pre-commit formatting fixes

Command had accidentally been moved out of if-else block.

.github/workflows/base.yml

@@ -12,19 +12,19 @@ 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
-            axolotl_extras:
-          - cuda: "117"
-            cuda_version: 11.7.0
-            pytorch: 1.13.1
-            axolotl_extras:
+            python_version: "3.9"
+            pytorch: 2.0.1
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
           - cuda: "118"
             cuda_version: 11.8.0
-            pytorch: 2.0.0
-            axolotl_extras: gptq
+            python_version: "3.10"
+            pytorch: 2.0.1
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -46,12 +46,11 @@ jobs:
           context: .
           file: ./docker/Dockerfile-base
           push: ${{ github.event_name != 'pull_request' }}
-          tags: ${{ steps.metadata.outputs.tags }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+          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=${{ matrix.pytorch }}
-            AXOLOTL_EXTRAS=${{ matrix.axolotl_extras }}
+            TORCH_CUDA_ARCH_LIST=${{ matrix.torch_cuda_arch_list }}

.github/workflows/main.yml

@@ -11,20 +11,24 @@ 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
-            pytorch: 2.0.0
+            python_version: "3.9"
+            pytorch: 2.0.1
             axolotl_extras:
           - cuda: cu118
             cuda_version: 11.8.0
-            pytorch: 2.0.0
-            axolotl_extras: gptq
-          - cuda: cu117
-            cuda_version: 11.7.0
-            pytorch: 1.13.1
+            python_version: "3.10"
+            pytorch: 2.0.1
             axolotl_extras:
+          - cuda: cu118
+            cuda_version: 11.8.0
+            python_version: "3.9"
+            pytorch: 2.0.1
+            axolotl_extras: gptq
     runs-on: self-hosted
     steps:
       - name: Checkout
@@ -46,13 +50,11 @@ jobs:
         with:
           context: .
           build-args: |
-            BASE_TAG=${{ github.ref_name }}-base-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}
           file: ./docker/Dockerfile
           push: ${{ github.event_name != 'pull_request' }}
-          tags: ${{ steps.metadata.outputs.tags }}-${{ 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: ${{ steps.metadata.outputs.labels }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
   build-axolotl-runpod:
     needs: build-axolotl
     if: github.repository_owner == 'OpenAccess-AI-Collective'
@@ -60,18 +62,21 @@ jobs:
     strategy:
       matrix:
         include:
-          - cuda: cu118
+          - cuda: 118
             cuda_version: 11.8.0
-            pytorch: 2.0.0
+            python_version: "3.9"
+            pytorch: 2.0.1
             axolotl_extras:
-          - cuda: cu118
+          - cuda: 118
             cuda_version: 11.8.0
-            pytorch: 2.0.0
+            python_version: "3.10"
+            pytorch: 2.0.1
+            axolotl_extras:
+          - cuda: 118
+            cuda_version: 11.8.0
+            python_version: "3.9"
+            pytorch: 2.0.1
             axolotl_extras: gptq
-          - cuda: cu117
-            cuda_version: 11.7.0
-            pytorch: 1.13.1
-            axolotl_extras:
     runs-on: self-hosted
     steps:
       - name: Checkout
@@ -93,10 +98,9 @@ jobs:
         with:
           context: .
           build-args: |
-            BASE_TAG=${{ github.ref_name }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            CUDA=${{ matrix.cuda }}
           file: ./docker/Dockerfile-runpod
           push: ${{ github.event_name != 'pull_request' }}
-          tags: ${{ steps.metadata.outputs.tags }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+          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

.github/workflows/tests.yml

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

.mypy.ini

@@ -5,6 +5,9 @@ exclude = venv
 [mypy-alpaca_lora_4bit.*]
 ignore_missing_imports = True
 
+[mypy-axolotl.monkeypatch.*]
+ignore_errors = True
+
 [mypy-flash_attn.*]
 ignore_missing_imports = True
 
@@ -31,3 +34,6 @@ ignore_missing_imports = True
 
 [mypy-addict]
 ignore_missing_imports = True
+
+[mypy-xformers.*]
+ignore_missing_imports = True

.pre-commit-config.yaml

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

FAQS.md

@@ -2,3 +2,6 @@
 
 - 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

@@ -0,0 +1,202 @@
+
+                                 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

@@ -16,31 +16,32 @@
 
 ## Axolotl supports
 
-|         | fp16/fp32 | fp16/fp32 w/ lora | qlora | 4bit-quant | 4bit-quant w/flash attention | flash attention | xformers attention |
-|---------|:----------|:------------------|------|------------|------------------------------|-----------------|--------------------|
-| llama   | ✅         | ✅                 | ✅  | ✅          | ✅                            | ✅               | ✅                  |
-| Pythia  | ✅         | ✅                 | ❓  | ❌          | ❌                            | ❌               | ❓                  |
-| cerebras | ✅         | ✅                 | ❓  | ❌          | ❌                            | ❌               | ❓                  |
-| mpt     | ✅         | ❌                 | ❓  | ❌          | ❌                            | ❌               | ❓                  |
-| falcon  | ✅         | ❌                 | ❌  | ❌          | ❌                            | ❌               | ❓                  |
+|          | fp16/fp32 | lora | qlora | gptq | gptq w/ lora | gptq w/flash attn | flash attn | xformers attn |
+|----------|:----------|:-----|-------|------|:-------------|-------------------|------------|---------------|
+| llama    | ✅         | ✅    | ✅     | ✅    | ✅             | ✅                 | ✅          | ✅             |
+| Pythia   | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❌          | ❓             |
+| cerebras | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❌          | ✅             |
+| mpt      | ✅         | ❌    | ❓     | ❌    | ❓            | ❌                 | ❌          | ❓             |
+| falcon   | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❌          | ✅             |
+| gpt-j    | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❓          | ✅             |
+| XGen     | ✅         | ❓    | ✅     | ❓    | ❓            | ❓                 | ❓          | ✅
 
 
 ## Quickstart ⚡
 
-**Requirements**: Python 3.9.
+**Requirements**: Python >=3.9 and Pytorch >=2.0.
 
 ```bash
 git clone https://github.com/OpenAccess-AI-Collective/axolotl
 
 pip3 install -e .
-
-accelerate config
+pip3 install -U git+https://github.com/huggingface/peft.git
 
 # finetune lora
-accelerate launch scripts/finetune.py examples/lora-openllama-3b/config.yml
+accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml
 
 # inference
-accelerate launch scripts/finetune.py examples/lora-openllama-3b/config.yml \
+accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml \
     --inference --lora_model_dir="./lora-out"
 ```
 
@@ -50,18 +51,82 @@ accelerate launch scripts/finetune.py examples/lora-openllama-3b/config.yml \
 
 - Docker
   ```bash
-  docker run --gpus '"all"' --rm -it winglian/axolotl:main
+  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
   ```
-  - `winglian/axolotl:dev`: dev branch
-  - `winglian/axolotl-runpod:main`: for runpod
 
 - Conda/Pip venv
   1. Install python **3.9**
 
-  2. Install python dependencies with ONE of the following:
-      - `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]`
+  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>
 
 ### Dataset
 
@@ -71,7 +136,7 @@ Have dataset(s) in one of the following format (JSONL recommended):
   ```json
   {"instruction": "...", "input": "...", "output": "..."}
   ```
-- `sharegpt`: conversations
+- `sharegpt:chat`: conversations
   ```json
   {"conversations": [{"from": "...", "value": "..."}]}
   ```
@@ -112,16 +177,73 @@ Have dataset(s) in one of the following format (JSONL recommended):
   ```json
   {"article": "...", "summary": "..."}
   ```
-
-> Have some new format to propose? Check if it's already defined in [data.py](src/axolotl/utils/data.py) in `dev` branch!
+- `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": "..."}]}
+  ```
 
 </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 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:
+See [examples](examples) for quick start. It is recommended to duplicate and modify to your needs. The most important options are:
 
 - model
   ```yaml
@@ -131,10 +253,24 @@ See sample configs in [configs](configs) folder or [examples](examples) for quic
 
 - dataset
   ```yaml
+  sequence_len: 2048 # max token length for prompt
+
+  # huggingface repo
   datasets:
-    - path: vicgalle/alpaca-gpt4 # local or huggingface repo
+    - 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
       type: alpaca # format from earlier
-  sequence_len: 2048 # max token length / prompt
   ```
 
 - loading
@@ -144,6 +280,8 @@ See sample configs in [configs](configs) folder or [examples](examples) for quic
   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.
 
