chore: lint

* support for custom lr groups for non-embedding modules

invert name check for group modules
include lr_groups in training args
additional conditional for creating optimizer
fix regular params as w weight decay
fix lookup and add docs

* address pr feedback

.github/workflows/lint.yml

@@ -1,6 +1,7 @@
 name: lint
 on:
   # check on PRs, and manual triggers
+  merge_group:
   pull_request:
       paths:
        - '**.py'

.github/workflows/main.yml

@@ -25,7 +25,6 @@ jobs:
             python_version: "3.11"
             pytorch: 2.3.1
             axolotl_extras: mamba-ssm
-            is_latest: true
           - cuda: 124
             cuda_version: 12.4.1
             python_version: "3.11"
@@ -36,6 +35,7 @@ jobs:
             python_version: "3.11"
             pytorch: 2.5.1
             axolotl_extras:
+            is_latest: true
     runs-on: axolotl-gpu-runner
     steps:
       - name: Checkout
@@ -92,7 +92,6 @@ jobs:
             python_version: "3.11"
             pytorch: 2.3.1
             axolotl_extras:
-            is_latest: true
           - cuda: 124
             cuda_version: 12.4.1
             python_version: "3.11"
@@ -103,6 +102,7 @@ jobs:
             python_version: "3.11"
             pytorch: 2.5.1
             axolotl_extras:
+            is_latest: true
     runs-on: axolotl-gpu-runner
     steps:
       - name: Checkout

.github/workflows/multi-gpu-e2e.yml

@@ -52,7 +52,7 @@ jobs:
       - name: Install Modal
         run: |
           python -m pip install --upgrade pip
-          pip install modal==0.63.64 jinja2
+          pip install modal==0.71.8 jinja2
       - name: Update env vars
         run: |
           echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV

.github/workflows/tests-nightly.yml

@@ -129,7 +129,7 @@ jobs:
       - name: Install Modal
         run: |
           python -m pip install --upgrade pip
-          pip install modal==0.63.64 jinja2
+          pip install modal==0.71.8 jinja2
       - name: Update env vars
         run: |
           echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV

.github/workflows/tests.yml

@@ -1,6 +1,7 @@
 name: Tests
 on:
   # check on push/merge to main, PRs, and manual triggers
+  merge_group:
   push:
     branches:
       - "main"
@@ -60,6 +61,15 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v4
 
+      - name: Restore HF cache
+        id: hf-cache-restore
+        uses: actions/cache/restore@v4
+        with:
+          path: |
+            /home/runner/.cache/huggingface/hub/datasets--*
+            /home/runner/.cache/huggingface/hub/models--*
+          key: ${{ runner.os }}-hf-hub-cache-${{ hashFiles('**/conftest.py') }}
+
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
@@ -100,6 +110,15 @@ jobs:
         run: |
           find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
 
+      - name: Save HF cache
+        id: hf-cache
+        uses: actions/cache/save@v4
+        with:
+          path: |
+            /home/runner/.cache/huggingface/hub/datasets--*
+            /home/runner/.cache/huggingface/hub/models--*
+          key: ${{ steps.hf-cache-restore.outputs.cache-primary-key }}
+
   pytest-sdist:
     name: PyTest from Source Dist
     runs-on: ubuntu-latest
@@ -115,6 +134,15 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v4
 
+      - name: Restore HF cache
+        id: hf-cache-restore
+        uses: actions/cache/restore@v4
+        with:
+          path: |
+            /home/runner/.cache/huggingface/hub/datasets--*
+            /home/runner/.cache/huggingface/hub/models--*
+          key: ${{ runner.os }}-hf-hub-cache-${{ hashFiles('**/conftest.py') }}
+
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
@@ -156,6 +184,15 @@ jobs:
         run: |
           find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
 
+      - name: Save HF cache
+        id: hf-cache
+        uses: actions/cache/save@v4
+        with:
+          path: |
+            /home/runner/.cache/huggingface/hub/datasets--*
+            /home/runner/.cache/huggingface/hub/models--*
+          key: ${{ steps.hf-cache-restore.outputs.cache-primary-key }}
+
   docker-e2e-tests-1st:
     if: ${{ ! contains(github.event.commits[0].message, '[skip e2e]') && github.repository_owner == 'axolotl-ai-cloud' }}
     # this job needs to be run on self-hosted GPU runners...
@@ -183,7 +220,7 @@ jobs:
       - name: Install Modal
         run: |
           python -m pip install --upgrade pip
-          pip install modal==0.63.64 jinja2
+          pip install modal==0.71.8 jinja2
       - name: Update env vars
         run: |
           echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
@@ -229,7 +266,7 @@ jobs:
       - name: Install Modal
         run: |
           python -m pip install --upgrade pip
-          pip install modal==0.63.64 jinja2
+          pip install modal==0.71.8 jinja2
       - name: Update env vars
         run: |
           echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV

