConfig,
     LlamaConfig,
-    PreTrainedModel,
-    PreTrainedTokenizerBase,
 )
 
-from axolotl.prompt_tokenizers import LLAMA_DEFAULT_PAD_TOKEN
+try:
+    from transformers import LlamaForCausalLM
+except ImportError:
+    logging.warning(
+        "This version of transformers does not support Llama. Consider upgrading."
+    )
 
-LOG = logging.getLogger("axolotl")
+from axolotl.prompt_tokenizers import LLAMA_DEFAULT_PAD_TOKEN
 
 if TYPE_CHECKING:
     from peft import PeftConfig  # noqa: F401
@@ -36,32 +40,21 @@ def load_tokenizer(
     tokenizer_type,
     cfg,
 ):
-    tokenizer_kwargs = {}
-    use_fast = True  # this is the default
-    if cfg.tokenizer_use_fast is not None:
-        use_fast = cfg.tokenizer_use_fast
-    if cfg.tokenizer_legacy is not None:
-        # True is the default w/ https://github.com/huggingface/transformers/pull/25224
-        tokenizer_kwargs["legacy"] = cfg.tokenizer_legacy
     if tokenizer_type:
         tokenizer = getattr(transformers, tokenizer_type).from_pretrained(
             tokenizer_config,
             trust_remote_code=cfg.trust_remote_code or False,
-            use_fast=use_fast,
-            **tokenizer_kwargs,
         )
     else:
         tokenizer = AutoTokenizer.from_pretrained(
             tokenizer_config,
             trust_remote_code=cfg.trust_remote_code or False,
-            use_fast=use_fast,
-            **tokenizer_kwargs,
         )
 
-    LOG.debug(f"EOS: {tokenizer.eos_token_id} / {tokenizer.eos_token}")
-    LOG.debug(f"BOS: {tokenizer.bos_token_id} / {tokenizer.bos_token}")
-    LOG.debug(f"PAD: {tokenizer.pad_token_id} / {tokenizer.pad_token}")
-    LOG.debug(f"UNK: {tokenizer.unk_token_id} / {tokenizer.unk_token}")
+    logging.debug(f"EOS: {tokenizer.eos_token_id} / {tokenizer.eos_token}")
+    logging.debug(f"BOS: {tokenizer.bos_token_id} / {tokenizer.bos_token}")
+    logging.debug(f"PAD: {tokenizer.pad_token_id} / {tokenizer.pad_token}")
+    logging.debug(f"UNK: {tokenizer.unk_token_id} / {tokenizer.unk_token}")
 
     if tokenizer.__class__.__name__ in [
         "LlamaTokenizer",
@@ -83,70 +76,45 @@ def load_tokenizer(
 
 
 def load_model(
-    base_model, base_model_config, model_type, tokenizer, cfg, adapter="lora"
+    base_model,
+    base_model_config,
+    model_type,
+    tokenizer,
+    cfg,
+    adapter="lora",
+    inference=False,
 ):
-    # type: (str, str, str, PreTrainedTokenizerBase, DictDefault, Optional[str]) -> Tuple[PreTrainedModel, Optional[PeftConfig]]
+    # type: (str, str, str, str, DictDefault, Optional[str], bool) -> Tuple[PreTrainedModel, Optional[PeftConfig]]
     """
     Load a model from a base model and a model type.
     """
 
     # TODO refactor as a kwarg
     load_in_8bit = cfg.load_in_8bit
-    cfg.is_llama_derived_model = (
-        "llama" in base_model
-        or (cfg.model_type and "llama" in cfg.model_type.lower())
-        or cfg.is_llama_derived_model is True
+    is_llama_derived_model = "llama" in base_model or (
+        cfg.model_type and "llama" in cfg.model_type.lower()
     )
 
-    if cfg.is_llama_derived_model and cfg.flash_attention:
-        if cfg.device not in ["mps", "cpu"] and not cfg.inference:
-            from axolotl.monkeypatch.llama_attn_hijack_flash import (
-                replace_llama_attn_with_flash_attn,
-            )
+    if is_llama_derived_model and cfg.flash_attention:
+        if cfg.device not in ["mps", "cpu"] and inference is False:
+            from axolotl.flash_attn import replace_llama_attn_with_flash_attn
 
-            LOG.info("patching with flash attention")
+            logging.info("patching with flash attention")
             replace_llama_attn_with_flash_attn()
-    elif cfg.is_llama_derived_model and cfg.xformers_attention:
+    elif is_llama_derived_model and cfg.xformers_attention:
         from axolotl.monkeypatch.llama_attn_hijack_xformers import (
             hijack_llama_attention,
         )
 
-        LOG.info("patching with xformers attention")
+        logging.info("patching with xformers attention")
         hijack_llama_attention()
-    elif cfg.is_llama_derived_model and cfg.sdp_attention:
+    elif is_llama_derived_model and cfg.sdp_attention:
         from axolotl.monkeypatch.llama_attn_hijack_xformers import (
             hijack_llama_sdp_attention,
         )
 
-        LOG.info("patching with sdp attention")
+        logging.info("patching with sdp attention")
         hijack_llama_sdp_attention()
-    elif cfg.is_llama_derived_model and cfg.landmark_attention:
-        from axolotl.monkeypatch.llama_landmark_attn import (
-            MEM_TOKEN,
-            patch_llama_with_landmark_attn,
-        )
-
-        LOG.info("patching with landmark attention")
-        patch_llama_with_landmark_attn()
-
-        # Note: This might overwrite previous additional_special_tokens
-        tokenizer.add_special_tokens({"additional_special_tokens": [MEM_TOKEN]})
-
-    if cfg.is_llama_derived_model and cfg.xpos_rope:
-        from axolotl.monkeypatch.xpos_rope_llama_monkey_patch import (
-            replace_llama_rope_with_xpos_rope,
-        )
-
-        LOG.info("patching with xpos rope")
-        replace_llama_rope_with_xpos_rope()
-
-    if cfg.is_llama_derived_model and (
-        cfg.max_packed_sequence_len or cfg.sample_packing
-    ):
-        from axolotl.monkeypatch.llama_expand_mask import hijack_expand_mask
-
-        LOG.info("patching _expand_mask")
-        hijack_expand_mask()
 
     if cfg.bf16 or cfg.bfloat16:
         torch_dtype = torch.bfloat16
@@ -161,25 +129,12 @@ def load_model(
             )
 
             replace_peft_model_with_int4_lora_model()
+        from peft import prepare_model_for_int8_training
     except Exception as err:
-        LOG.exception(err)
+        logging.exception(err)
         raise err
 
-    if not cfg.gptq and (
-        (cfg.adapter == "lora" and load_in_8bit)
-        or (cfg.adapter == "qlora" and cfg.load_in_4bit)
-    ):
-        try:
-            from peft import prepare_model_for_kbit_training
-        except ImportError:
-            # For backward compatibility
-            from peft import (
-                prepare_model_for_int8_training as prepare_model_for_kbit_training,
-            )
-
     model_kwargs = {}
-    if cfg.model_revision:
-        model_kwargs["revision"] = cfg.model_revision
     if cfg.adapter == "qlora" and cfg.load_in_4bit:
         model_kwargs["quantization_config"] = BitsAndBytesConfig(
             load_in_4bit=True,
@@ -190,7 +145,7 @@ def load_model(
             bnb_4bit_quant_type="nf4",
         )
     try:
-        if cfg.gptq and cfg.is_llama_derived_model:
+        if cfg.gptq and is_llama_derived_model:
             from alpaca_lora_4bit.autograd_4bit import load_llama_model_4bit_low_ram
             from huggingface_hub import snapshot_download
 