@@ -171,12 +309,22 @@ 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:
 # 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
 # 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
@@ -197,18 +345,21 @@ tf32: true # require >=ampere
 
 # a list of one or more datasets to finetune the model with
 datasets:
-  # this can be either a hf dataset, or relative path
+  # hf dataset repo | "json" for local dataset, make sure to fill data_files
   - path: vicgalle/alpaca-gpt4
   # The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection]
-    type: alpaca # format OR format:prompt_style (chat/instruct)
+    type: alpaca # format | format:<prompt_style> (chat/instruct) | <prompt_strategies>.load_<load_fn>
     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
@@ -260,20 +411,25 @@ wandb_log_model: # 'checkpoint'
 output_dir: ./completed-model
 
 # training hyperparameters
-batch_size: 8
+gradient_accumulation_steps: 1
 micro_batch_size: 2
 eval_batch_size: 2
 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
 
-# does not work with current implementation of 4-bit LoRA
+# Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing
 gradient_checkpointing: false
 
 # stop training after this many evaluation losses have increased in a row
@@ -295,11 +451,27 @@ 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:
 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:
@@ -343,17 +515,6 @@ strict:
 
 </details>
 
-### Accelerate
-
-Configure accelerate
-
-```bash
-accelerate config
-
-# Edit manually
-# nano ~/.cache/huggingface/accelerate/default_config.yaml
-```
-
 ### Train
 
 Run
@@ -361,17 +522,37 @@ 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 ./completed-model
+  --inference --lora_model_dir="./lora-output-dir"
   ```
 - Full weights finetune:
   ```bash
-  --inference --base_model ./completed-model
+  --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
   ```
 
 ### Merge LORA to base
@@ -382,6 +563,12 @@ 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
@@ -389,6 +576,7 @@ Add below flag to train command above
 Please reduce any below
   - `micro_batch_size`
   - `eval_batch_size`
+  - `gradient_accumulation_steps`
   - `sequence_len`
 
 > RuntimeError: expected scalar type Float but found Half
@@ -399,10 +587,34 @@ Try set `fp16: true`
 
 Try to turn off xformers.
 
-## Need help? 🙋‍♂️
+> accelerate config missing
+
+It's safe to ignore it.
+
+## Need help? 🙋♂️
 
 Join our [Discord server](https://discord.gg/HhrNrHJPRb) where we can help you
 
+## Badge ❤🏷️
+
+Building something cool with Axolotl? Consider adding a badge to your model card.
+
+```markdown
+[<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)
+```
+
+[<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

@@ -1,15 +0,0 @@
-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

@@ -1,40 +0,0 @@
-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
-batch_size: 32
-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

@@ -1,41 +0,0 @@
-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
-batch_size: 32
-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

@@ -1,39 +0,0 @@
-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
-batch_size: 64
-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

@@ -1,44 +0,0 @@
-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
-batch_size: 128
-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

@@ -1,45 +0,0 @@
-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
-batch_size: 8
-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

@@ -1,41 +0,0 @@
-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
-batch_size: 128
-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/quickstart.yml

@@ -1,45 +0,0 @@
-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
-batch_size: 4
-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

@@ -1,86 +0,0 @@
-# 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
-batch_size: 8
-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

@@ -1,56 +0,0 @@
-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
-batch_size: 2
-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

@@ -1,45 +0,0 @@
-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
-batch_size: 8
-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 --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
+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
 ```
 ---
 

docker-compose.yaml

@@ -0,0 +1,20 @@
+# 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

@@ -3,18 +3,16 @@ 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" \
-            "accelerate @ git+https://github.com/huggingface/accelerate.git@main" \
-            "transformers @ git+https://github.com/huggingface/transformers.git@main"
-
-RUN mkdir axolotl
-COPY . axolotl/
+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
 # If AXOLOTL_EXTRAS is set, append it in brackets
 RUN cd axolotl && \
     if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
@@ -23,5 +21,10 @@ 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="2.0.0"
+ARG PYTORCH_VERSION="2.0.1"
 ARG CUDA="118"
 
 ENV PYTHON_VERSION=$PYTHON_VERSION
@@ -29,17 +29,18 @@ ENV PATH="/root/miniconda3/envs/py${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==${PYTORCH} torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu$CUDA
+    python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} --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+PTX"
+ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
 
-RUN git clone https://github.com/HazyResearch/flash-attention.git && \
+RUN git clone https://github.com/Dao-AILab/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 && \
@@ -52,6 +53,8 @@ RUN git clone https://github.com/HazyResearch/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"
+
 WORKDIR /workspace
 
 RUN git clone https://github.com/microsoft/DeepSpeed.git && \
@@ -71,11 +74,14 @@ 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 --global-option="--cpp_ext" --global-option="--cuda_ext" --no-cache -v --disable-pip-version-check .
+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 mkdir -p /workspace/builds
 COPY --from=bnb-builder /workspace/bitsandbytes /workspace/builds/bitsandbytes
@@ -95,4 +101,4 @@ 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
+    pip3 install -U --no-cache-dir pydantic==1.10.10

docker/Dockerfile-runpod

@@ -1,6 +1,10 @@
 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 && \

examples/cerebras/qlora.yml

@@ -0,0 +1,60 @@
+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: falcon-7b
+wandb_project:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:

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

@@ -0,0 +1,92 @@
+# 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: falcon-7b
+wandb_project:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:

examples/gptj/qlora.yml

@@ -0,0 +1,57 @@
+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/4bit-lora-7b/config.yml
+accelerate launch scripts/finetune.py examples/gptq-lora-7b/config.yml
 
 ```

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

@@ -26,7 +26,7 @@ wandb_watch:
 wandb_run_id:
 wandb_log_model:
 output_dir: ./llama-7b-lora-int4
-batch_size: 1
+gradient_accumulation_steps: 1
 micro_batch_size: 1
 num_epochs: 3
 optimizer: adamw_bnb_8bit

examples/jeopardy-bot/config.yml

@@ -7,30 +7,28 @@ datasets:
   - path: openaccess-ai-collective/jeopardy
     type: jeopardy
 dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
+val_set_size: 0.02
 adapter:
 lora_model_dir:
-sequence_len: 2048
-max_packed_sequence_len: 2048
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
+sequence_len: 512
+max_packed_sequence_len:
+lora_r:
+lora_alpha:
+lora_dropout:
 lora_target_modules:
-  - q_proj
-  - v_proj
 lora_fan_in_fan_out: false
-wandb_project: jeopardy-bot-7b
+wandb_project:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
 output_dir: ./jeopardy-bot-7b
-batch_size: 4
+gradient_accumulation_steps: 1
 micro_batch_size: 1
-num_epochs: 2
+num_epochs: 3
 optimizer: adamw_bnb_8bit
 torchdistx_path:
 lr_scheduler: cosine
-learning_rate: 0.0000002
+learning_rate: 0.00003
 train_on_inputs: false
 group_by_length: false
 bf16: true
@@ -48,11 +46,10 @@ eval_steps: 110
 save_steps: 660
 debug:
 deepspeed:
-weight_decay: 0.0001
+weight_decay: 0.1
 fsdp:
 fsdp_config:
 tokens:
-  pad_token: "[PAD]"
   bos_token: "<s>"
   eos_token: "</s>"
   unk_token: "<unk>"

examples/llama-2/README.md

@@ -0,0 +1,20 @@
+# 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

@@ -0,0 +1,66 @@
+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

@@ -0,0 +1,67 @@
+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/mpt-7b/config.yml

@@ -24,7 +24,7 @@ wandb_watch:
 wandb_run_id:
 wandb_log_model:
 output_dir: ./mpt-alpaca-7b
-batch_size: 1
+gradient_accumulation_steps: 1
 micro_batch_size: 1
 num_epochs: 3
 optimizer: adamw_bnb_8bit

examples/openllama-3b/README.md

@@ -0,0 +1,16 @@
+# 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

@@ -0,0 +1,62 @@
+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/openllama-3b/lora.yml

@@ -1,5 +1,5 @@
-base_model: openlm-research/open_llama_3b_600bt_preview
-base_model_config: openlm-research/open_llama_3b_600bt_preview
+base_model: openlm-research/open_llama_3b
+base_model_config: openlm-research/open_llama_3b
 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:
+xformers_attention: true
 flash_attention:
 gptq_groupsize:
 gptq_model_v1:

examples/openllama-3b/qlora.yml

@@ -1,5 +1,5 @@
-base_model: openlm-research/open_llama_3b_600bt_preview
-base_model_config: openlm-research/open_llama_3b_600bt_preview
+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

examples/pythia-12b/README.md

@@ -0,0 +1,9 @@
+# Pythia 12B
+
+- Single-GPU A100 only (?)
+
+```shell
+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

@@ -1,39 +1,49 @@
-base_model: EleutherAI/gpt-neox-20b
+base_model: EleutherAI/pythia-12b-deduped
+base_model_config: EleutherAI/pythia-12b-deduped
 base_model_ignore_patterns: pytorch*  # prefer safetensors
 model_type: GPTNeoXForCausalLM
 tokenizer_type: AutoTokenizer
-load_in_8bit: true
+load_in_8bit: false
+load_in_4bit: false
+gptq: false
+device_map: auto
 datasets:
-  - path: nomic-ai/gpt4all-j-prompt-generations
+  - path: vicgalle/alpaca-gpt4
     type: alpaca
-    shards: 4
-    shards_index: 0
 dataset_prepared_path: last_run_prepared
 val_set_size: 0.05
-adapter: lora
+adapter:
 lora_model_dir:
 sequence_len: 2048
 max_packed_sequence_len: 2048
-lora_r: 8
+lora_r: 64
 lora_alpha: 32
-lora_dropout: 0.05
+lora_dropout: 0.0
 lora_target_modules:
-  - query_key_value
+lora_target_linear: true
 lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
-wandb_project: gpt4all-neox-20b
+wandb_project:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
-output_dir: ./gpt4all-neox-20b
-batch_size: 48
-micro_batch_size: 4
+output_dir: ./pythia-12b
+gradient_accumulation_steps: 1
+micro_batch_size: 1
 num_epochs: 5
 learning_rate: 0.00003
-lr_scheduler: one_cycle
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
 train_on_inputs: false
 group_by_length: false
-bf16: True
-tf32: True
+bf16: false
+fp16: false
+float16: true
+tf32: true
+flash_optimum: true
 early_stopping_patience:
 resume_from_checkpoint:
 local_rank:
+gradient_checkpointing: true
+fsdp:
+fsdp_config:
+collator_pad_to_longest: true

examples/pythia/lora.yml

@@ -1,36 +1,29 @@
 base_model: EleutherAI/pythia-1.4b-deduped
-model_type: GPTNeoXForCausalLM
-tokenizer_type: AutoTokenizer
+base_model_config: EleutherAI/pythia-1.4b-deduped
 load_in_8bit: true
 datasets:
-  - path: data/alpaca_data_gpt4.jsonl
+  - path: teknium/GPT4-LLM-Cleaned
     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: 2048
-lora_r: 8
+sequence_len: 512
+lora_r: 16
 lora_alpha: 32
 lora_dropout: 0.05
 lora_target_modules:
   - query_key_value
-#  - xxx
+lora_target_linear:
 lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
-wandb_project: pythia-1.4b-lora
+wandb_project:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
-output_dir: ./lora-alpaca
-batch_size: 48
+output_dir: ./lora-alpaca-pythia
+gradient_accumulation_steps: 1
 micro_batch_size: 4
-num_epochs: 5
+num_epochs: 3
 learning_rate: 0.00001
 train_on_inputs: false
 group_by_length: false
@@ -39,3 +32,6 @@ tf32: True
 early_stopping_patience:
 resume_from_checkpoint:
 local_rank:
+weight_decay: 0.1
+eval_steps: 20
+logging_steps: 1

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

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

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: GPTNeoXTokenizer
+tokenizer_type: AutoTokenizer
 trust_remote_code:
 load_in_8bit: false
 datasets:

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

@@ -0,0 +1,90 @@
+# 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

@@ -1,6 +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
 addict
 fire
 PyYAML==6.0
@@ -10,6 +11,8 @@ sentencepiece
 wandb
 einops
 xformers
+optimum
+hf_transfer
 # qlora things
 bert-score==0.3.13
 evaluate==0.4.0

scripts/alpaca_json_to_jsonl.py

@@ -15,6 +15,9 @@ 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

@@ -13,11 +13,14 @@ import fire
 import torch
 import yaml
 
-from axolotl.utils.data import load_prepare_datasets
+# add src to the pythonpath so we don't need to pip install this
+from optimum.bettertransformer import BetterTransformer
+from transformers import GenerationConfig, TextStreamer
+
+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.models import load_model, load_tokenizer
-
-# add src to the pythonpath so we don't need to pip install this
 from axolotl.utils.tokenization import check_dataset_labels
 from axolotl.utils.trainer import setup_trainer
 from axolotl.utils.validation import validate_config
@@ -27,9 +30,12 @@ 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):
@@ -46,10 +52,11 @@ def choose_device(cfg):
             return "cpu"
 
     cfg.device = get_device()
-    if cfg.device == "cuda":
-        cfg.device_map = {"": cfg.local_rank}
-    else:
-        cfg.device_map = {"": cfg.device}
+    if cfg.device_map != "auto":
+        if cfg.device.startswith("cuda"):
+            cfg.device_map = {"": cfg.local_rank}
+        else:
+            cfg.device_map = {"": cfg.device}
 
 
 def get_multi_line_input() -> Optional[str]:
@@ -61,38 +68,68 @@ def get_multi_line_input() -> Optional[str]:
     return instruction
 
 
-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>"})
+def do_inference(cfg, model, tokenizer, prompter: Optional[str]):
+    default_tokens = {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>"}
 
-    prompter_module = getattr(importlib.import_module("axolotl.prompters"), prompter)
+    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
+        )
 
     while True:
+        print("=" * 80)
         # support for multiline inputs
         instruction = get_multi_line_input()
         if not instruction:
             return
-        prompt: str = next(prompter_module().build_prompt(instruction=instruction))
+        if prompter_module:
+            prompt: str = next(
+                prompter_module().build_prompt(instruction=instruction.strip("\n"))
+            )
+        else:
+            prompt = instruction.strip()
         batch = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
 
+        print("=" * 40)
         model.eval()
         with torch.no_grad():
-            # gc = GenerationConfig()  # TODO swap out and use this
-            generated = model.generate(
-                inputs=batch["input_ids"].to(cfg.device),
-                do_sample=True,
-                use_cache=True,
+            generation_config = GenerationConfig(
                 repetition_penalty=1.1,
-                max_new_tokens=100,
+                max_new_tokens=1024,
                 temperature=0.9,
                 top_p=0.95,
                 top_k=40,
+                bos_token_id=tokenizer.bos_token_id,
+                eos_token_id=tokenizer.eos_token_id,
+                pad_token_id=tokenizer.pad_token_id,
+                do_sample=True,
+                use_cache=True,
                 return_dict_in_generate=True,
                 output_attentions=False,
                 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]))
 
 
@@ -142,24 +179,30 @@ 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 cfg.strict is False:
+        if k in cfg_keys or not cfg.strict:
             # handle booleans
             if isinstance(cfg[k], bool):
                 cfg[k] = bool(kwargs[k])
             else:
                 cfg[k] = kwargs[k]
 
+    validate_config(cfg)
+
     # setup some derived config / hyperparams
-    cfg.gradient_accumulation_steps = cfg.batch_size // cfg.micro_batch_size
+    cfg.gradient_accumulation_steps = cfg.gradient_accumulation_steps or (
+        cfg.batch_size // cfg.micro_batch_size
+    )
+    cfg.batch_size = (
+        cfg.batch_size or cfg.micro_batch_size * cfg.gradient_accumulation_steps
+    )
     cfg.world_size = int(os.environ.get("WORLD_SIZE", 1))
     cfg.local_rank = int(os.environ.get("LOCAL_RANK", 0))
     choose_device(cfg)
     cfg.ddp = cfg.ddp if cfg.ddp is not None else cfg.world_size != 1
     if cfg.ddp:
         cfg.device_map = {"": int(os.environ.get("LOCAL_RANK", 0))}
-        cfg.gradient_accumulation_steps = (
-            cfg.gradient_accumulation_steps // cfg.world_size
-        )
+        cfg.batch_size = cfg.batch_size * cfg.world_size
+
     setup_wandb_env_vars(cfg)
     if cfg.device == "mps":
         cfg.load_in_8bit = False
@@ -168,21 +211,34 @@ def train(
             cfg.fp16 = True
         cfg.bf16 = False
 
-    validate_config(cfg)
+    if cfg.tf32:
+        torch.backends.cuda.matmul.allow_tf32 = True
 
     # load the tokenizer first
-    logging.info("loading tokenizer...")
-    tokenizer = load_tokenizer(cfg.base_model_config, cfg.tokenizer_type, cfg)
