fix reentrant when using offloading

* default true

* force e2e

* causal trainer only

* fix eval loggin [skip-ci]

* revert setup.py

* force tests

* guarding

* guarding

* fix test case

* use evaluate [skip-e2e]

* use evaluate [skip-e2e]

* kick off ci

* fixing

* reverting

.bandit

@@ -1,3 +1,3 @@
 [bandit]
 exclude = tests
-skips = B101,B615
+skips = B101,B615,B102,B110

.coderabbit.yaml

@@ -12,6 +12,6 @@ reviews:
   auto_review:
     enabled: true
     drafts: false
-    auto_incremental_review: true
+    auto_incremental_review: false
 chat:
   auto_reply: true

.flake8

@@ -1,5 +0,0 @@
-[flake8]
-max-line-length = 88
-
-select = C,E,F,W,B,B950
-extend-ignore = E203, E501, W503

.github/workflows/main.yml

@@ -36,6 +36,11 @@ jobs:
             python_version: "3.11"
             pytorch: 2.7.1
             axolotl_extras:
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.8.0
+            axolotl_extras:
     runs-on: axolotl-gpu-runner
     steps:
       - name: Checkout
@@ -110,6 +115,11 @@ jobs:
             python_version: "3.11"
             pytorch: 2.7.1
             axolotl_extras:
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.8.0
+            axolotl_extras:
     runs-on: axolotl-gpu-runner
     steps:
       - name: Checkout
@@ -169,6 +179,12 @@ jobs:
             pytorch: 2.7.1
             axolotl_extras: vllm
             is_latest: true
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.8.0
+            axolotl_extras:
+            is_latest:
     runs-on: axolotl-gpu-runner
     steps:
       - name: Checkout

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

@@ -33,13 +33,6 @@ jobs:
             axolotl_extras:
             num_gpus: 2
             nightly_build: "true"
-          - cuda: 126
-            cuda_version: 12.6.3
-            python_version: "3.11"
-            pytorch: 2.7.0
-            axolotl_extras:
-            num_gpus: 2
-            nightly_build: "true"
           - cuda: 126
             cuda_version: 12.6.3
             python_version: "3.11"
@@ -47,6 +40,13 @@ jobs:
             axolotl_extras: vllm
             num_gpus: 2
             nightly_build: "true"
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.8.0
+            axolotl_extras:
+            num_gpus: 2
+            nightly_build: "true"
     runs-on: [self-hosted, modal]
     timeout-minutes: 120
     steps:

.github/workflows/tests.yml

@@ -55,7 +55,7 @@ jobs:
       fail-fast: false
       matrix:
         python_version: ["3.11"]
-        pytorch_version: ["2.6.0", "2.7.0", "2.7.1"]
+        pytorch_version: ["2.6.0", "2.7.1", "2.8.0"]
     timeout-minutes: 20
 
     steps:
@@ -130,7 +130,7 @@ jobs:
       fail-fast: false
       matrix:
         python_version: ["3.11"]
-        pytorch_version: ["2.6.0", "2.7.0", "2.7.1"]
+        pytorch_version: ["2.6.0", "2.7.1", "2.8.0"]
     timeout-minutes: 20
 
     steps:
@@ -240,7 +240,7 @@ jobs:
           - cuda: 126
             cuda_version: 12.6.3
             python_version: "3.11"
-            pytorch: 2.6.0
+            pytorch: 2.7.1
             num_gpus: 1
             axolotl_extras:
             dockerfile: "Dockerfile-uv.jinja"
@@ -298,6 +298,13 @@ jobs:
             pytorch: 2.7.1
             num_gpus: 1
             axolotl_extras:
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.8.0
+            num_gpus: 1
+            gpu_type: "B200"
+            axolotl_extras:
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -318,6 +325,7 @@ jobs:
           echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
           echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
           echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
+          echo "GPU_TYPE=${{ matrix.gpu_type || 'L40S'}}" >> $GITHUB_ENV
           echo "CODECOV_TOKEN=${{ secrets.CODECOV_TOKEN }}" >> $GITHUB_ENV
           echo "E2E_DOCKERFILE=${{ matrix.dockerfile || 'Dockerfile.jinja'}}" >> $GITHUB_ENV
       - name: Run tests job on Modal
@@ -334,10 +342,10 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - cuda: 124
-            cuda_version: 12.4.1
+          - cuda: 126
+            cuda_version: 12.6.3
             python_version: "3.11"
-            pytorch: 2.6.0
+            pytorch: 2.7.1
             num_gpus: 1
             axolotl_extras:
     steps:

.isort.cfg

@@ -1,4 +0,0 @@
-[settings]
-profile=black
-known_third_party=wandb,comet_ml
-known_local_folder=src,tests

.pre-commit-config.yaml

@@ -10,22 +10,12 @@ repos:
     -   id: trailing-whitespace
     -   id: no-commit-to-branch
         args: ['--branch', 'main']
--   repo: https://github.com/psf/black
-    rev: 25.1.0
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.12
     hooks:
-    -   id: black
--   repo: https://github.com/pycqa/isort
-    rev: 6.0.1
-    hooks:
-      - id: isort
--   repo: https://github.com/PyCQA/flake8
-    rev: 7.3.0
-    hooks:
-    - id: flake8
--   repo: https://github.com/pylint-dev/pylint
-    rev: v3.3.8
-    hooks:
-    - id: pylint
+    -   id: ruff
+        args: [--fix]
+    -   id: ruff-format
 -   repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.17.1
     hooks:

.pylintrc

@@ -1,15 +0,0 @@
-[MASTER]
-init-hook="from pylint.config import find_default_config_files; import sys; sys.path.append(next(find_default_config_files()).parent.as_posix())"
-
-[TYPECHECK]
-
-# List of members which are set dynamically and missed by Pylint inference
-# system, and so shouldn't trigger E1101 when accessed.
-generated-members=numpy.*, torch.*
-
-
-[pylint.messages_control]
-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