@@ -211,7 +166,7 @@ def load_model(
                 if len(files) > 0:
                     model_path = str(files[0])
                 else:
-                    LOG.warning(
+                    logging.warning(
                         "unable to find a cached model file, this will likely fail..."
                     )
                     model_path = str(cache_model_path)
@@ -228,9 +183,7 @@ def load_model(
                 else True,
             )
             load_in_8bit = False
-        elif cfg.is_llama_derived_model and not cfg.trust_remote_code:
-            from transformers import LlamaForCausalLM
-
+        elif is_llama_derived_model and "LlamaForCausalLM" in globals():
             config = LlamaConfig.from_pretrained(base_model_config)
             model = LlamaForCausalLM.from_pretrained(
                 base_model,
@@ -238,6 +191,7 @@ def load_model(
                 load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
                 load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
                 torch_dtype=torch_dtype,
+                device_map="auto" if cfg.world_size == 1 else cfg.device_map,
                 **model_kwargs,
             )
         # elif model_type == "GPTNeoXForCausalLM" and cfg.flash_attention:
@@ -266,12 +220,13 @@ def load_model(
         #         device=cfg.device,
         #     )
         #     model.train() # sets to train instead of eval mode
-        elif model_type and not cfg.trust_remote_code:
+        elif model_type:
             model = getattr(transformers, model_type).from_pretrained(
                 base_model,
                 load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
                 load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
                 torch_dtype=torch_dtype,
+                device_map=cfg.device_map,
                 trust_remote_code=cfg.trust_remote_code or False,
                 **model_kwargs,
             )
@@ -280,58 +235,35 @@ def load_model(
                 base_model,
                 trust_remote_code=cfg.trust_remote_code or False,
             )
-            # Shouldn't be a problem most of the time. will obviously error if the model doesn't support this
-            # when training starts
-            if (
-                hasattr(config, "max_seq_len")
-                and config.max_seq_len
-                and cfg.sequence_len > config.max_seq_len
-            ):
-                config.max_seq_len = cfg.sequence_len
-                LOG.warning(f"increasing context length to {cfg.sequence_len}")
-            elif (
-                hasattr(config, "max_sequence_length")
-                and config.max_sequence_length
-                and cfg.sequence_len > config.max_sequence_length
-            ):
-                config.max_sequence_length = cfg.sequence_len
-                LOG.warning(f"increasing context length to {cfg.sequence_len}")
             model = AutoModelForCausalLM.from_pretrained(
                 base_model,
                 config=config,
                 load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
                 load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
                 torch_dtype=torch_dtype,
+                device_map=cfg.device_map,
                 trust_remote_code=cfg.trust_remote_code or False,
                 **model_kwargs,
             )
     except Exception as err:  # pylint: disable=broad-exception-caught
-        LOG.error(
+        logging.error(
             "Exception raised attempting to load model, retrying with AutoModelForCausalLM"
         )
-        LOG.exception(err)
+        logging.exception(err)
         model = AutoModelForCausalLM.from_pretrained(
             base_model,
             load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
-            load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
             torch_dtype=torch_dtype,
+            device_map=cfg.device_map,
             trust_remote_code=cfg.trust_remote_code or False,
             **model_kwargs,
         )
 
-    embeddings_len = (
-        math.ceil(len(tokenizer) / 32) * 32
-        if cfg.resize_token_embeddings_to_32x
-        else len(tokenizer)
-    )
+    embeddings_len = math.ceil(len(tokenizer) / 32) * 32
     model.resize_token_embeddings(embeddings_len)
 
-    if (
-        hasattr(model.config, "max_position_embeddings")
-        and model.config.max_position_embeddings
-        and cfg.sequence_len >= model.config.max_position_embeddings
-    ):
-        LOG.warning(
+    if cfg.sequence_len >= model.config.max_position_embeddings:
+        logging.warning(
             f"increasing model.config.max_position_embeddings to {cfg.sequence_len}"
         )
         model.config.max_position_embeddings = cfg.sequence_len
@@ -340,20 +272,8 @@ def load_model(
         (cfg.adapter == "lora" and load_in_8bit)
         or (cfg.adapter == "qlora" and cfg.load_in_4bit)
     ):
-        LOG.info("converting PEFT model w/ prepare_model_for_kbit_training")
-        model = prepare_model_for_kbit_training(
-            model, use_gradient_checkpointing=cfg.gradient_checkpointing
-        )
-
-        # LlamaRMSNorm layers are in fp32 after kbit_training, so we need to
-        # convert them back to fp16/bf16 for flash-attn compatibility.
-        if cfg.flash_attention and cfg.is_llama_derived_model:
-            for name, module in model.named_modules():
-                if "norm" in name:
-                    module.to(torch_dtype)
-                if "lm_head" in name or "embed_tokens" in name:
-                    if hasattr(module, "weight"):
-                        module.to(torch_dtype)
+        logging.info("converting PEFT model w/ prepare_model_for_int8_training")
+        model = prepare_model_for_int8_training(model)
 
     model, lora_config = load_adapter(model, cfg, adapter)
 
@@ -362,7 +282,7 @@ def load_model(
 
     if cfg.gptq:
         # Scales to half
-        LOG.info("Fitting 4bit scales and zeros to half")
+        logging.info("Fitting 4bit scales and zeros to half")
         for _, module in model.named_modules():
             if "Autograd4bitQuantLinear" in str(type(module)) or "Linear4bitLt" in str(
                 type(module)
@@ -388,7 +308,7 @@ def load_model(
         if param.requires_grad:
             requires_grad.append(f"{name}: {param.requires_grad}")
     if len(requires_grad) == 0:
-        LOG.warning("there are no parameters that require gradient updates")
+        logging.warning("there are no parameters that require gradient updates")
     model.config.use_cache = False
 
     if cfg.flash_optimum:
@@ -403,8 +323,6 @@ def load_adapter(model, cfg, adapter):
 
     if adapter is None:
         return model, None
-    if hasattr(model, "enable_input_require_grads"):
-        model.enable_input_require_grads()
     if adapter in ["lora", "qlora"]:
         return load_lora(model, cfg)
     if adapter == "llama-adapter":
@@ -424,10 +342,11 @@ def load_llama_adapter(model, cfg):
     )
 
     if cfg.lora_model_dir:
-        LOG.info("Loading pretained LORA")
+        logging.info("Loading pretained LORA")
         model = PeftModel.from_pretrained(
             model,
             cfg.lora_model_dir,
+            device_map=cfg.device_map,
             torch_dtype=torch.float16,
         )
     else:
@@ -471,7 +390,7 @@ def load_lora(model, cfg):
             bits = 8
 
         linear_names = find_all_linear_names(bits, model)
-        LOG.info(f"found linear modules: {repr(linear_names)}")
+        logging.info(f"found linear modules: {repr(linear_names)}")
         lora_target_modules = list(set(lora_target_modules + linear_names))
 
     lora_config = LoraConfig(
@@ -489,7 +408,8 @@ def load_lora(model, cfg):
         model = PeftModel.from_pretrained(
             model,
             cfg.lora_model_dir,
-            is_trainable=not cfg.inference,
+            device_map=cfg.device_map,
+            # torch_dtype=torch.float16,
         )
     else:
         model = get_peft_model(model, lora_config)

src/axolotl/utils/schedulers.py

@@ -1,9 +1,6 @@
 """Module for custom LRScheduler class"""
-import math
-from functools import partial
 