+    tokenizer_config = cfg.tokenizer_config or cfg.base_model_config
+    LOG.info(f"loading tokenizer... {tokenizer_config}")
+    tokenizer = load_tokenizer(tokenizer_config, cfg.tokenizer_type, cfg)
 
-    if check_not_in(
-        ["inference", "shard", "merge_lora"], kwargs
+    if (
+        check_not_in(["shard", "merge_lora"], kwargs) and not cfg.inference
     ):  # don't need to load dataset for these
-        train_dataset, eval_dataset = load_prepare_datasets(
-            tokenizer, cfg, DEFAULT_DATASET_PREPARED_PATH
-        )
+        if not cfg.pretraining_dataset:
+            train_dataset, eval_dataset = load_prepare_datasets(
+                tokenizer, cfg, DEFAULT_DATASET_PREPARED_PATH
+            )
+        else:
+            train_dataset = load_pretraining_dataset(
+                cfg.pretraining_dataset,
+                tokenizer,
+                max_tokens=cfg.sequence_len,
+                seed=cfg.seed,
+            )
+            # 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")
+            eval_dataset = None
 
     if cfg.debug or "debug" in kwargs:
-        logging.info("check_dataset_labels...")
+        LOG.info("check_dataset_labels...")
         check_dataset_labels(
             train_dataset.select(
                 [random.randrange(0, len(train_dataset) - 1) for _ in range(5)]  # nosec
@@ -191,11 +247,11 @@ def train(
         )
 
     if prepare_ds_only:
-        logging.info("Finished preparing dataset. Exiting...")
+        LOG.info("Finished preparing dataset. Exiting...")
         return
 
     # Load the model and tokenizer
-    logging.info("loading model and peft_config...")
+    LOG.info("loading model and peft_config...")
     model, peft_config = load_model(
         cfg.base_model,
         cfg.base_model_config,
@@ -203,22 +259,27 @@ def train(
         tokenizer,
         cfg,
         adapter=cfg.adapter,
-        inference=("inference" in kwargs),
     )
 
     if "merge_lora" in kwargs and cfg.adapter is not None:
-        logging.info("running merge of LoRA with base model")
+        LOG.info("running merge of LoRA with base model")
         model = model.merge_and_unload()
         model.to(dtype=torch.float16)
 
         if cfg.local_rank == 0:
-            logging.info("saving merged model")
+            LOG.info("saving merged model")
             model.save_pretrained(str(Path(cfg.output_dir) / "merged"))
         return
 
-    if "inference" in kwargs:
-        logging.info("calling do_inference function")
-        do_inference(cfg, model, tokenizer)
+    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)
         return
 
     if "shard" in kwargs:
@@ -230,27 +291,30 @@ def train(
     model.config.use_cache = False
 
     if torch.__version__ >= "2" and sys.platform != "win32":
-        logging.info("Compiling torch model")
+        LOG.info("Compiling torch model")
         model = torch.compile(model)
 
     # go ahead and presave, so we have the adapter config available to inspect
     if peft_config:
-        logging.info(f"Pre-saving adapter config to {cfg.output_dir}")
+        LOG.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
     if cfg.local_rank == 0:
+
+        def terminate_handler(_, __, model):
+            if cfg.flash_optimum:
+                model = BetterTransformer.reverse(model)
+            model.save_pretrained(cfg.output_dir)
+            sys.exit(0)
+
         signal.signal(
-            signal.SIGINT,
-            lambda signal, frame: (
-                model.save_pretrained(cfg.output_dir),
-                sys.exit(0),
-            ),
+            signal.SIGINT, lambda signum, frame: terminate_handler(signum, frame, model)
         )
 
-    logging.info("Starting trainer...")
+    LOG.info("Starting trainer...")
     if cfg.group_by_length:
-        logging.info("hang tight... sorting dataset for group_by_length")
+        LOG.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 = [
@@ -262,16 +326,29 @@ def train(
                 key=lambda path: int(path.split("-")[-1]),
             )
             resume_from_checkpoint = sorted_paths[-1]
-            logging.info(
+            LOG.info(
                 f"Using Auto-resume functionality to start with checkpoint at {resume_from_checkpoint}"
             )
-    trainer.train(resume_from_checkpoint=resume_from_checkpoint)
 
-    logging.info(f"Training Completed!!! Saving pre-trained model to {cfg.output_dir}")
+    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
+        ):
+            trainer.train(resume_from_checkpoint=resume_from_checkpoint)
+    else:
+        trainer.train(resume_from_checkpoint=resume_from_checkpoint)
+
+    LOG.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.local_rank == 0:
+    if cfg.fsdp:
+        model.save_pretrained(cfg.output_dir)
+    elif 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

scripts/runpod-entrypoint.sh

@@ -1,10 +1,21 @@
 #!/bin/bash
 
-echo $PUBLIC_KEY >> ~/.ssh/authorized_keys
-chmod 700 -R ~/.ssh
+# 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
 
-# Start the SSH service in the background
-service ssh start
+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
 
 # Execute the passed arguments (CMD)
 exec "$@"

src/axolotl/datasets.py

@@ -1,12 +1,13 @@
 """Module containing Dataset functionality"""
 
 import logging
+import os
 from typing import List
 
 import torch
 from datasets import IterableDataset
 
-from .prompt_tokenizers import InvalidDataException, PromptTokenizingStrategy
+from .prompt_tokenizers import 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
@@ -14,6 +15,8 @@ from .prompt_tokenizers import InvalidDataException, 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):
     """
@@ -32,13 +35,15 @@ class TokenizedPromptDataset(IterableDataset):
         self.dataset = dataset
 
     def __iter__(self):
-        iterator = iter(self.dataset)
-        # Loop through the entire dataset
-        for example in iterator:
-            try:
-                yield self.prompt_tokenizer.tokenize_prompt(example)
-            except InvalidDataException:
-                pass
+        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,
+            )
+        )
 
 
 # TODO this isn't the best since it can't interleave datasets
@@ -111,7 +116,7 @@ class ConstantLengthDataset(IterableDataset):
                                 "attention_mask": attention_mask,
                             }
                         else:
-                            logging.warning(
+                            LOG.warning(
                                 f"dropping batch due to tensor size mismatch input_ids: {input_ids.size()}, labels: {labels.size()}, attention_mask: {attention_mask.size()}"
                             )
                     buffer = {
@@ -122,11 +127,17 @@ class ConstantLengthDataset(IterableDataset):
                     buffer_len = 0
 
                 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)

src/axolotl/logging_config.py

@@ -0,0 +1,33 @@
+"""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_flash.py

@@ -8,7 +8,7 @@ import torch
 import transformers
 from einops import rearrange
 from flash_attn.bert_padding import pad_input, unpad_input
-from flash_attn.flash_attn_interface import flash_attn_unpadded_qkvpacked_func
+from flash_attn.flash_attn_interface import flash_attn_varlen_qkvpacked_func
 from transformers.models.llama.modeling_llama import apply_rotary_pos_emb
 
 
@@ -25,6 +25,7 @@ def forward(
 
     attention_mask: [bsz, q_len]
     """
+    # pylint: disable=duplicate-code
     bsz, q_len, _ = hidden_states.size()
 
     query_states = (
@@ -78,7 +79,7 @@ def forward(
             dtype=torch.int32,
             device=qkv.device,
         )
-        output = flash_attn_unpadded_qkvpacked_func(
+        output = flash_attn_varlen_qkvpacked_func(
             qkv, cu_q_lens, max_s, 0.0, softmax_scale=None, causal=True
         )
         output = rearrange(output, "(b s) ... -> b s ...", b=bsz)
@@ -94,7 +95,7 @@ def forward(
             three=3,
             h=nheads,
         )
-        output_unpad = flash_attn_unpadded_qkvpacked_func(
+        output_unpad = flash_attn_varlen_qkvpacked_func(
             x_unpad,
             cu_q_lens,
             max_s,

src/axolotl/monkeypatch/llama_attn_hijack_xformers.py

@@ -0,0 +1,283 @@
+"""
+Directly copied the code from https://raw.githubusercontent.com/oobabooga/text-generation-webui/main/modules/llama_attn_hijack.py and made some adjustments
+"""
+
+import logging
+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
+
+try:
+    import xformers.ops
+except ImportError:
+    logging.error("xformers not found! Please install it before trying to use it.")
+
+
+def hijack_llama_attention():
+    transformers.models.llama.modeling_llama.LlamaAttention.forward = xformers_forward
+
+
+def hijack_llama_sdp_attention():
+    transformers.models.llama.modeling_llama.LlamaAttention.forward = (
+        sdp_attention_forward
+    )
+
+
+def xformers_forward(
+    self,
+    hidden_states: torch.Tensor,
+    attention_mask: Optional[torch.Tensor] = None,
+    position_ids: Optional[torch.LongTensor] = None,
+    past_key_value: Optional[Tuple[torch.Tensor]] = None,
+    output_attentions: bool = False,
+    use_cache: bool = False,
+) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
+    # 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)
+
+    kv_seq_len = key_states.shape[-2]
+    if past_key_value is not None:
+        kv_seq_len += past_key_value[0].shape[-2]
+    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
+    (
+        query_states,
+        key_states,
+    ) = transformers.models.llama.modeling_llama.apply_rotary_pos_emb(
+        query_states, key_states, cos, sin, position_ids
+    )
+    # [bsz, nh, t, hd]
+
+    if past_key_value is not None:
+        # reuse k, v, self_attention
+        key_states = torch.cat([past_key_value[0], key_states], dim=2)
+        value_states = torch.cat([past_key_value[1], value_states], dim=2)
+
+    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)
+        key_states = key_states.transpose(1, 2)
+        value_states = value_states.transpose(1, 2)
+
+        # This is a nasty hack. We know attention_mask in transformers is either LowerTriangular or all Zeros.
+        # We therefore check if one element in the upper triangular portion is zero. If it is, then the mask is all zeros.
+        if attention_mask is None or attention_mask[0, 0, 0, 1] == 0:
+            # input and output should be of form (bsz, q_len, num_heads, head_dim)
+            attn_output = xformers.ops.memory_efficient_attention(
+                query_states, key_states, value_states, attn_bias=None
+            )
+        else:
+            # input and output should be of form (bsz, q_len, num_heads, head_dim)
+            attn_output = xformers.ops.memory_efficient_attention(
+                query_states,
+                key_states,
+                value_states,