.gitignore

@@ -1,6 +1,7 @@
 **/axolotl.egg-info
 configs
 last_run_prepared/
+outputs
 .vscode
 _site/
 

.pre-commit-config.yaml

@@ -23,7 +23,7 @@ repos:
     hooks:
     - id: flake8
 -   repo: https://github.com/PyCQA/pylint
-    rev: v2.17.4
+    rev: v3.3.0
     hooks:
     - id: pylint
 -   repo: https://github.com/pre-commit/mirrors-mypy

.pylintrc

@@ -1,5 +1,5 @@
 [MASTER]
-init-hook="from pylint.config import find_pylintrc; import os, sys; sys.path.append(os.path.dirname(find_pylintrc()))"
+init-hook="from pylint.config import find_default_config_files; import sys; sys.path.append(next(find_default_config_files()).parent.as_posix())"
 
 [TYPECHECK]
 
@@ -12,3 +12,4 @@ generated-members=numpy.*, torch.*
 disable=missing-function-docstring, line-too-long, import-error,
     too-many-arguments, too-many-locals, too-many-statements, too-many-branches, too-few-public-methods,
     too-many-instance-attributes, fixme, import-outside-toplevel, logging-fstring-interpolation,
+    too-many-positional-arguments, possibly-used-before-assignment

README.md

@@ -519,8 +519,8 @@ See [examples](examples) for quick start. It is recommended to duplicate and mod
       train_on_split: validation
 
       # loading from s3 or gcs
-      # s3 creds will be loaded from the system default and gcs only supports public access
-    - path: s3://path_to_ds # Accepts folder with arrow/parquet or file path like above. Supports s3, gcs.
+      # s3 creds will be loaded from the system default / gcs will attempt to load from gcloud creds, google metadata service, or anon
+    - path: s3://path_to_ds # Accepts folder with arrow/parquet or file path like above
       ...
 
       # Loading Data From a Public URL

cicd/Dockerfile.jinja

@@ -8,6 +8,7 @@ ENV PYTORCH_VERSION="{{ PYTORCH_VERSION }}"
 ENV GITHUB_REF="{{ GITHUB_REF }}"
 ENV GITHUB_SHA="{{ GITHUB_SHA }}"
 ENV NIGHTLY_BUILD="{{ NIGHTLY_BUILD }}"
+ENV HF_HOME="{{ HF_HOME }}"
 
 RUN apt-get update && \
     apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev

cicd/cicd.sh

@@ -5,6 +5,7 @@ python -c "import torch; assert '$PYTORCH_VERSION' in torch.__version__"
 
 pytest -v --durations=10 -n8 --ignore=tests/e2e/ --ignore=tests/patched/ /workspace/axolotl/tests/
 # pytest -v --durations=10 -n8 --dist loadfile /workspace/axolotl/tests/patched/
-pytest -v --durations=10 -n1 --dist loadfile /workspace/axolotl/tests/e2e/patched/
-pytest -v --durations=10 -n1 --dist loadfile /workspace/axolotl/tests/e2e/integrations/
-pytest -v --durations=10 --ignore=tests/e2e/patched/ --ignore=tests/e2e/multigpu/ --ignore=tests/e2e/integrations/ /workspace/axolotl/tests/e2e/
+pytest -v --durations=10 /workspace/axolotl/tests/e2e/patched/
+pytest -v --durations=10 -n1 /workspace/axolotl/tests/e2e/solo/
+pytest -v --durations=10 /workspace/axolotl/tests/e2e/integrations/
+pytest -v --durations=10 --ignore=tests/e2e/solo/ --ignore=tests/e2e/patched/ --ignore=tests/e2e/multigpu/ --ignore=tests/e2e/integrations/ /workspace/axolotl/tests/e2e/

cicd/multigpu.py

@@ -28,6 +28,7 @@ df_args = {
     "CUDA": os.environ.get("CUDA", "121"),
     "GITHUB_REF": os.environ.get("GITHUB_REF", "refs/heads/main"),
     "GITHUB_SHA": os.environ.get("GITHUB_SHA", ""),
+    "HF_HOME": "/workspace/data/huggingface-cache/hub",
 }
 
 dockerfile_contents = df_template.render(**df_args)
@@ -48,6 +49,12 @@ cicd_image = (
 
 app = App("Axolotl CI/CD", secrets=[])
 