@@ -17,6 +17,7 @@
     <br/>
     <a href="https://discord.com/invite/HhrNrHJPRb"><img src="https://img.shields.io/badge/discord-7289da.svg?style=flat-square&logo=discord" alt="discord" style="height: 20px;"></a>
     <a href="https://twitter.com/axolotl_ai"><img src="https://img.shields.io/twitter/follow/axolotl_ai?style=social" alt="twitter" style="height: 20px;"></a>
+    <a href="https://colab.research.google.com/github/axolotl-ai-cloud/axolotl/blob/main/examples/colab-notebooks/colab-axolotl-example.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="google-colab" style="height: 20px;"></a>
     <br/>
     <img src="https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/tests-nightly.yml/badge.svg" alt="tests-nightly">
     <img src="https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/multi-gpu-e2e.yml/badge.svg" alt="multigpu-semi-weekly tests">
@@ -70,6 +71,10 @@ Features:
 - Python 3.11
 - PyTorch ≥2.6.0
 
+### Google Colab
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/axolotl-ai-cloud/axolotl/blob/main/examples/colab-notebooks/colab-axolotl-example.ipynb#scrollTo=msOCO4NRmRLa)
+
 ### Installation
 
 #### Using pip

_quarto.yml

@@ -153,7 +153,7 @@ quartodoc:
         - utils.distributed
         - utils.dict
         - utils.optimizers.adopt
-        - utils.data.pretraining
+        - utils.data.streaming
         - utils.data.sft
         - utils.quantization
     - title: Schemas
@@ -272,6 +272,7 @@ website:
           contents:
             - docs/batch_vs_grad.qmd
             - docs/dataset_preprocessing.qmd
+            - docs/streaming.qmd
             - docs/multipack.qmd
             - docs/mixed_precision.qmd
             - docs/optimizers.qmd

cicd/multigpu.py

@@ -2,8 +2,6 @@
 modal application to run axolotl gpu tests in Modal
 """
 
-# pylint: disable=duplicate-code
-
 import os
 import pathlib
 import tempfile
@@ -63,7 +61,7 @@ def run_cmd(cmd: str, run_folder: str):
 
     # Propagate errors from subprocess.
     if exit_code := subprocess.call(cmd.split(), cwd=run_folder):  # nosec
-        exit(exit_code)  # pylint: disable=consider-using-sys-exit
+        exit(exit_code)
 
 
 @app.function(

cicd/single_gpu.py

@@ -1,7 +1,5 @@
 """Modal app to run axolotl GPU tests"""
 
-# pylint: disable=duplicate-code
-
 import os
 import pathlib
 import tempfile
@@ -59,7 +57,8 @@ VOLUME_CONFIG = {
 }
 
 N_GPUS = int(os.environ.get("N_GPUS", 1))
-GPU_CONFIG = f"L40S:{N_GPUS}"
+GPU_TYPE = os.environ.get("GPU_TYPE", "L40S")
+GPU_CONFIG = f"{GPU_TYPE}:{N_GPUS}"
 
 
 def run_cmd(cmd: str, run_folder: str):
@@ -70,4 +69,4 @@ def run_cmd(cmd: str, run_folder: str):
 
     # Propagate errors from subprocess.
     if exit_code := subprocess.call(cmd.split(), cwd=run_folder, env=sp_env):  # nosec
-        exit(exit_code)  # pylint: disable=consider-using-sys-exit
+        exit(exit_code)

codecov.yml

@@ -12,7 +12,7 @@ coverage:
       default:
         # basic
         target: auto
-        threshold: 0%
+        threshold: 1%
         base: auto
         # advanced
         branches: null
@@ -27,7 +27,7 @@ coverage:
       default:
         # basic
         target: auto
-        threshold: 0%
+        threshold: 1%
         base: auto
         # advanced
         branches: null

docs/installation.qmd

@@ -134,7 +134,7 @@ For providers supporting Docker:
 
 ### Google Colab {#sec-colab}
 
-Use our [example notebook](../examples/colab-notebooks/colab-axolotl-example.ipynb).
+[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/axolotl-ai-cloud/axolotl/blob/main/examples/colab-notebooks/colab-axolotl-example.ipynb#scrollTo=msOCO4NRmRLa)
 
 ## Platform-Specific Instructions {#sec-platform-specific}
 

docs/multi-gpu.qmd

@@ -63,15 +63,6 @@ Start from Stage 1 -> Stage 2 -> Stage 3.
 
 :::
 
-::: {.callout-tip}
-
-Using ZeRO Stage 3 with Single-GPU training
-
-ZeRO Stage 3 can be used for training on a single GPU by manually setting the environment variables:
-`WORLD_SIZE=1 LOCAL_RANK=0 MASTER_ADDR=0.0.0.0 MASTER_PORT=29500`
-
-:::
-
 ## Fully Sharded Data Parallel (FSDP) {#sec-fsdp}
 
 ::: {.callout-note}

docs/reward_modelling.qmd

@@ -11,6 +11,7 @@ We support the reward modelling techniques supported by `trl`.
 ### (Outcome) Reward Models
 