-from torch.optim import Optimizer
-from torch.optim.lr_scheduler import LambdaLR, LRScheduler
+from torch.optim.lr_scheduler import LRScheduler
 
 
 class InterpolatingLogScheduler(LRScheduler):
@@ -45,58 +42,3 @@ class InterpolatingLogScheduler(LRScheduler):
             lrs = [self.max_lr for base_lr in self.base_lrs]
 
         return lrs
-
-
-def _get_cosine_schedule_with_quadratic_warmup_lr_lambda(
-    current_step: int,
-    *,
-    num_warmup_steps: int,
-    num_training_steps: int,
-    num_cycles: float
-):
-    if current_step < num_warmup_steps:
-        return (float(current_step) / float(max(1, num_warmup_steps))) ** 2
-    progress = float(current_step - num_warmup_steps) / float(
-        max(1, num_training_steps - num_warmup_steps)
-    )
-    return max(
-        0.0, 0.5 * (1.0 + math.cos(math.pi * float(num_cycles) * 2.0 * progress))
-    )
-
-
-def get_cosine_schedule_with_quadratic_warmup(
-    optimizer: Optimizer,
-    num_warmup_steps: int,
-    num_training_steps: int,
-    num_cycles: float = 0.5,
-    last_epoch: int = -1,
-):
-    """
-    Create a schedule with a learning rate that decreases following the values of the cosine function between the
-    initial lr set in the optimizer to 0, after a warmup period during which it increases linearly between 0 and the
-    initial lr set in the optimizer.
-
-    Args:
-        optimizer ([`~torch.optim.Optimizer`]):
-            The optimizer for which to schedule the learning rate.
-        num_warmup_steps (`int`):
-            The number of steps for the warmup phase.
-        num_training_steps (`int`):
-            The total number of training steps.
-        num_cycles (`float`, *optional*, defaults to 0.5):
-            The number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0
-            following a half-cosine).
-        last_epoch (`int`, *optional*, defaults to -1):
-            The index of the last epoch when resuming training.
-
-    Return:
-        `torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
-    """
-
-    lr_lambda = partial(
-        _get_cosine_schedule_with_quadratic_warmup_lr_lambda,
-        num_warmup_steps=num_warmup_steps,
-        num_training_steps=num_training_steps,
-        num_cycles=num_cycles,
-    )
-    return LambdaLR(optimizer, lr_lambda, last_epoch)

src/axolotl/utils/tokenization.py

@@ -5,8 +5,6 @@ import logging
 
 from termcolor import colored
 
-LOG = logging.getLogger("axolotl")
-
 
 def check_dataset_labels(dataset, tokenizer):
     # the dataset is already shuffled, so let's just check the first 5 elements
@@ -34,7 +32,5 @@ def check_example_labels(example, tokenizer):
         )
         colored_tokens.append(colored_token)
 
-    LOG.info(" ".join(colored_tokens))
-    LOG.info("\n\n\n")
-
-    return " ".join(colored_tokens)
+    logging.info(" ".join(colored_tokens))
+    logging.info("\n\n\n")

src/axolotl/utils/trainer.py

@@ -1,230 +1,29 @@
 """Module containing the Trainer class and related functions"""
+
 import importlib
 import logging
 import math
 import os
 import sys
-from contextlib import contextmanager
-from dataclasses import dataclass, field
-from functools import partial
 from pathlib import Path
-from typing import Optional, Union
+from typing import Optional
 
 import bitsandbytes as bnb
 import torch.cuda
 import transformers
-from datasets import Dataset, set_caching_enabled
 from torch import nn
 from torch.optim.lr_scheduler import OneCycleLR
-from torch.utils.data import DataLoader, DistributedSampler, RandomSampler
-from transformers import EarlyStoppingCallback, Trainer, TrainingArguments
+from transformers import EarlyStoppingCallback, Trainer
 from transformers.trainer_pt_utils import get_parameter_names
 
 from axolotl.utils.callbacks import (
     SaveBetterTransformerModelCallback,
     SavePeftModelCallback,
 )
-from axolotl.utils.collators import DataCollatorForSeq2Seq
-from axolotl.utils.dataloader import MultipackDistributedDataloader
-from axolotl.utils.schedulers import (
-    InterpolatingLogScheduler,
-    get_cosine_schedule_with_quadratic_warmup,
-)
-
-LOG = logging.getLogger("axolotl")
+from axolotl.utils.schedulers import InterpolatingLogScheduler
 
 
-@torch.jit.script
-def weighted_cross_entropy(
-    logits: torch.Tensor, labels: torch.Tensor, weights: torch.Tensor
-):
-    # Flatten the logits, labels, and weights tensors
-    logits = logits.view(
-        -1, logits.size(-1)
-    )  # logits becomes of shape [batch_size*sequence_length, vocab_size]
-    labels = labels.view(-1)  # labels becomes of shape [batch_size*sequence_length]
-    weights = weights.view(-1)  # weights becomes of shape [batch_size*sequence_length]
-
-    # Compute the unweighted cross entropy loss
-    losses = torch.nn.functional.cross_entropy(logits, labels, reduction="none")
-
-    # Apply the weights to the losses and compute their sum
-    return (weights * losses).sum()
-
-
-@torch.jit.script
-def create_weighted_mask(labels: torch.Tensor):
-    # Check if the tensor is 2D. If not, unsqueeze it to make it 2D
-    if len(labels.shape) == 1:
-        labels = labels.unsqueeze(0)
-
-    weights = torch.zeros_like(labels).float()
-    for i in range(labels.shape[0]):
-        mask = labels[i] != -100
-
-        # Create a tensor to track group ids
-        group_ids = torch.zeros_like(labels[i]).int()
-        curr_group_id = 0
-
-        for j in range(1, len(labels[i])):
-            if mask[j] and not mask[j - 1]:  # switch from masked to unmasked label
-                curr_group_id += 1  # start new group
-            group_ids[j] = (
-                curr_group_id if mask[j] else 0
-            )  # assign group id if unmasked label
-
-        # Count only unmasked labels in each group
-        group_counts = torch.bincount(group_ids[mask])
-
-        mask_weights = torch.zeros_like(labels[i]).float()
-        mask_weights[mask] = 1.0 / group_counts[group_ids[mask]]
-
-        weights[i] = mask_weights
-
-    return weights.squeeze()  # squeeze the output to match the input dimension
-
-
-def trainer_weighted_loss(model_output, labels, shift_labels=True):
-    logits = (
-        model_output["logits"] if isinstance(model_output, dict) else model_output[0]
-    )
-    if shift_labels:
-        logits = logits[..., :-1, :].contiguous()
-        labels = labels[..., 1:].contiguous()
-
-    weights = create_weighted_mask(labels)
-    return weighted_cross_entropy(logits, labels, weights)
-
-
-@dataclass
-class AxolotlTrainingArguments(TrainingArguments):
-    """
-    Extend the base TrainingArguments for axolotl helpers
-    """
-
-    lr_quadratic_warmup: bool = field(
-        default=False,
-        metadata={"help": "Use quadratic warmup for cosine scheduling."},
-    )
-    sample_packing: bool = field(
-        default=False,
-        metadata={"help": "Use sample packing for efficient training."},
-    )
-    sample_packing_efficiency: float = field(
-        default=1.0,
-        metadata={"help": "Sample packing efficiency for calculating batch length."},
-    )
-    max_seq_length: int = field(
-        default=2048,
-        metadata={"help": "The maximum sequence length the model can handle"},
-    )
-    sample_packing_seq_len_multiplier: int = field(
-        default=1,
-        metadata={"help": "the multiplier for the max len for packed sequences"},
-    )
-    train_data_total_num_tokens: Optional[int] = field(
-        default=None,
-        metadata={"help": "the total number of tokens in the train dataset"},
-    )
-
-
-class AxolotlTrainer(Trainer):
-    """
-    Extend the base Trainer for axolotl helpers
-    """
-
-    args = None  # type: AxolotlTrainingArguments
-
-    def create_scheduler(
-        self, num_training_steps: int, optimizer: torch.optim.Optimizer = None
-    ):
-        """
-        Setup the scheduler. The optimizer of the trainer must have been set up either before this method is called or
-        passed as an argument.
-
-        Args:
-            num_training_steps (int): The number of training steps to do.
-            optimizer (torch.optim.Optimizer): The training optimizer
-        """
-
-        # fmt: off
-        if self.lr_scheduler is None:  # type: ignore  # pylint: disable=access-member-before-definition
-            # fmt: on
-            if (
-                self.args.lr_scheduler_type == "cosine"
-                and self.args.lr_quadratic_warmup is True
-            ):
-                self.lr_scheduler = get_cosine_schedule_with_quadratic_warmup(  # pylint: disable=attribute-defined-outside-init
-                    optimizer,
-                    num_warmup_steps=self.args.get_warmup_steps(num_training_steps),
-                    num_training_steps=num_training_steps,
-                )
-            else:
-                return super().create_scheduler(num_training_steps, optimizer)
-        return self.lr_scheduler
-
-    def _get_train_sampler(self) -> Optional[torch.utils.data.Sampler]:
-        if self.args.world_size > 1 and self.args.sample_packing:
-            return DistributedSampler(
-                self.train_dataset,
-                num_replicas=self.args.world_size,
-                rank=self.args.process_index,
-                seed=self.args.seed,
-            )
-        return super()._get_train_sampler()
-
-    def get_train_dataloader(self) -> Union[DataLoader, MultipackDistributedDataloader]:
-        if self.args.sample_packing:
-            train_sampler = self._get_train_sampler()
-            return self.accelerator.prepare(
-                MultipackDistributedDataloader(
-                    self.train_dataset,
-                    batch_size=self._train_batch_size,
-                    seq_max_length=self.args.max_seq_length,
-                    collate_fn=self.data_collator,
-                    sampler=train_sampler,
-                    packing_efficiency_estimate=self.args.sample_packing_efficiency,
-                    sample_packing_seq_len_multiplier=self.args.sample_packing_seq_len_multiplier,
-                    device_count=int(os.environ.get("WORLD_SIZE", 1)),
-                    total_num_tokens=self.args.train_data_total_num_tokens,
-                )
-            )
-        return super().get_train_dataloader()
-
-    def get_eval_dataloader(
-        self, eval_dataset: Optional[Dataset] = None
-    ) -> Union[DataLoader, MultipackDistributedDataloader]:
-        if self.args.sample_packing:
-            eval_dataset = (
-                eval_dataset if eval_dataset is not None else self.eval_dataset
-            )
-            eval_sampler = self._get_eval_sampler(eval_dataset)
-            return self.accelerator.prepare(
-                MultipackDistributedDataloader(
-                    eval_dataset,
-                    batch_size=self.args.eval_batch_size,
-                    seq_max_length=self.args.max_seq_length,
-                    collate_fn=self.data_collator,
-                    sampler=eval_sampler,
-                    packing_efficiency_estimate=self.args.sample_packing_efficiency,
-                    sample_packing_seq_len_multiplier=self.args.eval_batch_size,
-                    device_count=int(os.environ.get("WORLD_SIZE", 1)),
-                    total_num_tokens=None,
-                )
-            )
-        return super().get_eval_dataloader(eval_dataset)
-
-    def compute_loss(self, model, inputs, return_outputs=False):
-        # use one's weighted cross entropy loss calc
-        # if self.args.sample_packing:
-        #     labels = inputs.pop("labels")
-        #     outputs = model(**inputs)
-        #     loss = trainer_weighted_loss(outputs, labels, shift_labels=True)
-        #     return (loss, outputs) if return_outputs else loss
-        return super().compute_loss(model, inputs, return_outputs=return_outputs)
-
-
-class OneCycleLRSchedulerTrainer(AxolotlTrainer):
+class OneCycleLRSchedulerTrainer(Trainer):
     """
     Trainer subclass that uses the OneCycleLR scheduler
     """
@@ -253,117 +52,10 @@ class OneCycleLRSchedulerTrainer(AxolotlTrainer):
         return self.lr_scheduler
 