+                attn_bias=xformers.ops.LowerTriangularMask(),
+            )
+        attn_weights = None
+    else:
+        attn_weights = torch.matmul(
+            query_states, key_states.transpose(2, 3)
+        ) / math.sqrt(self.head_dim)
+
+        if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len):
+            raise ValueError(
+                f"Attention weights should be of size {(bsz * self.num_heads, q_len, kv_seq_len)}, but is"
+                f" {attn_weights.size()}"
+            )
+
+        if attention_mask is not None:
+            if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
+                raise ValueError(
+                    f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
+                )
+            attn_weights = attn_weights + attention_mask
+            attn_weights = torch.max(
+                attn_weights, torch.tensor(torch.finfo(attn_weights.dtype).min)
+            )
+
+        # upcast attention to fp32
+        attn_weights = nn.functional.softmax(
+            attn_weights, dim=-1, dtype=torch.float32
+        ).to(query_states.dtype)
+        attn_output = torch.matmul(attn_weights, value_states)
+
+        if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim):
+            raise ValueError(
+                f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is"
+                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.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)
+
+    return attn_output, attn_weights, past_key_value
+
+
+def sdp_attention_forward(
+    self,
+    hidden_states: torch.Tensor,
+    attention_mask: Optional[torch.Tensor] = None,
+    position_ids: Optional[torch.LongTensor] = None,
+    past_key_value: Optional[Tuple[torch.Tensor]] = None,
+    output_attentions: bool = False,
+    use_cache: bool = False,
+) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
+    # pylint: disable=duplicate-code
+    bsz, q_len, _ = hidden_states.size()
+
+    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:
+        kv_seq_len += past_key_value[0].shape[-2]
+    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
+    (
+        query_states,
+        key_states,
+    ) = transformers.models.llama.modeling_llama.apply_rotary_pos_emb(
+        query_states, key_states, cos, sin, position_ids
+    )
+    # [bsz, nh, t, hd]
+
+    if past_key_value is not None:
+        # reuse k, v, self_attention
+        key_states = torch.cat([past_key_value[0], key_states], dim=2)
+        value_states = torch.cat([past_key_value[1], value_states], dim=2)
+
+    past_key_value = (key_states, value_states) if use_cache else None
+
+    # 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
+    else:
+        attn_weights = torch.matmul(
+            query_states, key_states.transpose(2, 3)
+        ) / math.sqrt(self.head_dim)
+
+        if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len):
+            raise ValueError(
+                f"Attention weights should be of size {(bsz * self.num_heads, q_len, kv_seq_len)}, but is"
+                f" {attn_weights.size()}"
+            )
+
+        if attention_mask is not None:
+            if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
+                raise ValueError(
+                    f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
+                )
+            attn_weights = attn_weights + attention_mask
+            attn_weights = torch.max(
+                attn_weights, torch.tensor(torch.finfo(attn_weights.dtype).min)
+            )
+
+        # upcast attention to fp32
+        attn_weights = nn.functional.softmax(
+            attn_weights, dim=-1, dtype=torch.float32
+        ).to(query_states.dtype)
+        attn_output = torch.matmul(attn_weights, value_states)
+
+        if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim):
+            raise ValueError(
+                f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is"
+                f" {attn_output.size()}"
+            )
+
+    attn_output = attn_output.transpose(1, 2)
+    attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)
+
+    attn_output = self.o_proj(attn_output)
+
+    return attn_output, attn_weights, past_key_value

src/axolotl/monkeypatch/xpos_rope_llama_monkey_patch.py

@@ -0,0 +1,94 @@
+# 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
+from axolotl.prompters import AlpacaPrompter, PromptStyle, UnpromptedPrompter
 
 
 def load(tokenizer, cfg):
@@ -18,6 +18,42 @@ 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
@@ -31,9 +67,49 @@ class AlpacaQAPromptTokenizingStrategy(InstructionPromptTokenizingStrategy):
         )
 
 
-def load_qa(tokenizer, cfg):
-    return AlpacaQAPromptTokenizingStrategy(
-        AlpacaPrompter(PromptStyle.CHAT.value),
+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),
         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
+from axolotl.prompters import AlpacaPrompter, PromptStyle, UnpromptedPrompter
 
 
 def load(tokenizer, cfg):
@@ -11,3 +11,12 @@ 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

@@ -0,0 +1,139 @@
+"""
+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 = f"### System:\n{system}\n\n" if system 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):
+        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:"
+
+
+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,
+    )

src/axolotl/prompt_strategies/context_qa.py

@@ -0,0 +1,67 @@
+"""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/pygmalion.py

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

src/axolotl/prompt_strategies/sharegpt_jokes.py

@@ -0,0 +1,28 @@
+"""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

@@ -0,0 +1,67 @@
+"""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

@@ -10,6 +10,8 @@ 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
@@ -46,16 +48,22 @@ class PromptTokenizingStrategy(abc.ABC):
 
     @functools.lru_cache(maxsize=128)
     def _get_user_token(self):
-        id_or_ids = self.tokenizer.convert_tokens_to_ids("<|USER|>")
-        if isinstance(id_or_ids, (int,)):
-            return id_or_ids
+        try:
+            id_or_ids = self.tokenizer.convert_tokens_to_ids("<|USER|>")
+            if isinstance(id_or_ids, (int,)):
+                return id_or_ids
+        except KeyError:
+            pass
         return False
 
     @functools.lru_cache(maxsize=128)
     def _get_assistant_token(self):
-        id_or_ids = self.tokenizer.convert_tokens_to_ids("<|ASSISTANT|>")
-        if isinstance(id_or_ids, (int,)):
-            return id_or_ids
+        try:
+            id_or_ids = self.tokenizer.convert_tokens_to_ids("<|ASSISTANT|>")
+            if isinstance(id_or_ids, (int,)):
+                return id_or_ids
+        except KeyError:
+            pass
         return False
 
     def _tokenize(self, prompt: str, add_eos_token=True, strip_bos_token=False):
@@ -87,7 +95,9 @@ class InstructionPromptTokenizingStrategy(PromptTokenizingStrategy):
     Tokenizing strategy for instruction-based prompts.
     """
 
-    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str]:
+    def parse_instruction_fields(
+        self, prompt
+    ) -> Union[Tuple[str, str, str], Tuple[str, str, str, str]]:
         raise NotImplementedError
 
     def tokenize_prompt(self, prompt):
@@ -96,25 +106,27 @@ class InstructionPromptTokenizingStrategy(PromptTokenizingStrategy):
             input,  # pylint: disable=redefined-builtin
             response,
         ) = self.parse_instruction_fields(prompt)
-        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,
-                    )
+        user_prompt = next(
+            iter(
+                self.prompter.build_prompt(
+                    instruction,
+                    input,
                 )
             )
-            tokenized_user_prompt = self._tokenize(user_prompt, add_eos_token=False)
-            user_prompt_len = len(tokenized_user_prompt["input_ids"])
+        )
+        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_full_prompt["labels"] = [
-                -100
-            ] * user_prompt_len + tokenized_full_prompt["labels"][user_prompt_len:]
+            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_full_prompt
+        return tokenized_prompt
 
     def _build_full_prompt(
         self, instruction, input, response  # pylint: disable=redefined-builtin
@@ -380,7 +392,7 @@ class ShareGPTPromptTokenizingStrategy(PromptTokenizingStrategy):
                         # everything from this is masked out from the labels
                         labels = [IGNORE_TOKEN_ID] * len(res["input_ids"])
                     else:
-                        logging.warning(f"unhandled role: {part[0]}")
+                        LOG.warning(f"unhandled role: {part[0]}")
 
                 # pylint: disable=duplicate-code
                 result, current_len = parse_tokenized_to_result(
@@ -436,7 +448,7 @@ 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

@@ -5,6 +5,7 @@ import logging
 from enum import Enum, auto
 from typing import Generator, List, Optional, Tuple, Union
 
+LOG = logging.getLogger("axolotl")
 IGNORE_TOKEN_ID = -100
 
 
@@ -24,6 +25,8 @@ 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"
+    turn_format: str
+    turn_no_input_format: str
     prompt_style: Optional[PromptStyle] = None
 
     def __init__(self, prompt_style=PromptStyle.INSTRUCT.value):
@@ -32,23 +35,13 @@ class AlpacaPrompter:
 
     def match_prompt_style(self):
         if self.prompt_style == PromptStyle.INSTRUCT.value:
-            self.prompt_input = (
-                self.system_prompt
-                + "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
+            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_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.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:"
+            self.turn_format = "USER: {instruction}\n{input}\nASSISTANT:"
+            self.turn_no_input_format = "USER: {instruction}\nASSISTANT:"
 
     def build_prompt(
         self,
@@ -59,16 +52,17 @@ 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.prompt_input.format(instruction=instruction, input=input)
+            res = self.system_prompt + self.turn_format.format(
+                instruction=instruction, input=input
+            )
         else:
-            res = self.prompt_no_input.format(instruction=instruction)
+            res = self.system_no_input_prompt + self.turn_no_input_format.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):
     """
@@ -93,7 +87,10 @@ class MultipleChoiceExplainPrompter(AlpacaPrompter):
     """
 
     system_prompt = (
-        "Choose the answer that best answers the question. Explain your reasoning."
+        "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"
     )
 
 
@@ -102,7 +99,12 @@ class MultipleChoiceConcisePrompter(AlpacaPrompter):
     Prompter for multiple choice concise
     """
 