 Outcome reward models are trained using data which contains preference annotations for an entire interaction between the user and model (e.g. rather than per-turn or per-step).
+For improved training stability, you can use the `center_rewards_coefficient` parameter to encourage mean-zero reward outputs ([see TRL docs](https://huggingface.co/docs/trl/v0.10.1/en/reward_trainer#centering-rewards)).
 
 ```yaml
 base_model: google/gemma-2-2b

docs/scripts/generate_config_docs.py

@@ -47,7 +47,6 @@ class QuartoGenerator:
         """Check if a type is a Pydantic BaseModel."""
         return inspect.isclass(type_obj) and issubclass(type_obj, BaseModel)
 
-    # pylint: disable=too-many-return-statements
     def _extract_nested_type(self, field_type) -> Any:
         """Extract the actual type from complex type annotations."""
         # Handle Annotated types (Python 3.9+)
@@ -124,7 +123,6 @@ class QuartoGenerator:
 
         return field_type
 
-    # pylint: disable=too-many-return-statements
     def _extract_all_pydantic_models_from_type(
         self, field_type
     ) -> list[type[BaseModel]]:
@@ -318,7 +316,6 @@ class QuartoGenerator:
 
         return all_groups
 
-    # pylint: disable=too-many-return-statements
     def _extract_field_groups_from_source(
         self, model_class: type[BaseModel]
     ) -> list[dict]:
@@ -503,7 +500,7 @@ class QuartoGenerator:
                     nested_schema = nested_model.model_json_schema()
                     nested_properties = nested_schema.get("properties", {})
                     nested_required = nested_schema.get("required", [])
-                except Exception:  # pylint: disable=broad-exception-caught
+                except Exception:
                     # Fallback: use model fields directly
                     nested_properties = {}
                     nested_required = []
@@ -607,7 +604,7 @@ class QuartoGenerator:
             schema = model_class.model_json_schema()
             properties = schema.get("properties", {})
             required = schema.get("required", [])
-        except Exception as e:  # pylint: disable=broad-exception-caught
+        except Exception as e:
             print(
                 f"Warning: Could not generate JSON schema ({e}). Using model fields instead."
             )

docs/streaming.qmd

@@ -0,0 +1,120 @@
+---
+title: Streaming Datasets
+description: How to use streaming mode for large-scale datasets and memory-efficient training
+order: 10
+---
+
+Streaming enables memory-efficient training with large datasets by loading data
+incrementally rather than loading the entire dataset into memory at once.
+
+Use streaming when:
+
+- Your dataset is too large to fit in memory (e.g. when you're doing pretraining with massive text corpora)
+- You want to start training immediately without preprocessing the entire dataset
+
+Streaming works with both remote and locally stored datasets!
+
+::: {.callout-note}
+Streaming currently only supports a single dataset. Multi-dataset support will be added soon.
+:::
+
+
+## Configuration
+
+### Basic Streaming
+
+Enable streaming mode by setting the `streaming` flag:
+
+```yaml
+streaming: true
+```
+
+### Pretraining with Streaming
+
+For pretraining tasks, streaming is automatically enabled when using `pretraining_dataset`:
+
+```yaml
+pretraining_dataset:
+  - path: HuggingFaceFW/fineweb-edu
+    type: pretrain
+    text_column: text
+    split: train
+
+# Optionally, enable sample packing
+streaming_multipack_buffer_size: 10000
+sample_packing: true
+```
+
+### SFT with Streaming
+
+For supervised fine-tuning with streaming:
+
+```yaml
+streaming: true
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+    split: train
+
+# Optionally, enable sample packing
+streaming_multipack_buffer_size: 10000
+sample_packing: true
+```
+
+## Configuration Options
+
+### `streaming_multipack_buffer_size`
+
+Controls the buffer size for multipack streaming (default: 10,000). This determines how
+many samples are buffered before packing. Larger buffers can improve packing efficiency
+but use more memory.
+
+### `shuffle_merged_datasets`
+
+When enabled, shuffles the streaming dataset using the buffer. This requires additional
+memory for the shuffle buffer.
+
+## Sample Packing with Streaming
+
+Sample packing is supported for streaming datasets. When enabled, multiple samples are
+packed into a single sequence to maximize GPU utilization:
+
+```yaml
+sample_packing: true
+streaming_multipack_buffer_size: 10000
+
+# For SFT: attention is automatically isolated between packed samples
+# For pretraining: control with pretrain_multipack_attn
+pretrain_multipack_attn: true  # prevent cross-attention between packed samples
+```
+
+For more information, see our [documentation](multipack.qmd) on multipacking.
+
+## Important Considerations
+
+### Memory Usage
+
+While streaming reduces memory usage compared to loading entire datasets, you still need
+to consider:
+
+- You can control the memory usage by adjusting `streaming_multipack_buffer_size`
+- Sample packing requires buffering multiple samples
+- Shuffling requires additional memory for the shuffle buffer
+
+### Performance
+
+- Streaming may have slightly higher latency compared to preprocessed datasets, as samples are processed on-the-fly
+- Network speed and disk read speed are important when streaming from remote sources or a local dataset, respectively
+- Consider using `axolotl preprocess` for smaller or more frequently used datasets
+
+### Evaluation Datasets
+
+Evaluation datasets are not streamed to ensure consistent evaluation metrics. They're
+loaded normally even when training uses streaming.
+
+## Examples
+
+See the `examples/streaming/` directory for complete configuration examples:
+
+- `pretrain.yaml`: Pretraining with streaming dataset
+- `sft.yaml`: Supervised fine-tuning with streaming

examples/cloud/baseten.yaml

@@ -0,0 +1,10 @@
+provider: baseten
+project_name:
+
+secrets:
+  - HF_TOKEN
+  - WANDB_API_KEY
+
+gpu: h100
+gpu_count: 8
+node_count: 1

examples/gemma3/270m-qlora.yml

@@ -0,0 +1,68 @@
+base_model: google/gemma-3-270m-it
+# 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
+
+# gemma3 doesn't seem to play nice with ddp
+ddp_find_unused_parameters: true
+
+load_in_8bit: false
+load_in_4bit: true