+hf_cache_volume = modal.Volume.from_name(
+    "axolotl-ci-hf-hub-cache", create_if_missing=True
+)
+VOLUME_CONFIG = {
+    "/workspace/data/huggingface-cache/hub": hf_cache_volume,
+}
 
 N_GPUS = int(os.environ.get("N_GPUS", 2))
 GPU_CONFIG = modal.gpu.H100(count=N_GPUS)
@@ -67,6 +74,7 @@ def run_cmd(cmd: str, run_folder: str):
     timeout=60 * 60,
     cpu=8.0,
     memory=131072 * N_GPUS,
+    volumes=VOLUME_CONFIG,
 )
 def cicd_pytest():
     run_cmd("./cicd/multigpu.sh", "/workspace/axolotl")

cicd/tests.py

@@ -29,6 +29,7 @@ df_args = {
     "GITHUB_REF": os.environ.get("GITHUB_REF", "refs/heads/main"),
     "GITHUB_SHA": os.environ.get("GITHUB_SHA", ""),
     "NIGHTLY_BUILD": os.environ.get("NIGHTLY_BUILD", ""),
+    "HF_HOME": "/workspace/data/huggingface-cache/hub",
 }
 
 dockerfile_contents = df_template.render(**df_args)
@@ -50,6 +51,12 @@ cicd_image = (
 
 app = App("Axolotl CI/CD", secrets=[])
 
+hf_cache_volume = modal.Volume.from_name(
+    "axolotl-ci-hf-hub-cache", create_if_missing=True
+)
+VOLUME_CONFIG = {
+    "/workspace/data/huggingface-cache/hub": hf_cache_volume,
+}
 
 N_GPUS = int(os.environ.get("N_GPUS", 1))
 GPU_CONFIG = modal.gpu.A10G(count=N_GPUS)
@@ -69,6 +76,7 @@ def run_cmd(cmd: str, run_folder: str):
     timeout=60 * 60,
     cpu=8.0,
     memory=131072,
+    volumes=VOLUME_CONFIG,
 )
 def cicd_pytest():
     run_cmd("./cicd/cicd.sh", "/workspace/axolotl")

deepspeed_configs/zero1_torch_compile.json

@@ -0,0 +1,27 @@
+{
+  "zero_optimization": {
+    "stage": 1,
+    "overlap_comm": true
+  },
+  "bf16": {
+    "enabled": "auto"
+  },
+  "fp16": {
+    "enabled": "auto",
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 32,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },
+  "compile": {
+    "disable": false,
+    "backend": "inductor"
+  },
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": "auto",
+  "wall_clock_breakdown": false
+}

docker/Dockerfile-cloud

@@ -20,7 +20,8 @@ RUN apt install --yes --no-install-recommends openssh-server tmux && \
     printf "\n[[ -z \"\$TMUX\"  ]] && { tmux attach-session -t ssh_tmux || tmux new-session -s ssh_tmux; exit; }\n" >> ~/.bashrc && \
     printf "[ ! -z \"\$TERM\" -a -r /etc/motd ] && cat /etc/motd\n" >> ~/.bashrc && \
     chmod +x /workspace/axolotl/scripts/cloud-entrypoint.sh && \
-    chmod +x /root/cloud-entrypoint.sh
+    chmod +x /root/cloud-entrypoint.sh && \
+    echo 'set-option -g history-limit 5000' >> ~/.tmux.conf
 
 ENTRYPOINT ["/root/cloud-entrypoint.sh"]
 CMD ["sleep", "infinity"]

docs/config.qmd

@@ -127,34 +127,40 @@ datasets:
     # - tokenizer_default_fallback_*: where * is the name of the chat template to fallback to if the tokenizer does not have a chat template else default to tokenizer. E.g. tokenizer_default_fallback_chatml.
     # - jinja: Uses a custom jinja template for the chat template. The custom jinja template should be provided in the chat_template_jinja field.
     chat_template: tokenizer_default
-    # Custom jinja template for chat template. This will be only used if `chat_template` is set to `jinja` or empty (in which case chat_template is automatically set to `jinja`).
+
+    # Custom jinja chat template. Used only if `chat_template: jinja` or empty.
     chat_template_jinja:
-    # The key in the data example that contains the messages. Default is "messages".
+
+    # Key containing the messages (default: "messages")
     field_messages: messages
-    # The key in the message turn that contains the role. Default is "role".
+    # Key for role in each message (default: "role")
     message_field_role: role
-    # The key in the message turn that contains the content. Default is "content".
+    # Key for content in each message (default:  "content")
     message_field_content: content
-    # Optional[Dict[str, List]]. Roles mapping for the messages.
+
+    # Optional[Dict[str, List]]. Roles mapping in the messages. The default is:
     roles:
       user: ["human", "user"]
-      assistant: ["gpt", "assistant", "ai"]
+      assistant: ["gpt", "assistant"]
       system: ["system"]
+      tool: ["tool"]
 