-    prompt_input = "Choose the answer that best answers the question. Be concise in your response.\n\nUSER: {instruction}\n{input}\nASSISTANT:\n"
+    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:"
 
 
 class SummarizeTLDRPrompter(AlpacaPrompter):
@@ -110,9 +112,12 @@ class SummarizeTLDRPrompter(AlpacaPrompter):
     Prompter for summarize TLDR
     """
 
-    prompt_no_input = (
-        "USER: Summarize the following article as a TL;DR.\n{instruction}\nASSISTANT:"
-    )
+    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:"
 
 
 class CompletionPrompter:
@@ -128,9 +133,6 @@ class CompletionPrompter:
     ) -> Generator[str, None, None]:
         yield instruction
 
-    def get_response(self, output: str) -> str:
-        return output.strip()
-
 
 class GPTeacherPrompter(AlpacaPrompter):
     """
@@ -210,9 +212,6 @@ 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."""
@@ -243,7 +242,7 @@ class Conversation:
             if message:
                 yield (role + ":", " " + message)
             else:
-                logging.warning(f"role with empty message: {role}")
+                LOG.warning(f"role with empty message: {role}")
                 yield (role + ":", "")
 
     def copy(self):
@@ -261,34 +260,33 @@ 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):
+    def __init__(self, prompt_style=None, system_prompt: Optional[str] = None):
         if prompt_style != PromptStyle.CHAT.value:
             raise ValueError(
                 f"unsupported prompt_style for ShareGPTPrompter({prompt_style})"
             )
-
-    # 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:"
+        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 build_prompt(self, source) -> Generator[str, None, None]:
         # ignore the system prompt if provided
@@ -300,7 +298,7 @@ class ShareGPTPrompter:  # pylint: disable=too-few-public-methods
             # also happens on the data splitting leaving empty conversations
             raise IndexError
 
-        conv = conv_vicuna_v1_1.copy()
+        conv = self._conversation.copy()
         roles = {"human": conv.roles[0], "gpt": conv.roles[1]}
 
         try:

src/axolotl/utils/callbacks.py

@@ -2,13 +2,14 @@
 
 import os
 
+from optimum.bettertransformer import BetterTransformer
 from transformers import (
     TrainerCallback,
     TrainerControl,
     TrainerState,
     TrainingArguments,
 )
-from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR
+from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR, IntervalStrategy
 
 
 class SavePeftModelCallback(TrainerCallback):  # pylint: disable=too-few-public-methods
@@ -30,3 +31,39 @@ class SavePeftModelCallback(TrainerCallback):  # pylint: disable=too-few-public-
         kwargs["model"].save_pretrained(peft_model_path)
 
         return control
+
+
+class SaveBetterTransformerModelCallback(
+    TrainerCallback
+):  # pylint: disable=too-few-public-methods
+    """Callback to save the BetterTransformer wrapped model"""
+
+    def on_step_end(
+        self,
+        args: TrainingArguments,
+        state: TrainerState,
+        control: TrainerControl,
+        **kwargs,
+    ):
+        # Save
+        if (
+            args.save_strategy == IntervalStrategy.STEPS
+            and args.save_steps > 0
+            and state.global_step % args.save_steps == 0
+        ):
+            control.should_save = True
+
+        if control.should_save:
+            checkpoint_folder = os.path.join(
+                args.output_dir,
+                f"{PREFIX_CHECKPOINT_DIR}-{state.global_step}",
+            )
+
+            model = BetterTransformer.reverse(kwargs["model"])
+            model.save_pretrained(checkpoint_folder)
+            # FIXME - need to cleanup old checkpoints
+
+            # since we're saving here, we don't need the trainer loop to attempt to save too b/c
+            # the trainer will raise an exception since it can't save a BetterTransformer wrapped model
+            control.should_save = False
+        return control

src/axolotl/utils/data.py

@@ -1,10 +1,12 @@
 """Module containing data utilities"""
-
+import functools
+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 huggingface_hub import hf_hub_download
 from transformers import PreTrainedTokenizerBase
@@ -34,6 +36,8 @@ from axolotl.prompters import (
     SummarizeTLDRPrompter,
 )
 
+LOG = logging.getLogger("axolotl")
+
 
 def load_tokenized_prepared_datasets(
     tokenizer, cfg, default_dataset_prepared_path
@@ -72,12 +76,19 @@ def load_tokenized_prepared_datasets(
     if dataset:
         ...
     elif any(prepared_ds_path.glob("*")):
-        logging.info(f"Loading prepared dataset from disk at {prepared_ds_path}...")
+        LOG.info(f"Loading prepared dataset from disk at {prepared_ds_path}...")
         dataset = load_from_disk(str(prepared_ds_path))
-        logging.info("Prepared dataset loaded from disk...")
+        LOG.info("Prepared dataset loaded from disk...")
     else:
-        logging.info(f"Unable to find prepared dataset in {prepared_ds_path}")
-        logging.info("Loading raw datasets...")
+        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
+
         datasets = []
         # pylint: disable=invalid-name
         for d in cfg.datasets:
@@ -86,6 +97,7 @@ def load_tokenized_prepared_datasets(
             try:
                 load_dataset(
                     d.path,
+                    name=d.name,
                     streaming=True,
                     use_auth_token=use_auth_token,
                 )
@@ -94,44 +106,55 @@ def load_tokenized_prepared_datasets(
                 pass
 
             # prefer local dataset, even if hub exists
-            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:
+            local_path = Path(d.path)
+            if local_path.exists():
+                if local_path.is_dir():
                     ds = load_dataset(
                         d.path,
-                        streaming=False,
+                        name=d.name,
                         data_files=d.data_files,
-                        use_auth_token=use_auth_token,
+                        streaming=False,
+                        split=None,
+                    )
+                elif local_path.is_file():
+                    ds = load_dataset(
+                        "json",
+                        name=d.name,
+                        data_files=d.path,
+                        streaming=False,
+                        split=None,
                     )
                 else:
-                    ds = load_dataset(
-                        d.path,
-                        streaming=False,
-                        use_auth_token=use_auth_token,
+                    raise ValueError(
+                        "unhandled dataset load: local path exists, but is neither a directory or a file"
                     )
+            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", data_files=fp, streaming=False, split=None)
+                ds = load_dataset(
+                    "json", name=d.name, 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=42)["train"].shard(
+                    ds = ds.shuffle(seed=seed)["train"].shard(
                         num_shards=d.shards, index=0
                     )
                 else:
-                    ds = ds.shuffle(seed=42).shard(num_shards=d.shards, index=0)
+                    ds = ds.shuffle(seed=seed).shard(num_shards=d.shards, index=0)
             d_type = d.type
             d_type_split = d_type.split(":")
             d_base_type = d_type_split[0]
@@ -232,20 +255,32 @@ def load_tokenized_prepared_datasets(
                 ds_wrapper = TokenizedPromptDataset(ds_strategy, ds)
                 datasets.append(ds_wrapper)
             else:
-                logging.error(f"unhandled prompt tokenization strategy: {d.type}")
-        logging.info("tokenizing, merging, and shuffling master dataset")
+                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")
 
         samples: List[int] = []
+        chunk_size = 1000
         for d in datasets:
-            samples = samples + list(d)
-        dataset = Dataset.from_list(samples).shuffle(seed=42)
+            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)
         if cfg.local_rank == 0:
-            logging.info(
-                f"Saving merged prepared dataset to disk... {prepared_ds_path}"
-            )
+            LOG.info(f"Saving merged prepared dataset to disk... {prepared_ds_path}")
             dataset.save_to_disk(prepared_ds_path)
             if cfg.push_dataset_to_hub:
-                logging.info(
+                LOG.info(
                     f"Saving merged prepared dataset with push_to_hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                 )
                 dataset.push_to_hub(
@@ -296,7 +331,7 @@ def load_prepare_datasets(
         use_auth_token = cfg.hf_use_auth_token
         try:
             if cfg.push_dataset_to_hub:
-                logging.info(
+                LOG.info(
                     f"Checking for packed prepared dataset from hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                 )
                 dataset = load_dataset(
@@ -310,13 +345,13 @@ def load_prepare_datasets(
         if dataset:
             ...
         elif any(prepared_ds_path.glob("*")):
-            logging.info(
+            LOG.info(
                 f"Loading prepared packed dataset from disk at {prepared_ds_path}..."
             )
             dataset = load_from_disk(str(prepared_ds_path))
-            logging.info("Prepared packed dataset loaded from disk...")
+            LOG.info("Prepared packed dataset loaded from disk...")
             if cfg.push_dataset_to_hub:
-                logging.info(
+                LOG.info(
                     f"Saving packed prepared dataset with push_to_hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                 )
                 dataset.push_to_hub(
@@ -335,9 +370,7 @@ def load_prepare_datasets(
                 [dataset],
                 seq_length=max_packed_sequence_len,
             )
-            logging.info(
-                f"packing master dataset to len: {cfg.max_packed_sequence_len}"
-            )
+            LOG.info(f"packing master dataset to len: {cfg.max_packed_sequence_len}")
             dataset = Dataset.from_list(list(constant_len_dataset))
 
             # filter out bad data
@@ -353,12 +386,12 @@ def load_prepare_datasets(
             )
 
             if cfg.local_rank == 0:
-                logging.info(
+                LOG.info(
                     f"Saving packed prepared dataset to disk... {prepared_ds_path}"
                 )
                 dataset.save_to_disk(prepared_ds_path)
                 if cfg.push_dataset_to_hub:
-                    logging.info(
+                    LOG.info(
                         f"Saving packed prepared dataset with push_to_hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                     )
                     dataset.push_to_hub(
@@ -371,7 +404,7 @@ def load_prepare_datasets(