+
+# huggingface repo
+chat_template: gemma3
+eot_tokens:
+  - <end_of_turn>
+datasets:
+  - path: cgato/SlimOrcaDedupCleaned
+    type: chat_template
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+
+val_set_size: 0.0
+output_dir: ./outputs/out
+
+adapter: qlora
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+
+sequence_len: 2048
+sample_packing: true
+eval_sample_packing: false
+
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch:
+saves_per_epoch: 1
+weight_decay: 0.0
+special_tokens:

examples/qwen3/reward-model.yaml

@@ -0,0 +1,44 @@
+base_model: Skywork/Skywork-Reward-V2-Qwen3-8B
+model_type: AutoModelForSequenceClassification
+num_labels: 1
+
+reward_model: true
+center_rewards_coefficient: 0.01  # Incentivize mean-zero rewards for improved stability
+chat_template: qwen3
+datasets:
+  - path: argilla/distilabel-intel-orca-dpo-pairs
+    type: bradley_terry.chat_template
+
+val_set_size: 0.0
+output_dir: ./outputs/out
+
+sequence_len: 8192
+sample_packing: false
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+deepspeed: deepspeed_configs/zero1.json
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+eval_batch_size: 1
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+lr_scheduler: linear
+learning_rate: 0.00002
+
+bf16: true
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+warmup_ratio: 0.1
+logging_steps: 1
+weight_decay: 0.01

examples/streaming/README.md

@@ -0,0 +1,50 @@
+# Streaming Dataset Examples
+
+This directory contains example configurations for using Axolotl's streaming dataset
+functionality, which enables memory-efficient training with large datasets.
+
+## Examples
+
+Run the following examples with e.g. `axolotl train examples/streaming/sft.yaml`; no
+`axolotl preprocess` required!
+
+### Pretraining (`pretrain.yaml`)
+
+Demonstrates streaming configuration for pretraining tasks using the fineweb-edu dataset
+with SmolLM2-135M.
+
+- Uses `pretraining_dataset` configuration for automatic streaming
+- Multipack attention control to prevent cross-attention between packed sequences
+- Buffer size configuration for memory management
+
+### SFT (`sft.yaml`)
+
+Shows how to use streaming for supervised fine-tuning with the Alpaca dataset.
+
+- Explicit `streaming: true` flag for SFT datasets
+- Memory-efficient training on instruction datasets
+- Evaluation datasets are currently not streamed
+
+## Key Configuration Options
+
+### `streaming`
+- Enables streaming mode for standard datasets
+- Automatically enabled for `pretraining_dataset`
+
+### `streaming_multipack_buffer_size`
+- Controls buffer size for sample packing (default: 10,000)
+- Larger values improve packing efficiency but use more memory
+- Adjust based on available memory
+
+### `shuffle_merged_datasets`
+- Enables shuffling of streaming datasets
+- Requires additional memory for shuffle buffer
+
+### `sample_packing`
+- Packs multiple samples into single sequences
+- Minimize per-step padding tokens
+
+## Performance Tips
+
+- Download small / frequently-used datasets locally for better performance
+- Larger buffer sizes improve packing efficiency

examples/streaming/pretrain.yaml

@@ -0,0 +1,57 @@
+base_model: HuggingFaceTB/SmolLM2-135M
+
+# Streaming pretraining configuration
+pretraining_dataset:
+  - path: HuggingFaceFW/fineweb-edu
+    name: sample-10BT
+    type: pretrain
+    text_column: text
+    split: train
+
+# Streaming-specific settings
+streaming_multipack_buffer_size: 10000
+shuffle_merged_datasets: true
+
+# Training configuration
+max_steps: 1000
+output_dir: ./outputs/smollm2-135m-pretrain-streaming
+
+# Sequence and packing settings
+sequence_len: 1024
+sample_packing: true
+pretrain_multipack_attn: true  # Prevent cross-attention between packed sequences
+flash_attention: true
+
+# Batch size settings
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+
+# Optimizer and scheduler
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 5e-4
+warmup_ratio: 0.1
+weight_decay: 0.01
+
+# Precision and performance
+bf16: auto
+tf32: true
+
+# Logging and checkpointing
+logging_steps: 10
+save_strategy: steps
+save_steps: 250
+save_total_limit: 3
+
+# Weights & Biases (optional)
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+# Special tokens
+special_tokens:
+  pad_token: "<|endoftext|>"
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/streaming/sft.yaml

@@ -0,0 +1,55 @@
+base_model: HuggingFaceTB/SmolLM2-135M
+
+# Dataset configuration
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+    split: train
+
+# Streaming-specific settings
+streaming: true
+streaming_multipack_buffer_size: 10000
+shuffle_merged_datasets: true
+
+# Training configuration
+max_steps: 1000
+output_dir: ./outputs/smollm2-135m-sft-streaming
+
+# Sequence and packing settings
+sequence_len: 1024
+sample_packing: true
+flash_attention: true
+
+# Batch size settings
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+
+# Optimizer and scheduler
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 2e-4
+warmup_ratio: 0.1
+weight_decay: 0.0
+
+# Precision and performance
+bf16: auto
+tf32: true
+
+# Logging and checkpointing
+logging_steps: 10
+save_strategy: steps
+save_steps: 100
+save_total_limit: 3
+
+# Weights & Biases (optional)
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+# Special tokens
+special_tokens:
+  pad_token: "<|endoftext|>"
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

pyproject.toml

@@ -26,3 +26,34 @@ include-package-data = true
 
 [tool.setuptools.cmdclass]
 build_py = "setuptools_axolotl_dynamic_dependencies.BuildPyCommand"
+
+[tool.ruff]
+line-length = 88
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "C90", "B"]
+ignore = [
+    "E203",  # Whitespace before ':'
+    "E501",  # Line too long
+    "C901",  # Too complex
+    "B019",  # Use of functools.cache on methods
+    "E722",  # Bare except
+    "F821",  # Undefined name (for dynamic exec)
+]
+
+[tool.ruff.lint.isort]
+known-third-party = ["wandb", "comet_ml"]
+known-local-folder = ["src", "tests"]
+# Black-compatible isort settings
+force-single-line = false
+combine-as-imports = true
+split-on-trailing-comma = true
+
+[tool.ruff.format]
+# Use black's formatting style exactly
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+line-ending = "auto"
+docstring-code-format = false