-    ## NOTE: Leaving the below empty will default to using the simple legacy tokenization strategy where only last message is trained on.
+    # IMPORTANT: The following fields determine which parts of the conversation to train on.
+    # Priority order: message_field_training > message_field_training_detail > train_on_inputs or role in roles_to_train
+    # See examples at `docs/dataset-formats/conversation.qmd`
+    # Note: If the below 4 fields are empty, defaults to training only on the last message.
 
     # Optional[List[str]]. Roles to train on. The tokens from these roles will be considered for the loss.
-    roles_to_train: ["gpt", "assistant"]
+    roles_to_train: ["assistant"]  # default
     # Optional[str]. Which EOS tokens to train on in the conversation. Possible values are:
     # - all: train on all EOS tokens
-    # - turn: train on the EOS token at the end of each trainable turn
+    # - turn (default): train on the EOS token at the end of each trainable turn
     # - last: train on the last EOS token in the conversation
     train_on_eos: last
     # The key in the message turn that indicates via boolean whether tokens of a turn should be considered for training. Useful to selectively train on certain turns besides the `roles_to_train`.
     message_field_training: training
     # The key in the message turn that contains the training details. Useful to selectively train on certain tokens in a turn.
     # The value of the key is a List[Dict] containing `begin_offset` (start character index in content), `end_offset` (end character index in content), and `train` (boolean whether to train).
-    # See example at `docs/dataset-formats/conversation.qmd`
     message_field_training_detail: train_detail
 
 
@@ -238,6 +244,11 @@ total_num_tokens:
 sample_packing_group_size: 100000
 # The number of samples which can be packed into one sequence. Increase if using a large sequence_len with many short samples.
 sample_packing_bin_size: 200
+# whether to concatenate samples during pretraining
+pretraining_sample_concatenation:
+
+# Use batch flattening for speedups when not using sample_packing
+batch_flattening:
 
 # Passed through to transformers when loading the model when launched without accelerate
 # Use `sequential` when training w/ model parallelism to limit memory
@@ -331,7 +342,8 @@ comet_experiment_config: # Dictionary for additional configuration settings, see
 output_dir: ./completed-model
 
 # Whether to use torch.compile and which backend to use
-torch_compile:  # bool
+# setting to `auto` will enable torch compile when torch>=2.5.1
+torch_compile:  # Optional[Union[Literal["auto"], bool]]
 torch_compile_backend:  # Optional[str]
 
 # Training hyperparameters
@@ -348,10 +360,11 @@ warmup_ratio: 0.05  # cannot use with warmup_steps
 learning_rate: 0.00003
 lr_quadratic_warmup:
 logging_steps:
-eval_steps: # Leave empty to eval at each epoch, integers for every N steps. decimal for fraction of total steps
+eval_steps: # Leave empty to eval at each epoch, integer for every N steps. float for fraction of total steps
 evals_per_epoch: # number of times per epoch to run evals, mutually exclusive with eval_steps
-save_strategy: # Set to `"no"` to skip checkpoint saves
-save_steps: # Leave empty to save at each epoch
+eval_strategy: # Set to `"no"` to skip evaluation, `"epoch"` at end of each epoch, leave empty to infer from `eval_steps`.
+save_strategy: # Set to `"no"` to skip checkpoint saves, `"epoch"` at end of each epoch, `"best"` when better result is achieved, leave empty to infer from `save_steps`.
+save_steps: # Leave empty to save at each epoch, integer for every N steps. float for fraction of total steps
 saves_per_epoch: # number of times per epoch to save a checkpoint, mutually exclusive with save_steps
 save_total_limit: # Checkpoints saved at a time
 # Maximum number of iterations to train for. It precedes num_epochs which means that
@@ -363,6 +376,10 @@ eval_table_size: # Approximate number of predictions sent to wandb depending on
 eval_max_new_tokens: # Total number of tokens generated for predictions sent to wandb. Default is 128
 eval_causal_lm_metrics: # HF evaluate metrics used during evaluation. Default is ["sacrebleu", "comet", "ter", "chrf", "perplexity"]
 