         )
 
     if cfg.dataset_shard_num and cfg.dataset_shard_idx is not None:
-        logging.info(
+        LOG.info(
             f"Using index #{cfg.dataset_shard_idx} of {cfg.dataset_shard_num} shards"
         )
         dataset = dataset.shard(
@@ -379,8 +412,127 @@ def load_prepare_datasets(
             index=cfg.dataset_shard_idx,
         )
 
-    dataset = dataset.train_test_split(test_size=cfg.val_set_size, shuffle=False)
-    train_dataset = dataset["train"]
-    eval_dataset = dataset["test"]
+    if cfg.val_set_size:
+        dataset = dataset.train_test_split(test_size=cfg.val_set_size, shuffle=False)
+        train_dataset = dataset["train"]
+        eval_dataset = dataset["test"]
+    else:
+        train_dataset = dataset
+        eval_dataset = None
 
     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)
+
+    # 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)
+
+    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 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

src/axolotl/utils/models.py

@@ -10,46 +10,52 @@ from typing import TYPE_CHECKING, Optional, Tuple  # noqa: F401
 import bitsandbytes as bnb
 import torch
 import transformers
-from transformers import AutoModelForCausalLM  # noqa: F401
-from transformers import PreTrainedModel  # noqa: F401
-from transformers import AutoConfig, AutoTokenizer, BitsAndBytesConfig
-
-try:
-    from transformers import LlamaForCausalLM
-except ImportError:
-    logging.warning(
-        "This version of transformers does not support Llama. Consider upgrading."
-    )
+from optimum.bettertransformer import BetterTransformer
+from transformers import (  # noqa: F401
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+    LlamaConfig,
+    PreTrainedModel,
+    PreTrainedTokenizerBase,
+)
 
 from axolotl.prompt_tokenizers import LLAMA_DEFAULT_PAD_TOKEN
 
+LOG = logging.getLogger("axolotl")
+
 if TYPE_CHECKING:
     from peft import PeftConfig  # noqa: F401
-    from transformers import PreTrainedTokenizer  # noqa: F401
 
     from axolotl.utils.dict import DictDefault  # noqa: F401
 
 
 def load_tokenizer(
-    base_model_config,
+    tokenizer_config,
     tokenizer_type,
     cfg,
 ):
+    use_fast = True  # this is the default
+    if cfg.tokenizer_use_fast is not None:
+        use_fast = cfg.tokenizer_use_fast
     if tokenizer_type:
         tokenizer = getattr(transformers, tokenizer_type).from_pretrained(
-            base_model_config,
+            tokenizer_config,
             trust_remote_code=cfg.trust_remote_code or False,
+            use_fast=use_fast,
         )
     else:
         tokenizer = AutoTokenizer.from_pretrained(
-            base_model_config,
+            tokenizer_config,
             trust_remote_code=cfg.trust_remote_code or False,
+            use_fast=use_fast,
         )
 
-    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}")
+    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}")
 
     if tokenizer.__class__.__name__ in [
         "LlamaTokenizer",
@@ -71,42 +77,64 @@ def load_tokenizer(
 
 
 def load_model(
-    base_model,
-    base_model_config,
-    model_type,
-    tokenizer,
-    cfg,
-    adapter="lora",
-    inference=False,
+    base_model, base_model_config, model_type, tokenizer, cfg, adapter="lora"
 ):
-    # type: (str, str, str, str, DictDefault, Optional[str], bool) -> Tuple[PreTrainedModel, Optional[PeftConfig]]
+    # type: (str, str, str, PreTrainedTokenizerBase, DictDefault, Optional[str]) -> 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
-    is_llama_derived_model = "llama" in base_model or (
+    cfg.is_llama_derived_model = "llama" in base_model or (
         cfg.model_type and "llama" in cfg.model_type.lower()
     )
 
-    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
+    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,
+            )
 
-            logging.info("patching with flash attention")
+            LOG.info("patching with flash attention")
             replace_llama_attn_with_flash_attn()
-    elif is_llama_derived_model and cfg.xformers_attention:
-        from alpaca_lora_4bit.monkeypatch.llama_attn_hijack_xformers import (
+    elif cfg.is_llama_derived_model and cfg.xformers_attention:
+        from axolotl.monkeypatch.llama_attn_hijack_xformers import (
             hijack_llama_attention,
         )
 
-        logging.info("patching with xformers attention")
+        LOG.info("patching with xformers attention")
         hijack_llama_attention()
+    elif cfg.is_llama_derived_model and cfg.sdp_attention:
+        from axolotl.monkeypatch.llama_attn_hijack_xformers import (
+            hijack_llama_sdp_attention,
+        )
 
-    if cfg.bf16:
+        LOG.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.bf16 or cfg.bfloat16:
         torch_dtype = torch.bfloat16
-    elif cfg.load_in_8bit or cfg.fp16:
+    elif cfg.load_in_8bit or cfg.fp16 or cfg.float16:
         torch_dtype = torch.float16
     else:
         torch_dtype = torch.float32
@@ -117,12 +145,25 @@ def load_model(
             )
 
             replace_peft_model_with_int4_lora_model()
-        from peft import prepare_model_for_int8_training
     except Exception as err:
-        logging.exception(err)
+        LOG.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,
@@ -133,7 +174,7 @@ def load_model(
             bnb_4bit_quant_type="nf4",
         )
     try:
-        if cfg.gptq and is_llama_derived_model:
+        if cfg.gptq and cfg.is_llama_derived_model:
             from alpaca_lora_4bit.autograd_4bit import load_llama_model_4bit_low_ram
             from huggingface_hub import snapshot_download
 
@@ -154,7 +195,7 @@ def load_model(
                 if len(files) > 0:
                     model_path = str(files[0])
                 else:
-                    logging.warning(
+                    LOG.warning(
                         "unable to find a cached model file, this will likely fail..."
                     )
                     model_path = str(cache_model_path)
@@ -171,9 +212,13 @@ def load_model(
                 else True,
             )
             load_in_8bit = False
-        elif is_llama_derived_model and "LlamaForCausalLM" in globals():
+        elif cfg.is_llama_derived_model and not cfg.trust_remote_code:
+            from transformers import LlamaForCausalLM
+
+            config = LlamaConfig.from_pretrained(base_model_config)
             model = LlamaForCausalLM.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,
@@ -206,7 +251,7 @@ def load_model(
         #         device=cfg.device,
         #     )
         #     model.train() # sets to train instead of eval mode
-        elif model_type:
+        elif model_type and not cfg.trust_remote_code:
             model = getattr(transformers, model_type).from_pretrained(
                 base_model,
                 load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
@@ -221,6 +266,22 @@ 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,
@@ -232,28 +293,55 @@ def load_model(
                 **model_kwargs,
             )
     except Exception as err:  # pylint: disable=broad-exception-caught
-        logging.error(
+        LOG.error(
             "Exception raised attempting to load model, retrying with AutoModelForCausalLM"
         )
-        logging.exception(err)
+        LOG.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
+    embeddings_len = (
+        math.ceil(len(tokenizer) / 32) * 32
+        if cfg.resize_token_embeddings_to_32x
+        else len(tokenizer)
+    )
     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(
+            f"increasing model.config.max_position_embeddings to {cfg.sequence_len}"
+        )
+        model.config.max_position_embeddings = cfg.sequence_len
+
     if not cfg.gptq and (
         (cfg.adapter == "lora" and load_in_8bit)
         or (cfg.adapter == "qlora" and cfg.load_in_4bit)
     ):
-        logging.info("converting PEFT model w/ prepare_model_for_int8_training")
-        model = prepare_model_for_int8_training(model)
+        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)
 
     model, lora_config = load_adapter(model, cfg, adapter)
 
@@ -262,7 +350,7 @@ def load_model(
 
     if cfg.gptq:
         # Scales to half
-        logging.info("Fitting 4bit scales and zeros to half")
+        LOG.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)
@@ -288,9 +376,12 @@ def load_model(
         if param.requires_grad:
             requires_grad.append(f"{name}: {param.requires_grad}")
     if len(requires_grad) == 0:
-        logging.warning("there are no parameters that require gradient updates")
+        LOG.warning("there are no parameters that require gradient updates")
     model.config.use_cache = False
 
+    if cfg.flash_optimum:
+        model = BetterTransformer.transform(model)
+
     # TODO resume_from_checkpoint handling
     return model, lora_config
 
@@ -319,11 +410,10 @@ def load_llama_adapter(model, cfg):
     )
 
     if cfg.lora_model_dir:
-        logging.info("Loading pretained LORA")
+        LOG.info("Loading pretained LORA")
         model = PeftModel.from_pretrained(
             model,
             cfg.lora_model_dir,
-            device_map=cfg.device_map,
             torch_dtype=torch.float16,
         )
     else:
@@ -367,7 +457,7 @@ def load_lora(model, cfg):
             bits = 8
 
         linear_names = find_all_linear_names(bits, model)
-        logging.info(f"found linear modules: {repr(linear_names)}")
+        LOG.info(f"found linear modules: {repr(linear_names)}")
         lora_target_modules = list(set(lora_target_modules + linear_names))
 
     lora_config = LoraConfig(
@@ -385,8 +475,7 @@ def load_lora(model, cfg):
         model = PeftModel.from_pretrained(
             model,
             cfg.lora_model_dir,
-            device_map=cfg.device_map,
-            # torch_dtype=torch.float16,
+            is_trainable=not cfg.inference,
         )
     else:
         model = get_peft_model(model, lora_config)

src/axolotl/utils/schedulers.py

@@ -1,6 +1,9 @@
 """Module for custom LRScheduler class"""
+import math
+from functools import partial
 
-from torch.optim.lr_scheduler import LRScheduler
+from torch.optim import Optimizer
+from torch.optim.lr_scheduler import LambdaLR, LRScheduler
 
 
 class InterpolatingLogScheduler(LRScheduler):
@@ -42,3 +45,58 @@ 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

@@ -5,6 +5,8 @@ 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
@@ -32,5 +34,7 @@ def check_example_labels(example, tokenizer):
         )
         colored_tokens.append(colored_token)
 
-    logging.info(" ".join(colored_tokens))
-    logging.info("\n\n\n")
+    LOG.info(" ".join(colored_tokens))
+    LOG.info("\n\n\n")
+
+    return " ".join(colored_tokens)

src/axolotl/utils/trainer.py

@@ -1,9 +1,11 @@
 """Module containing the Trainer class and related functions"""
 
 import importlib
+import logging
 import math
 import os
 import sys
+from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Optional
 