requirements.txt

@@ -2,8 +2,7 @@
 
 # START section of dependencies that don't install on Darwin/MacOS
 bitsandbytes==0.47.0
-# triton 3.4.0 is not compatible with CCE
-triton>=3.0.0,<3.4.0
+triton>=3.0.0
 mamba-ssm==1.2.0.post1
 xformers>=0.0.23.post1
 autoawq==0.2.7.post3
@@ -13,8 +12,8 @@ liger-kernel==0.6.1
 packaging==23.2
 
 huggingface_hub>=0.33.0
-peft==0.17.0
-transformers==4.55.2
+peft>=0.17.0
+transformers==4.56.1
 tokenizers>=0.21.1
 accelerate==1.10.0
 datasets==4.0.0

scripts/chat_datasets.py

@@ -27,7 +27,7 @@ def parse_dataset(dataset=None, split="train"):
             break
     if not field_messages:
         raise ValueError(
-            f'No conversation field found in dataset: {", ".join(feature_keys)}'
+            f"No conversation field found in dataset: {', '.join(feature_keys)}"
         )
     ds_cfg["field_messages"] = field_messages
 
@@ -40,7 +40,7 @@ def parse_dataset(dataset=None, split="train"):
             break
     if not message_property_mappings["role"]:
         raise ValueError(
-            f'No role field found in messages: {", ".join(message_fields)}'
+            f"No role field found in messages: {', '.join(message_fields)}"
         )
 
     for key in ["content", "text", "value"]:
@@ -49,7 +49,7 @@ def parse_dataset(dataset=None, split="train"):
             break
     if not message_property_mappings["content"]:
         raise ValueError(
-            f'No content field found in messages: {", ".join(message_fields)}'
+            f"No content field found in messages: {', '.join(message_fields)}"
         )
     ds_cfg["message_property_mappings"] = message_property_mappings
 

scripts/cutcrossentropy_install.py

@@ -29,5 +29,5 @@ UV_PREFIX = "uv " if USE_UV else ""
 
 print(
     UNINSTALL_PREFIX
-    + f'{UV_PREFIX}pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@0ee9ee8"'
+    + f'{UV_PREFIX}pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@c6a32c5"'
 )

scripts/unsloth_install.py

@@ -1,11 +1,10 @@
 # noqa
-# pylint: skip-file
 import sys
 
 try:
     import torch
-except ImportError:
-    raise ImportError("Install torch via `pip install torch`")
+except ImportError as error:
+    raise ImportError("Install torch via `pip install torch`") from error
 from packaging.version import Version as V
 
 use_uv = "--uv" in sys.argv[1:]

setup.py

@@ -64,7 +64,9 @@ def parse_requirements(extras_require_map):
             else:
                 raise ValueError("Invalid version format")
 
-            if (major, minor) >= (2, 7):
+            if (major, minor) >= (2, 8):
+                pass
+            elif (major, minor) >= (2, 7):
                 _install_requires.pop(_install_requires.index(xformers_version))
                 if patch == 0:
                     _install_requires.append("xformers==0.0.30")
@@ -125,7 +127,7 @@ extras_require = {
         "yunchang==0.6.0",
     ],
     "deepspeed": [
-        "deepspeed==0.17.2",
+        "deepspeed==0.17.5",
         "deepspeed-kernels",
     ],
     "mamba-ssm": [

src/axolotl/cli/args.py

@@ -14,9 +14,13 @@ class PreprocessCliArgs:
     prompter: Optional[str] = field(default=None)
     download: Optional[bool] = field(default=True)
     iterable: Optional[bool] = field(
-        default=None,
+        default=False,
         metadata={
-            "help": "Use IterableDataset for streaming processing of large datasets"
+            "help": (
+                "Deprecated in v0.13.0, will be removed in v0.14.0. For streaming "
+                "datasets, use 'axolotl train' and set 'streaming: true' in your YAML "
+                "config, or pass --streaming instead in the CLI."
+            )
         },
     )
 

src/axolotl/cli/art.py

@@ -22,7 +22,7 @@ HAS_PRINTED_LOGO = False
 def print_axolotl_text_art():
     """Prints axolotl ASCII art."""
 
-    global HAS_PRINTED_LOGO  # pylint: disable=global-statement
+    global HAS_PRINTED_LOGO
     if HAS_PRINTED_LOGO:
         return
     if is_main_process():

src/axolotl/cli/cloud/__init__.py

@@ -7,6 +7,8 @@ from typing import Literal
 
 import yaml
 
+from axolotl.cli.cloud.base import Cloud
+from axolotl.cli.cloud.baseten import BasetenCloud
 from axolotl.cli.cloud.modal_ import ModalCloud
 from axolotl.utils.dict import DictDefault
 
@@ -38,8 +40,15 @@ def do_cli_train(
     cwd=None,
     **kwargs,
 ) -> None:
-    cloud_cfg = load_cloud_cfg(cloud_config)
-    cloud = ModalCloud(cloud_cfg)
+    cloud_cfg: DictDefault = load_cloud_cfg(cloud_config)
+    provider = cloud_cfg.provider or "modal"
+    cloud: Cloud | None
+    if provider == "modal":
+        cloud = ModalCloud(cloud_cfg)
+    elif provider == "baseten":
+        cloud = BasetenCloud(cloud_cfg.to_dict())
+    else:
+        raise ValueError(f"Unsupported cloud provider: {provider}")
     with open(config, "r", encoding="utf-8") as file:
         config_yaml = file.read()
     local_dirs = {}

src/axolotl/cli/cloud/baseten/__init__.py

@@ -0,0 +1,48 @@
+"""Baseten Cloud CLI"""
+
+import shutil
+import subprocess  # nosec B404
+import tempfile
+from os.path import dirname
+from typing import Literal
+
+import yaml
+
+from axolotl.cli.cloud.base import Cloud
+
+
+class BasetenCloud(Cloud):
+    """Baseten Cloud Axolotl CLI"""
+
+    def __init__(self, config: dict):
+        self.config = config
+
+    def preprocess(self, config_yaml: str, *args, **kwargs) -> None:
+        raise NotImplementedError(
+            "Separate preprocess function for Baseten is not "
+            "implemented and will happen during hte train step."
+        )
+
+    def train(
+        self,
+        config_yaml: str,
+        launcher: Literal["accelerate", "torchrun", "python"] = "accelerate",
+        launcher_args: list[str] | None = None,
+        local_dirs: dict[str, str] | None = None,  # pylint: disable=unused-argument
+        **kwargs,
+    ):
+        with tempfile.TemporaryDirectory() as tmp_dir:
+            config = self.config.copy()
+            config["launcher"] = launcher
+            config["launcher_args"] = launcher_args
+            with open(tmp_dir + "/cloud.yaml", "w", encoding="utf-8") as cloud_fout:
+                yaml.dump(config, cloud_fout)
+            with open(tmp_dir + "/train.yaml", "w", encoding="utf-8") as config_fout:
+                config_fout.write(config_yaml)