+profiler_steps: # enable the pytorch profiler to capture the first N steps of training to the output_dir.
+                # see https://pytorch.org/blog/understanding-gpu-memory-1/ for more information
+                # snapshots can be visualized @ https://pytorch.org/memory_viz
+
 loss_watchdog_threshold: # High loss value, indicating the learning has broken down (a good estimate is ~2 times the loss at the start of training)
 loss_watchdog_patience: # Number of high-loss steps in a row before the trainer aborts (default: 3)
 

docs/dataset-formats/conversation.qmd

@@ -68,6 +68,8 @@ We recommend checking the below examples for other usecases.
 datasets:
   - path: ...
     type: chat_template
+    roles_to_train:
+    train_on_eos:
 ```
 
 2. Using the `gemma` chat template to override the tokenizer_config.json's chat template on OpenAI messages format, training on all assistant messages.
@@ -77,7 +79,7 @@ chat_template: gemma # this overwrites the tokenizer's chat_template
 datasets:
   - path: ...
     type: chat_template
-    roles_to_train: ["assistant"]
+    roles_to_train: ["assistant"]  # default value
 ```
 
 3. Using the tokenizer_config.json's chat template or `chatml` as fallback if the former's chat template does not exist, on OpenAI messages format, training on all assistant messages.
@@ -87,7 +89,6 @@ chat_template: tokenizer_default_fallback_chatml # this overwrites the tokenizer
 datasets:
   - path: ...
     type: chat_template
-    roles_to_train: ["assistant"]
 ```
 
 4. Using a custom jinja template on OpenAI messages format, training on all assistant messages.
@@ -99,7 +100,6 @@ chat_template_jinja: "{{ bos_token }}{% for message in messages %}{% if (message
 datasets:
   - path: ...
     type: chat_template
-    roles_to_train: ["assistant"]
 ```
 
 5. (Advanced) Using fine-grained control over tokens and turns to train in a conversation

docs/dataset-formats/pretraining.qmd

@@ -19,7 +19,14 @@ For pretraining, there is no prompt template or roles.  The only required field
 Axolotl usually loads the entire dataset into memory. This will be challenging for large datasets. Use the following config to enable streaming:
 
 ```{.yaml filename="config.yaml"}
-pretraining_dataset: # hf path only
+pretraining_dataset:
+  - name:
+    path:
+    split:
+    text_column: # column in dataset with the data, usually `text`
+    type: pretrain
+    trust_remote_code:
+    skip: # number of rows of data to skip over from the beginning
 ...
 ```
 

docs/lr_groups.qmd

@@ -0,0 +1,29 @@
+---
+title: Learning Rate Groups
+description: "Setting different learning rates by module name"
+---
+
+## Background
+
+Inspired by LoRA+, Axolotl allows practitioners to specify separate learning rates for each module or groups of
+modules in a model.
+
+## Example
+
+```yaml
+lr_groups:
+  - name: o_proj
+    modules:
+      - self_attn.o_proj.weight
+    lr: 1e-6
+  - name: q_proj
+    modules:
+      - model.layers.2.self_attn.q_proj.weight
+    lr: 1e-5
+
+learning_rate: 2e-5
+```
+
+In this example, we have a default learning rate of 2e-5 across the entire model, but we have a separate learning rate
+of 1e-6 for all the self attention `o_proj` modules across all layers, and a learning are of 1e-5 to the 3rd layer's
+self attention `q_proj` module.

examples/cerebras/btlm-ft.yml

@@ -1,6 +1,10 @@
 base_model: cerebras/btlm-3b-8k-base
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: GPT2Tokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 tokenizer_use_fast: true
 tokenizer_legacy: true

examples/cerebras/qlora.yml

@@ -1,4 +1,7 @@
 base_model: cerebras/Cerebras-GPT-1.3B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 load_in_8bit: false
 load_in_4bit: true
 strict: false

examples/code-llama/13b/lora.yml

@@ -1,6 +1,9 @@
 base_model: codellama/CodeLlama-13b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: CodeLlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/code-llama/13b/qlora.yml

@@ -1,6 +1,9 @@
 base_model: codellama/CodeLlama-13b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: CodeLlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/code-llama/34b/lora.yml

@@ -1,6 +1,9 @@
 base_model: codellama/CodeLlama-34b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: CodeLlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/code-llama/34b/qlora.yml

@@ -1,6 +1,9 @@
 base_model: codellama/CodeLlama-34b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: CodeLlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/code-llama/7b/lora.yml

@@ -1,6 +1,9 @@
 base_model: codellama/CodeLlama-7b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: CodeLlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/code-llama/7b/qlora.yml

@@ -1,6 +1,9 @@
 base_model: codellama/CodeLlama-7b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: CodeLlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/dbrx/16bit-lora.yaml