 
-def add_position_ids(sample):
-    sample["position_ids"] = torch.arange(len(sample["input_ids"]))
-    return sample
-
-
-def drop_long_seq(sample, sequence_len=2048):
-    return len(sample["input_ids"]) <= sequence_len
-
-
-@contextmanager
-def disable_datasets_caching():
-    try:
-        set_caching_enabled(False)
-        yield
-    finally:
-        set_caching_enabled(True)
-
-
-def process_datasets_for_packing(cfg, train_dataset, eval_dataset):
-    if cfg.sample_packing:
-        drop_long = partial(drop_long_seq, sequence_len=cfg.sequence_len)
-        train_dataset = train_dataset.filter(drop_long, num_proc=os.cpu_count()).map(
-            add_position_ids, num_proc=os.cpu_count()
-        )
-        if eval_dataset:
-            eval_dataset = eval_dataset.filter(drop_long, num_proc=os.cpu_count()).map(
-                add_position_ids, num_proc=os.cpu_count()
-            )
-    return train_dataset, eval_dataset
-
-
-def calculate_total_num_steps(cfg, train_dataset, tokenizer):
-    if cfg.sample_packing:
-        # we have to drop anything longer then sequence len otherwise
-        # flash attention with position ids fails
-        total_num_tokens = (
-            cfg.total_num_tokens
-            if cfg.total_num_tokens
-            else sum(len(s["input_ids"]) for s in train_dataset)
-        )
-        if not cfg.total_num_tokens:
-            LOG.info(f"📝 UPDATE CONFIG WITH: `total_num_tokens: {total_num_tokens}`")
-
-        if cfg.sample_packing_eff_est:
-            total_num_steps = (
-                # match count to len est in dataloader
-                (
-                    math.floor(
-                        0.99
-                        * total_num_tokens
-                        / cfg.sample_packing_eff_est
-                        / 2048
-                        // cfg.batch_size
-                        // int(os.environ.get("WORLD_SIZE", 1))
-                    )
-                    - 1
-                )
-                * cfg.num_epochs
-            )
-            LOG.info(
-                f"total_num_tokens: {total_num_tokens}, total_num_steps: {total_num_steps}"
-            )
-        else:
-            sampler = RandomSampler(train_dataset)
-            data_loader = MultipackDistributedDataloader(
-                train_dataset,
-                batch_size=cfg.micro_batch_size,
-                seq_max_length=cfg.max_packed_sequence_len or cfg.sequence_len,
-                collate_fn=DataCollatorForSeq2Seq(
-                    tokenizer,
-                    return_tensors="pt",
-                    padding="longest",
-                ),
-                sampler=sampler,
-                packing_efficiency_estimate=cfg.sample_packing_eff_est,
-                sample_packing_seq_len_multiplier=cfg.micro_batch_size,
-                device_count=int(os.environ.get("WORLD_SIZE", 1)),
-            )
-            data_loader_len = data_loader.len_w_stats()
-            actual_eff = data_loader.efficiency()
-            LOG.info(f"data_loader_len: {data_loader_len}")
-            total_num_steps = int(
-                math.floor(
-                    data_loader_len
-                    * cfg.micro_batch_size
-                    * cfg.num_epochs
-                    // cfg.batch_size
-                )
-            )
-            LOG.info(
-                f"📝 UPDATE CONFIG WITH: `sample_packing_eff_est: {math.ceil(actual_eff * 100.0) / 100.0}`"
-            )
-    else:
-        total_num_steps = int(
-            math.ceil(len(train_dataset) * cfg.num_epochs / cfg.batch_size)
-        )
-    LOG.info(f"total_num_steps: {total_num_steps}")
-    return total_num_steps
-
-
-def setup_fsdp_envs(cfg):
-    os.environ["ACCELERATE_USE_FSDP"] = "true"
-    if cfg.fsdp_config.fsdp_sync_module_states:
-        os.environ["FSDP_SYNC_MODULE_STATES"] = "true"
-    if cfg.fsdp_config.fsdp_state_dict_type:
-        os.environ["FSDP_STATE_DICT_TYPE"] = cfg.fsdp_config.fsdp_state_dict_type
-
-
-def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_steps):
-    if cfg.fsdp:
-        setup_fsdp_envs(cfg)
+def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
+    total_num_steps = int(
+        math.ceil(len(train_dataset) * cfg.num_epochs / cfg.batch_size)
+    )
     warmup_steps = (
         cfg.warmup_steps
         if cfg.warmup_steps is not None
@@ -374,6 +66,8 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
         if cfg.logging_steps is not None
         else max(min(int(0.005 * total_num_steps), 10), 1)
     )
+    save_steps = cfg.save_steps
+    eval_steps = cfg.eval_steps
 
     training_arguments_kwargs = {}
     if cfg.bf16 == "full":
@@ -384,10 +78,6 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
     training_arguments_kwargs["tf32"] = cfg.tf32
     training_arguments_kwargs["warmup_steps"] = warmup_steps
     training_arguments_kwargs["logging_steps"] = logging_steps
-
-    if cfg.seed:
-        training_arguments_kwargs["seed"] = cfg.seed
-
     if cfg.gradient_checkpointing:
         if cfg.gptq:
             from alpaca_lora_4bit.gradient_checkpointing import (
@@ -411,9 +101,6 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
         if cfg.fsdp_config:
             training_arguments_kwargs["fsdp_config"] = dict(cfg.fsdp_config)
 