+            shutil.copyfile(dirname(__file__) + "/template/run.sh", tmp_dir + "/run.sh")
+            shutil.copyfile(
+                dirname(__file__) + "/template/train_sft.py", tmp_dir + "/train_sft.py"
+            )
+            subprocess.run(  # nosec B603 B607
+                ["truss", "train", "push", "train_sft.py"], cwd=tmp_dir, check=False
+            )

src/axolotl/cli/cloud/baseten/template/run.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+set -eux
+
+export NCCL_SOCKET_IFNAME="^docker0,lo"
+export NCCL_IB_DISABLE=0
+export NCCL_TIMEOUT=1800000
+
+axolotl preprocess train.yaml
+axolotl train train.yaml --launcher ${AXOLOTL_LAUNCHER} ${AXOLOTL_LAUNCHER_ARGS}

src/axolotl/cli/cloud/baseten/template/train_sft.py

@@ -0,0 +1,71 @@
+"""
+Baseten Training Script for Axolotl
+"""
+
+# pylint: skip-file
+import yaml
+from truss.base import truss_config
+
+# Import necessary classes from the Baseten Training SDK
+from truss_train import definitions
+
+cloud_config = yaml.safe_load(open("cloud.yaml", "r"))
+gpu = cloud_config.get("gpu", "h100")
+gpu_count = int(cloud_config.get("gpu_count", 1))
+node_count = int(cloud_config.get("node_count", 1))
+project_name = cloud_config.get("project_name", "axolotl-project") or "axolotl-project"
+secrets = cloud_config.get("secrets", [])
+launcher = cloud_config.get("launcher", "accelerate")
+launcher_args = cloud_config.get("launcher_args", [])
+script_name = "run.sh"
+
+launcher_args_str = ""
+if launcher_args:
+    launcher_args_str = "-- " + " ".join(launcher_args)
+
+# 1. Define a base image for your training job
+# must use torch 2.7.0 for vllm
+BASE_IMAGE = "axolotlai/axolotl:main-py3.11-cu126-2.7.1"
+
+# 2. Define the Runtime Environment for the Training Job
+# This includes start commands and environment variables.a
+# Secrets from the baseten workspace like API keys are referenced using
+# `SecretReference`.
+
+env_vars = {
+    "AXOLOTL_LAUNCHER": launcher,
+    "AXOLOTL_LAUNCHER_ARGS": launcher_args_str,
+}
+for secret_name in secrets:
+    env_vars[secret_name] = definitions.SecretReference(name=secret_name)
+
+training_runtime = definitions.Runtime(
+    start_commands=[  # Example: list of commands to run your training script
+        f"/bin/sh -c 'chmod +x ./{script_name} && ./{script_name}'"
+    ],
+    environment_variables=env_vars,
+)
+
+# 3. Define the Compute Resources for the Training Job
+training_compute = definitions.Compute(
+    node_count=node_count,
+    accelerator=truss_config.AcceleratorSpec(
+        accelerator=truss_config.Accelerator.H100,
+        count=gpu_count,
+    ),
+)
+
+# 4. Define the Training Job
+# This brings together the image, compute, and runtime configurations.
+my_training_job = definitions.TrainingJob(
+    image=definitions.Image(base_image=BASE_IMAGE),
+    compute=training_compute,
+    runtime=training_runtime,
+)
+
+
+# This config will be pushed using the Truss CLI.
+# The association of the job to the project happens at the time of push.
+first_project_with_job = definitions.TrainingProject(
+    name=project_name, job=my_training_job
+)

src/axolotl/cli/cloud/modal_.py

@@ -41,7 +41,7 @@ def run_cmd(cmd: str, run_folder: str, volumes=None):
     if exit_code := subprocess.call(  # nosec B603
         cmd.split(), cwd=run_folder, env=new_env
     ):
-        exit(exit_code)  # pylint: disable=consider-using-sys-exit
+        exit(exit_code)
 
     # Commit writes to volume.
     if volumes:
@@ -130,7 +130,6 @@ class ModalCloud(Cloud):
         res = []
         if self.config.secrets:
             for key in self.config.get("secrets", []):
-                # pylint: disable=duplicate-code
                 if isinstance(key, str):
                     if val := os.environ.get(key, ""):
                         res.append(modal.Secret.from_dict({key: val}))
@@ -177,8 +176,8 @@ class ModalCloud(Cloud):
             with self.app.run(detach=True):
                 modal_fn.remote(
                     config_yaml,
-                    volumes={k: v[0] for k, v in self.volumes.items()},
                     *args,
+                    volumes={k: v[0] for k, v in self.volumes.items()},
                     **kwargs,
                 )
 
@@ -187,7 +186,7 @@ class ModalCloud(Cloud):
             return int(self.config.timeout)
         return 60 * 60 * 24  # 24 hours
 
-    def get_train_gpu(self):  # pylint: disable=too-many-return-statements
+    def get_train_gpu(self):
         count = self.config.gpu_count or 1
         family = self.config.gpu.lower() or "l40s"
 
@@ -277,7 +276,7 @@ def _train(
     launcher: Literal["accelerate", "torchrun", "python"] = "accelerate",
     launcher_args: list[str] | None = None,
     volumes=None,
-    **kwargs,  # pylint: disable=unused-argument
+    **kwargs,
 ):
     Path("/workspace/mounts").mkdir(parents=True, exist_ok=True)
     with open("/workspace/mounts/config.yaml", "w", encoding="utf-8") as f_out:

src/axolotl/cli/config.py

@@ -210,7 +210,7 @@ def load_cfg(
     try:
         device_props = torch.cuda.get_device_properties("cuda")
         gpu_version = "sm_" + str(device_props.major) + str(device_props.minor)
-    except:  # pylint: disable=bare-except # noqa: E722
+    except:
         gpu_version = None
 
     prepare_plugins(cfg)

src/axolotl/cli/evaluate.py

@@ -28,7 +28,7 @@ def do_evaluate(cfg: DictDefault, cli_args: TrainerCliArgs) -> None:
         cfg: Dictionary mapping `axolotl` config keys to values.
         cli_args: CLI arguments.
     """
-    # pylint: disable=duplicate-code
+
     check_accelerate_default_config()
     if int(os.getenv("LOCAL_RANK", "0")) == 0:
         check_user_token()
@@ -49,7 +49,7 @@ def do_cli(config: Union[Path, str] = Path("examples/"), **kwargs) -> None:
         config: Path to `axolotl` config YAML file.
         kwargs: Additional keyword arguments to override config file values.
     """
-    # pylint: disable=duplicate-code
+
     parsed_cfg = load_cfg(config, **kwargs)
     parser = HfArgumentParser(TrainerCliArgs)
     parsed_cli_args, _ = parser.parse_args_into_dataclasses(

src/axolotl/cli/inference.py

@@ -14,10 +14,7 @@ from transformers import GenerationConfig, TextIteratorStreamer, TextStreamer
 from axolotl.cli.args import InferenceCliArgs
 from axolotl.cli.config import load_cfg