@@ -1,4 +1,7 @@
 base_model: LnL-AI/dbrx-base-converted-v2
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/dbrx/8bit-lora.yaml

@@ -1,4 +1,7 @@
 base_model: LnL-AI/dbrx-base-converted-v2
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: true

examples/dbrx/fft-ds-zero3.yaml

@@ -1,4 +1,7 @@
 base_model: LnL-AI/dbrx-base-converted-v2
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/deepseek-v2/fft-fsdp-16b.yaml

@@ -1,4 +1,6 @@
 base_model: deepseek-ai/DeepSeek-V2-Lite
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 trust_remote_code: true
 
 load_in_8bit: false

examples/deepseek-v2/qlora-fsdp-2_5.yaml

@@ -1,4 +1,7 @@
 base_model: axolotl-quants/DeepSeek-V2.5-bnb-nf4-bf16
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

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

@@ -1,7 +1,12 @@
 base_model: tiiuae/falcon-7b
-trust_remote_code: true
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+# required by falcon custom model code: https://huggingface.co/tiiuae/falcon-7b/tree/main
+trust_remote_code: true
 
 load_in_8bit: true
 load_in_4bit: false

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

@@ -1,10 +1,15 @@
 # 1b: tiiuae/falcon-rw-1b
 # 40b: tiiuae/falcon-40b
 base_model: tiiuae/falcon-7b
-# required by falcon custom model code: https://huggingface.co/tiiuae/falcon-7b/tree/main
-trust_remote_code: true
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+# required by falcon custom model code: https://huggingface.co/tiiuae/falcon-7b/tree/main
+trust_remote_code: true
+
 
 load_in_8bit: false
 # enable 4bit for QLoRA

examples/falcon/config-7b.yml

@@ -1,7 +1,12 @@
 base_model: tiiuae/falcon-7b
-trust_remote_code: true
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+# required by falcon custom model code: https://huggingface.co/tiiuae/falcon-7b/tree/main
+trust_remote_code: true
 
 load_in_8bit: false
 load_in_4bit: false

examples/gemma/qlora.yml

@@ -1,7 +1,10 @@
 # use google/gemma-7b if you have access
 base_model: mhenrichsen/gemma-7b
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/gemma2/qlora.yml

@@ -1,6 +1,9 @@
 base_model: google/gemma-2-9b
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/gemma2/reward-model.yaml

@@ -1,6 +1,9 @@
 base_model: google/gemma-2-2b
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForSequenceClassification
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/gptj/qlora.yml

@@ -1,4 +1,7 @@
 base_model: EleutherAI/gpt-j-6b
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 load_in_8bit: false
 load_in_4bit: true
 strict: false

examples/jamba/qlora.yaml

@@ -1,4 +1,7 @@
 base_model: ai21labs/Jamba-v0.1
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/jamba/qlora_deepspeed.yaml

@@ -1,4 +1,6 @@
 base_model: ai21labs/Jamba-v0.1
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 trust_remote_code: true
 
 load_in_8bit: false

examples/jamba/qlora_fsdp_large.yaml

@@ -1,5 +1,8 @@
 base_model: ai21labs/AI21-Jamba-1.5-Large
+# optionally might have model_type or tokenizer_type
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_4bit: true
 strict: false

examples/jeopardy-bot/config.yml

@@ -1,6 +1,10 @@
 base_model: huggyllama/llama-7b
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 load_in_8bit: false
 datasets:
   - path: openaccess-ai-collective/jeopardy

examples/llama-2/fft_optimized.yml

@@ -1,6 +1,9 @@
 base_model: NousResearch/Llama-2-7b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/llama-2/gptq-lora.yml

@@ -1,8 +1,13 @@
 base_model: TheBloke/Llama-2-7B-GPTQ
-gptq: true
-gptq_disable_exllama: true
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+gptq: true
+gptq_disable_exllama: true
+
 tokenizer_use_fast: true
 tokenizer_legacy: true
 load_in_8bit: false

examples/llama-2/lisa.yml

@@ -1,6 +1,9 @@
 base_model: NousResearch/Llama-2-7b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/llama-2/loftq.yml

@@ -1,6 +1,9 @@
 base_model: NousResearch/Llama-2-7b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/llama-2/lora.yml

@@ -1,6 +1,9 @@
 base_model: NousResearch/Llama-2-7b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/llama-2/qlora-fsdp.yml

@@ -1,6 +1,9 @@
 base_model: NousResearch/Llama-2-7b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/llama-2/qlora.yml

@@ -1,6 +1,9 @@
 base_model: NousResearch/Llama-2-7b-hf
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/llama-3-vision/lora-11b.yaml