-    if cfg.lr_quadratic_warmup is not None:
-        training_arguments_kwargs["lr_quadratic_warmup"] = cfg.lr_quadratic_warmup
-
     # deepspeed
     if (
         os.environ.get("ACCELERATE_USE_DEEPSPEED") == "true"
@@ -426,31 +113,7 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
             # TODO search Path("./") for one
             training_arguments_kwargs["deepspeed"] = "./ds_config.json"
 
-    if cfg.adam_beta1:
-        training_arguments_kwargs["adam_beta1"] = cfg.adam_beta1
-    if cfg.adam_beta2:
-        training_arguments_kwargs["adam_beta2"] = cfg.adam_beta2
-    if cfg.adam_epsilon:
-        training_arguments_kwargs["adam_epsilon"] = cfg.adam_epsilon
-    if cfg.max_grad_norm:
-        training_arguments_kwargs["max_grad_norm"] = cfg.max_grad_norm
-
-    if cfg.hub_model_id:
-        training_arguments_kwargs["hub_model_id"] = cfg.hub_model_id
-        training_arguments_kwargs["push_to_hub"] = True
-        training_arguments_kwargs["hub_private_repo"] = True
-
-    if cfg.save_safetensors:
-        training_arguments_kwargs["save_safetensors"] = cfg.save_safetensors
-
-    if cfg.sample_packing_eff_est:
-        training_arguments_kwargs[
-            "sample_packing_efficiency"
-        ] = cfg.sample_packing_eff_est
-
-    training_args = AxolotlTrainingArguments(  # pylint: disable=unexpected-keyword-arg
-        # max_steps=total_num_steps,  # this is helpful in case we don't actually know total # of steps
-        max_seq_length=cfg.sequence_len,
+    training_args = transformers.TrainingArguments(
         per_device_train_batch_size=cfg.micro_batch_size,
         per_device_eval_batch_size=cfg.eval_batch_size
         if cfg.eval_batch_size is not None
@@ -460,16 +123,16 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
         num_train_epochs=cfg.num_epochs,
         learning_rate=cfg.learning_rate,
         evaluation_strategy="steps" if cfg.val_set_size > 0 else "no",
-        save_strategy="steps" if cfg.save_steps else "epoch",
-        eval_steps=cfg.eval_steps if cfg.val_set_size > 0 else None,
-        save_steps=cfg.save_steps,
+        save_strategy="steps" if save_steps else "epoch",
+        eval_steps=eval_steps if cfg.val_set_size > 0 else None,
+        save_steps=save_steps,
         output_dir=cfg.output_dir,
-        save_total_limit=cfg.save_total_limit if cfg.save_total_limit else 4,
+        save_total_limit=3,
         load_best_model_at_end=(
             cfg.load_best_model_at_end is not False
             and cfg.val_set_size > 0
-            and cfg.save_steps
-            and cfg.save_steps % cfg.eval_steps == 0
+            and save_steps
+            and save_steps % eval_steps == 0
             and cfg.load_in_8bit is not True
         )
         or False,
@@ -482,9 +145,6 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
         if cfg.lr_scheduler and cfg.lr_scheduler not in ("one_cycle", "log_sweep")
         else "cosine",
         weight_decay=cfg.weight_decay if cfg.weight_decay is not None else 0.0,
-        sample_packing=cfg.sample_packing if cfg.sample_packing else False,
-        sample_packing_seq_len_multiplier=cfg.micro_batch_size or 1,
-        train_data_total_num_tokens=cfg.total_num_tokens,
         **training_arguments_kwargs,
     )
 
@@ -570,6 +230,7 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
         callbacks.append(SavePeftModelCallback)
 
     if hasattr(model, "use_bettertransformer") and model.use_bettertransformer is True:
+        logging.info("Setting up SaveBetterTransformerModelCallback.")
         callbacks.append(SaveBetterTransformerModelCallback)
 
     data_collator_kwargs = {
@@ -578,39 +239,19 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
     if cfg.collator_pad_to_longest:
         data_collator_kwargs["padding"] = "longest"
     else:
-        # A100 is best at 64, while others at 8. Let's use the larger so we don't have to check
-        # https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html
-        data_collator_kwargs["pad_to_multiple_of"] = 64
-
-    if cfg.is_llama_derived_model and cfg.landmark_attention:
-        from axolotl.monkeypatch.llama_landmark_attn import (
-            add_mem_tokens,
-            get_mem_id,
-            set_model_mem_id,
-        )
-
-        set_model_mem_id(model, tokenizer)
-
-        LOG.info("Adding landmark attention tokens to dataset")
-
-        for dataset in [train_dataset, eval_dataset]:
-            dataset = dataset.map(
-                partial(add_mem_tokens, mem_freq=50, mem_id=get_mem_id(tokenizer)),
-                batched=False,
-                num_proc=32,
-            )
+        data_collator_kwargs["pad_to_multiple_of"] = 8
 
     trainer_cls = (
         OneCycleLRSchedulerTrainer
         if cfg.lr_scheduler == "one_cycle" and (cfg.fsdp or cfg.adapter == "qlora")
-        else AxolotlTrainer
+        else transformers.Trainer
     )
     trainer = trainer_cls(
         model=model,
         train_dataset=train_dataset,
         eval_dataset=eval_dataset,
         args=training_args,
-        data_collator=DataCollatorForSeq2Seq(
+        data_collator=transformers.DataCollatorForSeq2Seq(
             tokenizer,
             return_tensors="pt",
             **data_collator_kwargs,

src/axolotl/utils/validation.py

@@ -4,33 +4,12 @@ import logging
 
 import torch
 
-LOG = logging.getLogger("axolotl")
-
 
 def validate_config(cfg):
-    if cfg.max_packed_sequence_len and cfg.sample_packing:
-        raise ValueError(
-            "please set only one of max_packed_sequence_len (deprecated soon) or sample_packing"
-        )
-    if cfg.max_packed_sequence_len:
-        LOG.warning(
-            str(
-                PendingDeprecationWarning(
-                    "max_packed_sequence_len will be deprecated in favor of sample_packing"
-                )
-            )
-        )
-
     if cfg.gradient_accumulation_steps and cfg.batch_size:
         raise ValueError(
             "please set only one of gradient_accumulation_steps or batch_size"
         )
-    if cfg.batch_size:
-        LOG.warning(
-            "%s\n%s",
-            "batch_size is not recommended. Please use gradient_accumulation_steps instead.",
-            "To calculate the equivalent gradient_accumulation_steps, divide batch_size / micro_batch_size / number of gpus.",
-        )
     if cfg.load_4bit:
         raise ValueError(
             "cfg.load_4bit parameter has been deprecated and replaced by cfg.gptq"
@@ -59,10 +38,10 @@ def validate_config(cfg):
                 raise ValueError("Require cfg.load_in_4bit to be True for qlora")
 
     if not cfg.load_in_8bit and cfg.adapter == "lora":
-        LOG.warning("We recommend setting `load_in_8bit: true` for LORA finetuning")
+        logging.warning("We recommend setting `load_in_8bit: true` for LORA finetuning")
 
     if cfg.trust_remote_code:
-        LOG.warning(
+        logging.warning(
             "`trust_remote_code` is set to true. Please make sure that you reviewed the remote code/model."
         )
 