 from axolotl.cli.utils import load_model_and_tokenizer
-from axolotl.utils.chat_templates import (
-    get_chat_template,
-    get_chat_template_from_config,
-)
+from axolotl.utils.chat_templates import get_chat_template_from_config
 from axolotl.utils.dict import DictDefault
 from axolotl.utils.logging import get_logger
 
@@ -35,7 +32,7 @@ def get_multi_line_input() -> str:
 
     instruction = ""
     for line in sys.stdin:
-        instruction += line  # pylint: disable=consider-using-join
+        instruction += line
 
     return instruction
 
@@ -64,7 +61,9 @@ def do_inference(
             importlib.import_module("axolotl.prompters"), prompter
         )
     elif cfg.chat_template:
-        chat_template_str = get_chat_template(cfg.chat_template, tokenizer=tokenizer)
+        chat_template_str = get_chat_template_from_config(
+            cfg, ds_cfg=None, tokenizer=tokenizer
+        )
     elif cfg.datasets[0].type == "chat_template":
         chat_template_str = get_chat_template_from_config(
             cfg=cfg, ds_cfg=cfg.datasets[0], tokenizer=tokenizer
@@ -159,7 +158,13 @@ def do_inference_gradio(
             importlib.import_module("axolotl.prompters"), prompter
         )
     elif cfg.chat_template:
-        chat_template_str = get_chat_template(cfg.chat_template, tokenizer=tokenizer)
+        chat_template_str = get_chat_template_from_config(
+            cfg, ds_cfg=None, tokenizer=tokenizer
+        )
+    elif cfg.datasets[0].type == "chat_template":
+        chat_template_str = get_chat_template_from_config(
+            cfg=cfg, ds_cfg=cfg.datasets[0], tokenizer=tokenizer
+        )
 
     model = model.to(cfg.device, dtype=cfg.torch_dtype)
 
@@ -167,7 +172,6 @@ def do_inference_gradio(
         if not instruction:
             return
         if prompter_module:
-            # pylint: disable=stop-iteration-return
             prompt: str = next(
                 prompter_module().build_prompt(instruction=instruction.strip("\n"))
             )
@@ -252,7 +256,7 @@ def do_cli(
         config: Path to `axolotl` config YAML file.
         kwargs: Additional keyword arguments to override config file values.
     """
-    # pylint: disable=duplicate-code
+
     parsed_cfg = load_cfg(config, inference=True, rl=None, **kwargs)
     parsed_cfg.sample_packing = False
     parser = transformers.HfArgumentParser(InferenceCliArgs)

src/axolotl/cli/main.py

@@ -1,7 +1,5 @@
 """Click CLI definitions for various axolotl commands."""
 
-# pylint: disable=redefined-outer-name
-
 import os
 import subprocess  # nosec B404
 from typing import Literal, Optional

src/axolotl/cli/merge_lora.py

@@ -43,7 +43,10 @@ def do_merge_lora(*, cfg: DictDefault) -> None:
             safe_serialization=safe_serialization,
             progressbar=True,
         )
-        tokenizer.save_pretrained(str(Path(cfg.output_dir) / "merged"))
+        tokenizer.save_pretrained(
+            str(Path(cfg.output_dir) / "merged"),
+            save_jinja_files=cfg.tokenizer_save_jinja_files,
+        )
 
         if processor:
             processor.save_pretrained(str(Path(cfg.output_dir) / "merged"))

src/axolotl/cli/merge_sharded_fsdp_weights.py

@@ -32,7 +32,7 @@ LOG = get_logger(__name__)
 class BFloat16CastPlanner(_EmptyStateDictLoadPlanner):
     """A custom planner to cast tensors to bfloat16 on the fly during loading."""
 
-    def commit_tensor(self, read_item, tensor):  # pylint: disable=unused-argument
+    def commit_tensor(self, read_item, tensor):
         tensor.copy_(tensor.to(torch.bfloat16))
 
 
@@ -59,10 +59,10 @@ def _distributed_checkpoint_to_merged_weights(
     state_dict: Dict = {}
     save_path_ = Path(save_path)
     save_path_.mkdir(exist_ok=True)
-    dist_cp_format_utils._load_state_dict(  # pylint: disable=protected-access
+    dist_cp_format_utils._load_state_dict(
         state_dict,
         storage_reader=dist_cp.FileSystemReader(checkpoint_dir),
-        planner=BFloat16CastPlanner(),  # pylint: disable=protected-access
+        planner=BFloat16CastPlanner(),
         no_dist=True,
     )
 
@@ -191,7 +191,7 @@ def do_cli(config: Union[Path, str] = Path("examples/"), **kwargs):
         config: Path to `axolotl` config YAML file.
         kwargs: Additional keyword arguments to override config file values.
     """
-    # pylint: disable=duplicate-code
+
     parsed_cfg = load_cfg(config, **kwargs)
 
     fsdp_dir = Path(parsed_cfg.output_dir) / "pytorch_model_fsdp_0"

src/axolotl/cli/preprocess.py

@@ -35,10 +35,20 @@ def do_preprocess(cfg: DictDefault, cli_args: PreprocessCliArgs) -> None:
     check_accelerate_default_config()
     check_user_token()
 
+    if cli_args.iterable:
+        LOG.error(
+            "The --iterable CLI argument for 'axolotl preprocess' is no longer "
+            "supported. For training, set 'streaming: true' in your YAML config or "
+            "pass '--streaming' in your 'axolotl train' command for on-the-fly "
+            "preprocessing."
+        )
+        return
+
     for key in ["skip_prepare_dataset", "pretraining_dataset"]:
         if cfg.get(key):
             LOG.error(
-                f"You have set `{key}:`. `preprocess` is not needed. Run the `axolotl train` CLI directly instead."
+                f"You have set `{key}:`. `preprocess` is not needed. Run the 'axolotl "
+                "train' CLI directly instead."
             )
             return
 
@@ -73,7 +83,7 @@ def do_preprocess(cfg: DictDefault, cli_args: PreprocessCliArgs) -> None:
                     AutoModelForCausalLM.from_pretrained(
                         model_name, trust_remote_code=True
                     )
-                except Exception as exc:  # pylint: disable=broad-exception-caught,unused-variable  # nosec B110  # noqa F841
+                except Exception:  # nosec B110
                     pass
                 # fmt: on
 
@@ -95,7 +105,7 @@ def do_cli(
         config: Path to `axolotl` config YAML file.
         kwargs: Additional keyword arguments to override config file values.
     """
-    # pylint: disable=duplicate-code
+
     os.environ["AXOLOTL_IS_PREPROCESS"] = "1"
     is_preprocess = kwargs.pop("is_preprocess", True)
     parsed_cfg = load_cfg(config, is_preprocess=is_preprocess, **kwargs)

src/axolotl/cli/quantize.py