@@ -1,5 +1,9 @@
 base_model: alpindale/Llama-3.2-11B-Vision-Instruct
+# optionally might have model_type or tokenizer_type or processor_type
 processor_type: AutoProcessor
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 strict: false
 
 # these 3 lines are needed for now to handle vision chat templates w images

examples/llama-3/fft-8b-liger-fsdp.yaml

@@ -1,4 +1,6 @@
 base_model: NousResearch/Meta-Llama-3.1-8B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 plugins:
   - axolotl.integrations.liger.LigerPlugin

examples/llama-3/fft-8b.yaml

@@ -1,4 +1,6 @@
 base_model: NousResearch/Meta-Llama-3.1-8B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/llama-3/instruct-dpo-lora-8b.yml

@@ -1,6 +1,9 @@
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/llama-3/instruct-lora-8b.yml

@@ -1,6 +1,9 @@
 base_model: NousResearch/Meta-Llama-3-8B-Instruct
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/llama-3/lora-1b-deduplicate-dpo.yml

@@ -1,6 +1,9 @@
 base_model: meta-llama/Llama-3.2-1B
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/llama-3/lora-1b-deduplicate-sft.yml

@@ -1,6 +1,9 @@
 base_model: meta-llama/Llama-3.2-1B
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/llama-3/lora-1b.yml

@@ -1,4 +1,6 @@
 base_model: NousResearch/Llama-3.2-1B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/llama-3/lora-8b.yml

@@ -1,6 +1,9 @@
 base_model: NousResearch/Meta-Llama-3-8B
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/llama-3/qlora-1b-kto.yaml

@@ -1,4 +1,6 @@
 base_model: meta-llama/Llama-3.2-1B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/llama-3/qlora-1b.yml

@@ -1,4 +1,6 @@
 base_model: NousResearch/Llama-3.2-1B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/llama-3/qlora-fsdp-405b.yaml

@@ -1,5 +1,8 @@
 base_model: hugging-quants/Meta-Llama-3.1-405B-BNB-NF4-BF16
+# optionally might have model_type or tokenizer_type
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_4bit: true
 strict: false

examples/llama-3/qlora-fsdp-70b.yaml

@@ -1,6 +1,9 @@
 base_model: casperhansen/llama-3-70b-fp16
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: AutoTokenizer  # PreTrainedTokenizerFast
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/llama-3/qlora.yml

@@ -1,6 +1,9 @@
 base_model: NousResearch/Meta-Llama-3-8B
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/mamba/config.yml

@@ -1,7 +1,10 @@
 base_model: state-spaces/mamba-2.8b
+# optionally might have model_type or tokenizer_type or tokenizer_config
 model_type: MambaLMHeadModel
 tokenizer_type: AutoTokenizer
 tokenizer_config: EleutherAI/gpt-neox-20b
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/mistral/bigstral-ds-zero3.yaml

@@ -1,6 +1,10 @@
 base_model: mistral-community/Mixtral-8x22B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/mistral/config.yml

@@ -1,6 +1,9 @@
 base_model: mistralai/Mistral-7B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: MistralForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/mistral/lora-mps.yml

@@ -1,6 +1,9 @@
 base_model: mistralai/Mistral-7B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: MistralForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/mistral/lora.yml

@@ -1,6 +1,9 @@
 base_model: mistralai/Mistral-7B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: MistralForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/mistral/mistral-dpo-qlora.yml

@@ -4,8 +4,11 @@
 #face problems with the special tokens.
 
 base_model: mistralai/Mistral-7B-Instruct-v0.2
+# optionally might have model_type or tokenizer_type
 model_type: MistralForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/mistral/mistral-qlora-fsdp.yml

@@ -1,6 +1,10 @@
 base_model: mistralai/Mixtral-8x7B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/mistral/mistral-qlora-orpo.yml

@@ -1,6 +1,9 @@
 base_model: mistralai/Mistral-7B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: MistralForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/mistral/mixtral-8x22b-qlora-fsdp.yml

@@ -1,6 +1,9 @@
 base_model: mistral-community/Mixtral-8x22B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/mistral/mixtral-qlora-fsdp.yml

@@ -1,6 +1,10 @@
 base_model: mistralai/Mixtral-8x7B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/mistral/mixtral.yml

@@ -1,6 +1,10 @@
 base_model: mistralai/Mixtral-8x7B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/mistral/mixtral_22.yml

@@ -1,6 +1,10 @@
 base_model: mistral-community/Mixtral-8x22B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/mistral/qlora.yml