@@ -71,56 +50,23 @@ def validate_config(cfg):
             "Require cfg.hf_use_auth_token to be True for push_dataset_to_hub"
         )
 
-    if (cfg.base_model and "falcon" in cfg.base_model.lower()) and cfg.fsdp:
-        raise ValueError("FSDP is not supported for falcon models")
-
-    if (
-        cfg.base_model and "mpt" in cfg.base_model.lower()
-    ) and cfg.gradient_checkpointing:
-        raise ValueError("gradient_checkpointing is not supported for MPT models")
-
     if cfg.flash_optimum is True:
         if cfg.adapter:
-            LOG.warning("BetterTransformers probably doesn't work with PEFT adapters")
+            logging.warning(
+                "BetterTransformers probably doesn't work with PEFT adapters"
+            )
         if cfg.fp16 or cfg.bf16:
             raise ValueError("AMP is not supported with BetterTransformer")
         if cfg.float16 is not True and cfg.bloat16 is not True:
-            LOG.warning(
+            logging.warning(
                 "You should probably set bfloat16 or float16 to true to "
                 "load the model in float16 for BetterTransformers"
             )
         if int(torch.__version__.split(".")[0]) < 2:
-            LOG.warning("torch>=2.0.0 required")
+            logging.warning("torch>=2.0.0 required")
             raise ValueError(
                 f"flash_optimum for BetterTransformers may not be used with {torch.__version__}"
             )
-
-    if cfg.pretraining_dataset and cfg.group_by_length:
-        LOG.warning(
-            "You probably want to disable group_by_length as it will force a streamed dataset to download completely."
-        )
-
-    if any([cfg.adam_beta1, cfg.adam_beta2, cfg.adam_epsilon]) and (
-        not cfg.optimizer or "adamw" not in cfg.optimizer
-    ):
-        LOG.warning("adamw hyperparameters found, but no adamw optimizer set")
-
-    if cfg.push_to_hub_model_id:
-        raise ValueError(
-            "push_to_hub_model_id is deprecated. Please use hub_model_id instead."
-        )
-
-    if cfg.sample_packing and cfg.sdp_attention:
-        # incompatible due to bug w/ accelerate causing 0.0 loss when using llama2
-        raise ValueError(
-            "sample_packing not compatible with sdp_attention. Use flash_attention"
-        )
-
-    if cfg.sample_packing and cfg.xformers_attention:
-        raise ValueError(
-            "sample_packing not compatible with xformers_attention. Use flash_attention"
-        )
-
     # TODO
     # MPT 7b
     # https://github.com/facebookresearch/bitsandbytes/issues/25

src/axolotl/utils/wandb.py

@@ -15,5 +15,3 @@ def setup_wandb_env_vars(cfg):
             os.environ["WANDB_LOG_MODEL"] = cfg.wandb_log_model
         if cfg.wandb_run_id and len(cfg.wandb_run_id) > 0:
             os.environ["WANDB_RUN_ID"] = cfg.wandb_run_id
-    else:
-        os.environ["WANDB_DISABLED"] = "true"

tests/monkeypatch/test_llama_attn_hijack_flash.py

@@ -1,30 +0,0 @@
-"""
-Unit tests for the monkeypatch utils
-"""
-import unittest
-
-import torch
-
-from axolotl.monkeypatch.utils import get_cu_seqlens, get_cu_seqlens_from_pos_ids
-
-
-class TestMonkeyPatchUtils(unittest.TestCase):
-    """
-    Unit test class for monkeypatch utils
-    """
-
-    def test_get_cu_seqlens_1d(self):
-        attn_mask = torch.tensor([[1, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3, 3, 4, 4, 0, 0]])
-        target_res = torch.tensor([0, 4, 7, 12, 14, 16], dtype=torch.int32)
-        self.assertTrue(torch.allclose(get_cu_seqlens(attn_mask)[0], target_res))
-
-    def test_get_cu_seqlens_from_pos_ids_1d(self):
-        position_ids = torch.tensor([[0, 1, 2, 3, 0, 1, 2, 0, 1, 2, 3, 4, 0, 1, 0, 0]])
-        target_res = torch.tensor([0, 4, 7, 12, 14, 16], dtype=torch.int32)
-        self.assertTrue(
-            torch.allclose(get_cu_seqlens_from_pos_ids(position_ids)[0], target_res)
-        )
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/test_expand_mask.py

@@ -1,44 +0,0 @@
-"""
-Unit tests for the monkey patch for expand mask to handle packed sequences
-"""
-import unittest
-
-import torch
-
-from axolotl.monkeypatch.llama_expand_mask import _expand_mask
-
-
-class TestExpandMask(unittest.TestCase):
-    """
-    Test class for attention mask expansion for packed sequences
-    """
-
-    def test_output(self):
-        mask = torch.tensor([[1, 1, 1, 2], [2, 3, 3, 0]])
-        dtype = torch.float32
-        expected_output = torch.tensor(
-            [
-                [
-                    [
-                        [0.0000e00, -3.4028e38, -3.4028e38, -3.4028e38],
-                        [0.0000e00, 0.0000e00, -3.4028e38, -3.4028e38],
-                        [0.0000e00, 0.0000e00, 0.0000e00, -3.4028e38],
-                        [-3.4028e38, -3.4028e38, -3.4028e38, 0.0000e00],
-                    ]
-                ],
-                [
-                    [
-                        [0.0000e00, -3.4028e38, -3.4028e38, -3.4028e38],
-                        [-3.4028e38, 0.0000e00, -3.4028e38, -3.4028e38],
-                        [-3.4028e38, 0.0000e00, 0.0000e00, -3.4028e38],
-                        [-3.4028e38, -3.4028e38, -3.4028e38, -3.4028e38],
-                    ]
-                ],
-            ]
-        )
-        # Check that the output matches the expected output
-        self.assertTrue(torch.allclose(_expand_mask(mask, dtype), expected_output))
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/test_packed_dataset.py

@@ -27,7 +27,7 @@ class TestPacking(unittest.TestCase):
             }
         )
 
-    def test_increments_attention(self):
+    def test_resets_attention(self):
         prompter = AlpacaPrompter("chat")
         strat = AlpacaPromptTokenizingStrategy(
             prompter,
@@ -55,14 +55,10 @@ class TestPacking(unittest.TestCase):
         # first example doesn't have mask reset
         assert example["input_ids"][0] == self.tokenizer.bos_token_id
         assert example["attention_mask"][0] == 1
-        assert example["position_ids"][0] == 0
-        assert example["position_ids"][1] == 1
 
         # but subsequent one does
         assert example["input_ids"][next_bos_index] == self.tokenizer.bos_token_id
-        assert example["attention_mask"][next_bos_index] == 2
-        assert example["position_ids"][next_bos_index] == 0
-        assert example["position_ids"][next_bos_index + 1] == 1
+        assert example["attention_mask"][next_bos_index] == 0
 
 
 if __name__ == "__main__":

tests/test_prompt_tokenizers.py

@@ -4,24 +4,12 @@ import logging
 import unittest
 from pathlib import Path
 
-from transformers import AutoTokenizer, LlamaTokenizer
+from transformers import AutoTokenizer
 
-from axolotl.prompt_strategies.alpaca_chat import NoSystemPrompter
-from axolotl.prompt_strategies.alpaca_w_system import (
-    InstructionWSystemPromptTokenizingStrategy,
-    SystemDataPrompter,
-)
-from axolotl.prompt_strategies.llama2_chat import (
-    Llama2ChatPrompter,
-    LLama2ChatTokenizingStrategy,
-)
-from axolotl.prompt_tokenizers import (
-    AlpacaPromptTokenizingStrategy,
-    ShareGPTPromptTokenizingStrategy,
-)
-from axolotl.prompters import AlpacaPrompter, PromptStyle, ShareGPTPrompter
+from axolotl.prompt_tokenizers import ShareGPTPromptTokenizingStrategy
+from axolotl.prompters import ShareGPTPrompter
 