@@ -12,14 +14,70 @@ import torch.cuda
 import transformers
 from torch import nn
 from torch.optim.lr_scheduler import OneCycleLR
-from transformers import EarlyStoppingCallback, Trainer
+from transformers import EarlyStoppingCallback, Trainer, TrainingArguments
 from transformers.trainer_pt_utils import get_parameter_names
 
-from axolotl.utils.callbacks import SavePeftModelCallback
-from axolotl.utils.schedulers import InterpolatingLogScheduler
+from axolotl.utils.callbacks import (
+    SaveBetterTransformerModelCallback,
+    SavePeftModelCallback,
+)
+from axolotl.utils.schedulers import (
+    InterpolatingLogScheduler,
+    get_cosine_schedule_with_quadratic_warmup,
+)
+
+LOG = logging.getLogger("axolotl")
 
 
-class OneCycleLRSchedulerTrainer(Trainer):
+@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."},
+    )
+
+
+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
+
+
+class OneCycleLRSchedulerTrainer(AxolotlTrainer):
     """
     Trainer subclass that uses the OneCycleLR scheduler
     """
@@ -62,8 +120,6 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
         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":
@@ -74,6 +130,10 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
     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 (
@@ -97,6 +157,9 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
         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"
@@ -109,7 +172,24 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
             # TODO search Path("./") for one
             training_arguments_kwargs["deepspeed"] = "./ds_config.json"
 
-    training_args = transformers.TrainingArguments(
+    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
+
+    training_args = AxolotlTrainingArguments(  # pylint: disable=unexpected-keyword-arg
         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
@@ -119,16 +199,16 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
         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 save_steps else "epoch",
-        eval_steps=eval_steps if cfg.val_set_size > 0 else None,
-        save_steps=save_steps,
+        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,
         output_dir=cfg.output_dir,
         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 save_steps
-            and save_steps % eval_steps == 0
+            and cfg.save_steps
+            and cfg.save_steps % cfg.eval_steps == 0
             and cfg.load_in_8bit is not True
         )
         or False,
@@ -225,6 +305,9 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
     ]:  # only save in rank 0
         callbacks.append(SavePeftModelCallback)
 
+    if hasattr(model, "use_bettertransformer") and model.use_bettertransformer is True:
+        callbacks.append(SaveBetterTransformerModelCallback)
+
     data_collator_kwargs = {
         "padding": True,
     }
@@ -233,10 +316,30 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
     else:
         data_collator_kwargs["pad_to_multiple_of"] = 8
 
+    if cfg.is_llama_derived_model and cfg.landmark_attention:
+        from functools import partial
+
+        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,
+            )
+
     trainer_cls = (
         OneCycleLRSchedulerTrainer
         if cfg.lr_scheduler == "one_cycle" and (cfg.fsdp or cfg.adapter == "qlora")
-        else transformers.Trainer
+        else AxolotlTrainer
     )
     trainer = trainer_cls(
         model=model,

src/axolotl/utils/validation.py

@@ -2,8 +2,22 @@
 
 import logging
 
+import torch
+
+LOG = logging.getLogger("axolotl")
+
 
 def validate_config(cfg):
+    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"
@@ -32,10 +46,10 @@ 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":
-        logging.warning("We recommend setting `load_in_8bit: true` for LORA finetuning")
+        LOG.warning("We recommend setting `load_in_8bit: true` for LORA finetuning")
 
     if cfg.trust_remote_code:
-        logging.warning(
+        LOG.warning(
             "`trust_remote_code` is set to true. Please make sure that you reviewed the remote code/model."
         )
 
@@ -44,7 +58,53 @@ 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")
+        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(
+                "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")
+            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."
+        )
+
     # TODO
     # MPT 7b
     # https://github.com/facebookresearch/bitsandbytes/issues/25
-    # no 8bit adamw w bf16
+    # no 8bit adaAmw w bf16
+
+    # GPT-NeoX
+    # evals broken when extending context len
+    # File "/root/miniconda3/envs/py3.9/lib/python3.9/site-packages/transformers/models/gpt_neox/modeling_gpt_neox.py", line 162, in forward                        attn_output, attn_weights = self._attn(query, key, value, attention_mask, head_mask)
+    # File "/root/miniconda3/envs/py3.9/lib/python3.9/site-packages/optimum/bettertransformer/models/attention.py", line 74, in gpt2_wrapped_scaled_dot_product
+    # attention_mask = causal_mask + attention_mask
+    # RuntimeError: The size of tensor a (2048) must match the size of tensor b (8132) at non-singleton dimension 3

src/axolotl/utils/wandb.py

@@ -15,3 +15,5 @@ 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/fixtures/alpaca/alpaca.json

@@ -0,0 +1,12 @@
+[
+  {
+    "instruction": "You will be given a series of words. Output these words in reverse order, with each word on its own line.",
+    "input": "Words: ['Hello', 'world'].",
+    "output": "['world', 'Hello']"
+  },
+  {
+    "instruction": "In this task, you're given a short description of an event. Your job is to order the steps involved in the event from first to last. Note that there may be multiple correct answers for each event.",
+    "input": "Description: A man walks into a bar and orders a drink. He pays for his drink and leaves the bar.",
+    "output": "1. The man walks into the bar.\n2. He orders a drink.\n3. He pays for his drink.\n4. He leaves the bar."
+  }
+]

tests/test_packed_dataset.py

@@ -0,0 +1,65 @@
+"""Module for testing dataset sequence packing"""
+
+import unittest
+from pathlib import Path
+
+from datasets import Dataset, load_dataset
+from transformers import AutoTokenizer
+
+from axolotl.datasets import ConstantLengthDataset, TokenizedPromptDataset
+from axolotl.prompt_tokenizers import AlpacaPromptTokenizingStrategy
+from axolotl.prompters import AlpacaPrompter
+
+
+class TestPacking(unittest.TestCase):
+    """
+    Test class for packing dataset sequences
+    """
+
+    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_resets_attention(self):
+        prompter = AlpacaPrompter("chat")
+        strat = AlpacaPromptTokenizingStrategy(
+            prompter,
+            self.tokenizer,
+            False,
+            2048,
+        )
+        dateset = load_dataset(
+            "json",
+            data_files=str(Path(__file__).parent / "fixtures/alpaca/alpaca.json"),
+        )["train"]
+        dataset = Dataset.from_list(list(TokenizedPromptDataset(strat, dateset)))
+
+        constant_len_dataset = ConstantLengthDataset(
+            self.tokenizer,
+            [dataset],
+            seq_length=2048,
+        )
+        packed_dataset = Dataset.from_list(list(constant_len_dataset))
+        example = packed_dataset[0]
+        next_bos_index = (
+            example["input_ids"][1:].index(self.tokenizer.bos_token_id) + 1
+        )  # add one since we sliced
+
+        # first example doesn't have mask reset
+        assert example["input_ids"][0] == self.tokenizer.bos_token_id
+        assert example["attention_mask"][0] == 1
+
+        # but subsequent one does
+        assert example["input_ids"][next_bos_index] == self.tokenizer.bos_token_id
+        assert example["attention_mask"][next_bos_index] == 0
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_prompt_tokenizers.py

@@ -6,10 +6,18 @@ from pathlib import Path
 
 from transformers import AutoTokenizer
 
-from axolotl.prompt_tokenizers import ShareGPTPromptTokenizingStrategy
-from axolotl.prompters import ShareGPTPrompter
+from axolotl.prompt_strategies.alpaca_chat import NoSystemPrompter
+from axolotl.prompt_strategies.alpaca_w_system import (
+    InstructionWSystemPromptTokenizingStrategy,
+    SystemDataPrompter,
+)
+from axolotl.prompt_tokenizers import (
+    AlpacaPromptTokenizingStrategy,
+    ShareGPTPromptTokenizingStrategy,
+)
+from axolotl.prompters import AlpacaPrompter, PromptStyle, ShareGPTPrompter
 
-logging.basicConfig(level="INFO")
+LOG = logging.getLogger("axolotl")
 
 
 class TestPromptTokenizationStrategies(unittest.TestCase):
@@ -18,6 +26,7 @@ class TestPromptTokenizationStrategies(unittest.TestCase):
     """
 
     def setUp(self) -> None:
+        # pylint: disable=duplicate-code
         self.tokenizer = AutoTokenizer.from_pretrained("huggyllama/llama-7b")
         self.tokenizer.add_special_tokens(
             {
@@ -28,7 +37,6 @@ 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:
@@ -52,6 +60,80 @@ 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"][0:4] == [1, 835, 2184, 29901]  # "<s>### System:"
+        assert example["input_ids"][5:7] == [1509, 20118]  # "use cot"
+        assert example["input_ids"][9] == 11889  # USER
+
 
 if __name__ == "__main__":
     unittest.main()

tests/test_prompters.py

@@ -2,7 +2,13 @@
 
 import unittest
 
-from axolotl.prompters import AlpacaPrompter, PromptStyle
+from axolotl.prompt_strategies.alpaca_w_system import SystemDataPrompter
+from axolotl.prompters import (
+    AlpacaPrompter,
+    MultipleChoiceExplainPrompter,
+    PromptStyle,
+    UnpromptedPrompter,
+)
 
 
 class AlpacaPrompterTest(unittest.TestCase):
@@ -55,3 +61,64 @@ 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

@@ -0,0 +1,31 @@
+"""
+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

@@ -1,6 +1,8 @@
 """Module for testing the validation module"""
 
+import logging
 import unittest
+from typing import Optional
 
 import pytest
 
@@ -13,6 +15,12 @@ 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(
             {
@@ -23,6 +31,17 @@ 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(
             {
@@ -117,3 +136,180 @@ class ValidationTest(unittest.TestCase):
             }
         )
         validate_config(cfg)
+
+    def test_gradient_accumulations_or_batch_size(self):
+        cfg = DictDefault(
+            {
+                "gradient_accumulation_steps": 1,
+                "batch_size": 1,
+            }
+        )
+
+        with pytest.raises(
+            ValueError, match=r".*gradient_accumulation_steps or batch_size.*"
+        ):
+            validate_config(cfg)
+
+        cfg = DictDefault(
+            {
+                "batch_size": 1,
+            }
+        )
+
+        validate_config(cfg)
+
+        cfg = DictDefault(
+            {
+                "gradient_accumulation_steps": 1,
+            }
+        )
+
+        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)