@@ -1,6 +1,9 @@
 base_model: mistralai/Mistral-7B-v0.1
+# optionally might have model_type or tokenizer_type
 model_type: MistralForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/mpt-7b/config.yml

@@ -1,5 +1,9 @@
 base_model: mosaicml/mpt-7b
+# optionally might have model_type or tokenizer_type
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true  # required for mpt as their model class is not merged into transformers yet
 load_in_8bit: false
 datasets:

examples/openllama-3b/config.yml

@@ -1,6 +1,10 @@
 base_model: openlm-research/open_llama_3b_v2
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 load_in_8bit: false
 load_in_4bit: false
 strict: false

examples/openllama-3b/lora.yml

@@ -1,6 +1,10 @@
 base_model: openlm-research/open_llama_3b_v2
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 load_in_8bit: true
 load_in_4bit: false
 strict: false

examples/openllama-3b/qlora.yml

@@ -1,6 +1,10 @@
 base_model: openlm-research/open_llama_3b_v2
+# optionally might have model_type or tokenizer_type
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 load_in_8bit: false
 load_in_4bit: true
 strict: false

examples/phi/lora-3.5.yaml

@@ -1,6 +1,9 @@
 base_model: microsoft/Phi-3.5-mini-instruct
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: true
 load_in_4bit: false

examples/phi/phi-ft.yml

@@ -1,6 +1,9 @@
 base_model: microsoft/phi-1_5
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/phi/phi-qlora.yml

@@ -1,6 +1,9 @@
 base_model: microsoft/phi-1_5
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true

examples/phi/phi2-ft.yml

@@ -1,6 +1,9 @@
 base_model: microsoft/phi-2
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/phi/phi3-ft-fsdp.yml

@@ -1,6 +1,9 @@
 base_model: microsoft/Phi-3-mini-4k-instruct
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: false

examples/phi/phi3-ft.yml

@@ -1,7 +1,11 @@
 base_model: microsoft/Phi-3-mini-4k-instruct
+# optionally might have model_type or tokenizer_type
 trust_remote_code: true
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 chat_template: phi_3
 
 load_in_8bit: false

examples/pythia-12b/config.yml

@@ -1,7 +1,11 @@
 base_model: EleutherAI/pythia-12b-deduped
 base_model_ignore_patterns: pytorch*  # prefer safetensors
+# optionally might have model_type or tokenizer_type
 model_type: GPTNeoXForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 load_in_8bit: false
 load_in_4bit: false
 gptq: false

examples/pythia/lora.yml

@@ -1,4 +1,7 @@
 base_model: EleutherAI/pythia-1.4b-deduped
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 load_in_8bit: true
 datasets:
   - path: teknium/GPT4-LLM-Cleaned

examples/qwen/lora.yml

@@ -1,6 +1,9 @@
 base_model: Qwen/Qwen-7B
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 trust_remote_code: true
 

examples/qwen/qlora.yml

@@ -1,6 +1,9 @@
 base_model: Qwen/Qwen-7B
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 trust_remote_code: true
 

examples/qwen/qwen2-moe-lora.yaml

@@ -1,4 +1,7 @@
 base_model: Qwen/Qwen1.5-MoE-A2.7B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/qwen/qwen2-moe-qlora.yaml

@@ -1,4 +1,7 @@
 base_model: Qwen/Qwen1.5-MoE-A2.7B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/qwen2/dpo.yaml

@@ -1,4 +1,6 @@
 base_model: Qwen/Qwen2.5-0.5B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 strict: false
 

examples/qwen2/qlora-fsdp.yaml

@@ -1,4 +1,7 @@
 base_model: Qwen/Qwen2-7B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/redpajama/config-3b.yml

@@ -1,6 +1,10 @@
 base_model: togethercomputer/RedPajama-INCITE-Chat-3B-v1
+# optionally might have model_type or tokenizer_type
 model_type: GPTNeoXForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code:
 load_in_8bit: false
 datasets:

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

@@ -1,4 +1,7 @@
 base_model: replit/replit-code-v1-3b
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 load_in_8bit: false
 datasets:

examples/stablelm-2/1.6b/fft.yml

@@ -1,6 +1,10 @@
 base_model: stabilityai/stablelm-2-1_6b
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: false

examples/stablelm-2/1.6b/lora.yml

@@ -1,6 +1,10 @@
 base_model: stabilityai/stablelm-2-1_6b
+# optionally might have model_type or tokenizer_type
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
 trust_remote_code: true
 
 load_in_8bit: true

examples/starcoder2/qlora.yml

@@ -1,4 +1,6 @@
 base_model: bigcode/starcoder2-3b
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
 
 load_in_8bit: false
 load_in_4bit: true