-LOG = logging.getLogger("axolotl")
+logging.basicConfig(level="INFO")
 
 
 class TestPromptTokenizationStrategies(unittest.TestCase):
@@ -41,6 +29,7 @@ class TestPromptTokenizationStrategies(unittest.TestCase):
         )
 
     def test_sharegpt_integration(self):
+        print(Path(__file__).parent)
         with open(
             Path(__file__).parent / "fixtures/conversation.json", encoding="utf-8"
         ) as fin:
@@ -64,166 +53,6 @@ class TestPromptTokenizationStrategies(unittest.TestCase):
             self.assertEqual(len(example[fields]), len(tokenized_conversation[fields]))
             self.assertEqual(example[fields], tokenized_conversation[fields])
 
-    def test_no_sys_prompt(self):
-        """
-        tests the interface between the user and assistant parts
-        """
-        prompter = NoSystemPrompter()
-        # pylint: disable=duplicate-code
-        strat = AlpacaPromptTokenizingStrategy(
-            prompter,
-            self.tokenizer,
-            False,
-            2048,
-        )
-        sample = {
-            "instruction": "hello cruel. lorem ipsum dolor sit amet.",
-            "output": "world!",
-        }
-        example = strat.tokenize_prompt(sample)
-        world_idx = example["input_ids"].index(3186)
-        assert example["labels"][world_idx] == 3186
-        assert example["labels"][world_idx - 1] == -100
-
-    def test_alpaca(self):
-        """
-        tests the interface between the user and assistant parts
-        """
-        # pylint: disable=duplicate-code
-        prompter = AlpacaPrompter()
-        strat = AlpacaPromptTokenizingStrategy(
-            prompter,
-            self.tokenizer,
-            False,
-            2048,
-        )
-        sample = {"instruction": "hello!", "output": "Hi! How can I help?"}
-        example = strat.tokenize_prompt(sample)
-        world_idx = example["input_ids"].index(6324)
-        assert example["labels"][world_idx] == 6324
-        assert example["labels"][world_idx - 1] == -100
-
-
-class InstructionWSystemPromptTokenizingStrategyTest(unittest.TestCase):
-    """
-    Test class for prompt tokenization strategies with sys prompt from the dataset
-    """
-
-    def setUp(self) -> None:
-        # pylint: disable=duplicate-code
-        self.tokenizer = AutoTokenizer.from_pretrained("huggyllama/llama-7b")
-        self.tokenizer.add_special_tokens(
-            {
-                "bos_token": "<s>",
-                "eos_token": "</s>",
-                "unk_token": "<unk>",
-            }
-        )
-
-    def test_system_alpaca(self):
-        prompter = SystemDataPrompter(PromptStyle.CHAT.value)
-        strat = InstructionWSystemPromptTokenizingStrategy(
-            prompter,
-            self.tokenizer,
-            False,
-            2048,
-        )
-        sample = {
-            "system": "use cot",
-            "instruction": "hello!",
-            "output": "Hi! How can I help?",
-        }
-        example = strat.tokenize_prompt(sample)
-        assert example["input_ids"][0:5] == [
-            1,
-            28962,
-            1254,
-            12665,
-            29901,
-        ]  # "<s>SYSTEM:"
-        assert example["input_ids"][5:7] == [671, 20118]  # " use cot"
-        assert example["input_ids"][8] == 11889  # USER
-
-
-class Llama2ChatTokenizationTest(unittest.TestCase):
-    """
-    Test class for prompt tokenization strategies with sys prompt from the dataset
-    """
-
-    def setUp(self) -> None:
-        # pylint: disable=duplicate-code
-        self.tokenizer = LlamaTokenizer.from_pretrained("NousResearch/Llama-2-7b-hf")
-        # woraround because official Meta repos are not open
-
-    def test_llama2_chat_integration(self):
-        with open(
-            Path(__file__).parent / "fixtures/conversation.json", encoding="utf-8"
-        ) as fin:
-            data = fin.read()
-            conversation = json.loads(data)
-        with open(
-            Path(__file__).parent / "fixtures/conversation.tokenized_llama2chat.json",
-            encoding="utf-8",
-        ) as fin:
-            data = fin.read()
-            tokenized_conversation = json.loads(data)
-        prompter = Llama2ChatPrompter()
-        strat = LLama2ChatTokenizingStrategy(
-            prompter,
-            self.tokenizer,
-            False,
-            4096,
-        )
-        example = strat.tokenize_prompt(conversation)
-        for fields in ["input_ids", "attention_mask", "labels"]:
-            self.assertEqual(len(example[fields]), len(tokenized_conversation[fields]))
-            self.assertEqual(example[fields], tokenized_conversation[fields])
-
-    def compare_with_transformers_integration(self):
-        # this needs transformers >= v4.31.0
-        from transformers.models.llama.tokenization_llama import B_SYS, E_SYS
-        from transformers.pipelines.conversational import Conversation
-
-        # from transformers.models.llama.tokenization_llama import DEFAULT_SYSTEM_PROMPT
-        # broken as of 23/7/20
-        # see https://github.com/huggingface/transformers/pull/24935
-        # pylint: disable=C0103
-        DEFAULT_SYSTEM_PROMPT = """\
-You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
-
-If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."""
-        with open(
-            Path(__file__).parent / "fixtures/conversation.json", encoding="utf-8"
-        ) as fin:
-            data = fin.read()
-            conversation = json.loads(data)
-        with open(
-            Path(__file__).parent / "fixtures/conversation.tokenized_llama2chat.json",
-            encoding="utf-8",
-        ) as fin:
-            data = fin.read()
-            tokenized_conversation = json.loads(data)
-
-        user_input = []
-        answers = []
-        for msg in conversation["conversations"]:
-            if msg["from"] == "human":
-                user_input.append(msg["value"])
-            else:
-                answers.append(msg["value"])
-        hf_conf = Conversation(
-            text=user_input[-1],
-            past_user_inputs=[B_SYS + DEFAULT_SYSTEM_PROMPT + E_SYS + user_input[0]]
-            + user_input[1:-1],
-            generated_responses=answers,
-        )
-        # pylint: disable=W0212
-        hf_tokens = self.tokenizer._build_conversation_input_ids(hf_conf)
-
-        self.assertEqual(
-            hf_tokens, tokenized_conversation["input_ids"][: len(hf_tokens)]
-        )
-
 
 if __name__ == "__main__":
     unittest.main()

tests/test_prompters.py

@@ -2,13 +2,7 @@
 
 import unittest
 
-from axolotl.prompt_strategies.alpaca_w_system import SystemDataPrompter
-from axolotl.prompters import (
-    AlpacaPrompter,
-    MultipleChoiceExplainPrompter,
-    PromptStyle,
-    UnpromptedPrompter,
-)
+from axolotl.prompters import AlpacaPrompter, PromptStyle
 
 
 class AlpacaPrompterTest(unittest.TestCase):
@@ -61,64 +55,3 @@ class AlpacaPrompterTest(unittest.TestCase):
         assert "### Response:" not in res
         assert "USER:" in res
         assert "ASSISTANT:" in res
-
-    def test_system_prompt(self):
-        prompter = SystemDataPrompter(prompt_style=PromptStyle.CHAT.value)
-        res = next(
-            prompter.build_prompt_w_system(
-                "use cot", "tell me a joke about the following", "alpacas"
-            )
-        )
-        assert "use cot" in res
-        assert res.startswith("SYSTEM:")
-        assert "### Instruction:" not in res
-        assert "### Input:" not in res
-        assert "alpacas" in res
-        assert "### Response:" not in res
-        assert "USER:" in res
-        assert "ASSISTANT:" in res
-
-
-class UnpromptedPrompterTest(unittest.TestCase):
-    """
-    Test class for UnpromptedPrompter with no system prompts
-    """
-
-    def test_prompt_style_w_none(self):
-        prompter = UnpromptedPrompter(prompt_style=None)
-        res = next(prompter.build_prompt("tell me a joke"))
-        assert "### Instruction:" in res
-        assert "tell me a joke" in res
-        assert res.startswith("###")
-
-    def test_prompt_style_w_instruct(self):
-        prompter = UnpromptedPrompter(prompt_style=PromptStyle.INSTRUCT.value)
-        res = next(
-            prompter.build_prompt("tell me a joke about the following", "alpacas")
-        )
-        assert "### Instruction:" in res
-        assert "tell me a joke" in res
-        assert res.startswith("###")
-
-    def test_prompt_style_w_chat(self):
-        prompter = UnpromptedPrompter(prompt_style=PromptStyle.CHAT.value)
-        res = next(
-            prompter.build_prompt("tell me a joke about the following", "alpacas")
-        )
-        assert "USER:" in res
-        assert "tell me a joke" in res
-        assert res.startswith("USER:")
-
-
-class MultipleChoiceExplainPrompterTest(unittest.TestCase):
-    """
-    Test class for MultipleChoiceExplainPrompter
-    """
-
-    def test_prompt_style_w_chat(self):
-        prompter = MultipleChoiceExplainPrompter(prompt_style=PromptStyle.CHAT.value)
-        res = next(prompter.build_prompt("choose one", "- A\n- B\n- C", "C"))
-        assert "USER:" in res
-        assert "choose one" in res
-        assert "Choose the answer that best answers the question." in res
-        assert "- A\n- B\n- C" in res

tests/test_tokenizers.py

@@ -1,31 +0,0 @@
-"""
-Test cases for the tokenizer loading
-"""
-import unittest
-
-from axolotl.utils.dict import DictDefault
-from axolotl.utils.models import load_tokenizer
-
-
-class TestTokenizers(unittest.TestCase):
-    """
-    test class for the load_tokenizer fn
-    """
-
-    def test_default_use_fast(self):
-        cfg = DictDefault({})
-        tokenizer = load_tokenizer("huggyllama/llama-7b", None, cfg)
-        assert "Fast" in tokenizer.__class__.__name__
-
-    def test_dont_use_fast(self):
-        cfg = DictDefault(
-            {
-                "tokenizer_use_fast": False,
-            }
-        )
-        tokenizer = load_tokenizer("huggyllama/llama-7b", None, cfg)
-        assert "Fast" not in tokenizer.__class__.__name__
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/test_validation.py

@@ -1,8 +1,6 @@
 """Module for testing the validation module"""
 
-import logging
 import unittest
-from typing import Optional
 
 import pytest
 
@@ -15,12 +13,6 @@ class ValidationTest(unittest.TestCase):
     Test the validation module
     """
 
-    _caplog: Optional[pytest.LogCaptureFixture] = None
-
-    @pytest.fixture(autouse=True)
-    def inject_fixtures(self, caplog):
-        self._caplog = caplog
-
     def test_load_4bit_deprecate(self):
         cfg = DictDefault(
             {
@@ -31,17 +23,6 @@ class ValidationTest(unittest.TestCase):
         with pytest.raises(ValueError):
             validate_config(cfg)
 
-    def test_batch_size_unused_warning(self):
-        cfg = DictDefault(
-            {
-                "batch_size": 32,
-            }
-        )
-
-        with self._caplog.at_level(logging.WARNING):
-            validate_config(cfg)
-            assert "batch_size is not recommended" in self._caplog.records[0].message
-
     def test_qlora(self):
         base_cfg = DictDefault(
             {
@@ -165,175 +146,3 @@ class ValidationTest(unittest.TestCase):
         )
 
         validate_config(cfg)
-
-    def test_falcon_fsdp(self):
-        regex_exp = r".*FSDP is not supported for falcon models.*"
-
-        # Check for lower-case
-        cfg = DictDefault(
-            {
-                "base_model": "tiiuae/falcon-7b",
-                "fsdp": ["full_shard", "auto_wrap"],
-            }
-        )
-
-        with pytest.raises(ValueError, match=regex_exp):
-            validate_config(cfg)
-
-        # Check for upper-case
-        cfg = DictDefault(
-            {
-                "base_model": "Falcon-7b",
-                "fsdp": ["full_shard", "auto_wrap"],
-            }
-        )
-
-        with pytest.raises(ValueError, match=regex_exp):
-            validate_config(cfg)
-
-        cfg = DictDefault(
-            {
-                "base_model": "tiiuae/falcon-7b",
-            }
-        )
-
-        validate_config(cfg)
-
-    def test_mpt_gradient_checkpointing(self):
-        regex_exp = r".*gradient_checkpointing is not supported for MPT models*"
-
-        # Check for lower-case
-        cfg = DictDefault(
-            {
-                "base_model": "mosaicml/mpt-7b",
-                "gradient_checkpointing": True,
-            }
-        )
-
-        with pytest.raises(ValueError, match=regex_exp):
-            validate_config(cfg)
-
-    def test_flash_optimum(self):
-        cfg = DictDefault(
-            {
-                "flash_optimum": True,
-                "adapter": "lora",
-            }
-        )
-
-        with self._caplog.at_level(logging.WARNING):
-            validate_config(cfg)
-            assert any(
-                "BetterTransformers probably doesn't work with PEFT adapters"
-                in record.message
-                for record in self._caplog.records
-            )
-
-        cfg = DictDefault(
-            {
-                "flash_optimum": True,
-            }
-        )
-
-        with self._caplog.at_level(logging.WARNING):
-            validate_config(cfg)
-            assert any(
-                "probably set bfloat16 or float16" in record.message
-                for record in self._caplog.records
-            )
-
-        cfg = DictDefault(
-            {
-                "flash_optimum": True,
-                "fp16": True,
-            }
-        )
-        regex_exp = r".*AMP is not supported.*"
-
-        with pytest.raises(ValueError, match=regex_exp):
-            validate_config(cfg)
-
-        cfg = DictDefault(
-            {
-                "flash_optimum": True,
-                "bf16": True,
-            }
-        )
-        regex_exp = r".*AMP is not supported.*"
-
-        with pytest.raises(ValueError, match=regex_exp):
-            validate_config(cfg)
-
-    def test_adamw_hyperparams(self):
-        cfg = DictDefault(
-            {
-                "optimizer": None,
-                "adam_epsilon": 0.0001,
-            }
-        )
-
-        with self._caplog.at_level(logging.WARNING):
-            validate_config(cfg)
-            assert any(
-                "adamw hyperparameters found, but no adamw optimizer set"
-                in record.message
-                for record in self._caplog.records
-            )
-
-        cfg = DictDefault(
-            {
-                "optimizer": "adafactor",
-                "adam_beta1": 0.0001,
-            }
-        )
-
-        with self._caplog.at_level(logging.WARNING):
-            validate_config(cfg)
-            assert any(
-                "adamw hyperparameters found, but no adamw optimizer set"
-                in record.message
-                for record in self._caplog.records
-            )
-
-        cfg = DictDefault(
-            {
-                "optimizer": "adamw_bnb_8bit",
-                "adam_beta1": 0.9,
-                "adam_beta2": 0.99,
-                "adam_epsilon": 0.0001,
-            }
-        )
-
-        validate_config(cfg)
-
-        cfg = DictDefault(
-            {
-                "optimizer": "adafactor",
-            }
-        )
-
-        validate_config(cfg)
-
-    def test_packing(self):
-        cfg = DictDefault(
-            {
-                "max_packed_sequence_len": 2048,
-            }
-        )
-        with self._caplog.at_level(logging.WARNING):
-            validate_config(cfg)
-            assert any(
-                "max_packed_sequence_len will be deprecated in favor of sample_packing"
-                in record.message
-                for record in self._caplog.records
-            )
-
-        cfg = DictDefault(
-            {
-                "max_packed_sequence_len": 2048,
-                "sample_packing": True,
-            }
-        )
-        regex_exp = r".*set only one of max_packed_sequence_len \(deprecated soon\) or sample_packing.*"
-        with pytest.raises(ValueError, match=regex_exp):
-            validate_config(cfg)