@@ -84,5 +84,6 @@ def do_quantize(
         str(Path(output_dir) / "quantized"),
         safe_serialization=False,
         progressbar=True,
+        save_jinja_files=cfg.tokenizer_save_jinja_files,
     )
     LOG.info(f"Quantized model saved to: {str(Path(output_dir) / 'quantized')}...")

src/axolotl/cli/train.py

@@ -59,7 +59,7 @@ def do_cli(config: Union[Path, str] = Path("examples/"), **kwargs):
         config: Path to `axolotl` config YAML file.
         kwargs: Additional keyword arguments to override config file values.
     """
-    # pylint: disable=duplicate-code
+
     parsed_cfg = load_cfg(config, **kwargs)
     parser = HfArgumentParser(TrainerCliArgs)
     parsed_cli_args, _ = parser.parse_args_into_dataclasses(

src/axolotl/cli/utils/args.py

@@ -65,7 +65,7 @@ def add_options_from_dataclass(config_class: Type[Any]) -> Callable:
         for field in reversed(dataclasses.fields(config_class)):
             field_type = _strip_optional_type(field.type)
 
-            if field_type == bool:
+            if field_type is bool:
                 field_name = field.name.replace("_", "-")
                 option_name = f"--{field_name}/--no-{field_name}"
                 function = click.option(
@@ -103,7 +103,7 @@ def add_options_from_config(config_class: Type[BaseModel]) -> Callable:
         for name, field in reversed(config_class.model_fields.items()):
             field_type = _strip_optional_type(field.annotation)
 
-            if field_type == bool:
+            if field_type is bool:
                 field_name = name.replace("_", "-")
                 option_name = f"--{field_name}/--no-{field_name}"
                 function = click.option(

src/axolotl/cli/utils/sweeps.py

@@ -49,7 +49,10 @@ def generate_sweep_configs(
                 new_config = {}
                 # new_config = deepcopy(base_config)
                 # Combine regular parameters with paired parameters
-                full_combo = {**dict(zip(param_names, reg_combo)), **paired_set}
+                full_combo = {
+                    **dict(zip(param_names, reg_combo, strict=False)),
+                    **paired_set,
+                }
                 for param_name, param_value in full_combo.items():
                     new_config[param_name] = param_value
                 print(new_config)
@@ -58,7 +61,7 @@ def generate_sweep_configs(
             # If no paired values, just use regular combinations
             # new_config = deepcopy(base_config)
             new_config = {}
-            for param_name, param_value in zip(param_names, reg_combo):
+            for param_name, param_value in zip(param_names, reg_combo, strict=False):
                 new_config[param_name] = param_value
             print(new_config)
             all_combinations.append(new_config)

src/axolotl/cli/utils/train.py

@@ -95,7 +95,6 @@ def generate_config_files(config: str, sweep: str | None) -> Iterator[tuple[str,
         permutation_id = f"sweep{idx:04d}"
         permutation["output_dir"] = str(permutation_dir / permutation_id)
 
-        # pylint: disable=consider-using-with
         temp_file = tempfile.NamedTemporaryFile(
             mode="w",
             suffix=".yaml",

src/axolotl/cli/vllm_serve.py

@@ -39,7 +39,7 @@ def do_vllm_serve(
     model = cfg.base_model
 
     serve_module = cli_args.get("serve_module", "trl.scripts.vllm_serve")
-    vllm_serve_main = getattr(__import__(serve_module, fromlist=["main"]), "main")
+    vllm_serve_main = __import__(serve_module, fromlist=["main"]).main
     tensor_parallel_size = 1
     data_parallel_size = 1
 
@@ -68,7 +68,6 @@ def do_vllm_serve(
         cli_args.get("enable_reasoning") or cfg.vllm.enable_reasoning or False
     )
 
-    # pylint: disable=unexpected-keyword-arg
     vllm_script_args = AxolotlScriptArguments(
         model=model,
         tensor_parallel_size=tensor_parallel_size,

src/axolotl/common/datasets.py

@@ -6,7 +6,7 @@ from dataclasses import dataclass
 
 from datasets import Dataset
 
-import axolotl.monkeypatch.data.batch_dataset_fetcher  # pylint: disable=unused-import  # noqa: F401
+import axolotl.monkeypatch.data.batch_dataset_fetcher  # noqa: F401
 from axolotl.cli.args import PreprocessCliArgs, TrainerCliArgs
 from axolotl.loaders import load_processor, load_tokenizer
 from axolotl.utils.data import prepare_datasets, prepare_preference_datasets
@@ -55,13 +55,11 @@ def load_datasets(
     """
     tokenizer = load_tokenizer(cfg)
     processor = load_processor(cfg, tokenizer=tokenizer) if cfg.processor_type else None
-    preprocess_iterable = getattr(cli_args, "iterable", False)
 
     train_dataset, eval_dataset, total_num_steps, prompters = prepare_datasets(
         cfg,
         tokenizer,
         processor=processor,
-        preprocess_iterable=preprocess_iterable,
     )
 
     if (

src/axolotl/convert.py

@@ -67,9 +67,7 @@ class JsonToJsonlConverter:
         self.json_parser = json_parser
         self.jsonl_serializer = jsonl_serializer
 
-    def convert(
-        self, input_file_path, output_file_path
-    ):  # pylint: disable=unused-argument
+    def convert(self, input_file_path, output_file_path):
         content = self.file_reader.read(input_file_path)
         data = self.json_parser.parse(content)
         # data = [r for r in data if r["conversations"]]  # vicuna cleaned has rows with empty conversations

src/axolotl/core/attention/flex_block_mask.py

@@ -84,9 +84,7 @@ def create_causal_mask(
     batch_size, dtype = input_embeds.shape[0], input_embeds.dtype
     if attention_mask is not None:
 
-        def causal_doc_mask_mod(
-            batch_idx, head_idx, q_idx, kv_idx
-        ):  # pylint: disable=unused-argument
+        def causal_doc_mask_mod(batch_idx, head_idx, q_idx, kv_idx):
             """
             Defines the logic of a block causal mask by combining both a standard causal mask
             and a block diagonal document mask.
@@ -103,9 +101,7 @@ def create_causal_mask(
         mask_factory_function = causal_doc_mask_mod
     else:
         mask_factory_function = causal_mask_function
-    mask_interface = ALL_MASK_ATTENTION_FUNCTIONS[
-        config._attn_implementation  # pylint: disable=protected-access
-    ]
+    mask_interface = ALL_MASK_ATTENTION_FUNCTIONS[config._attn_implementation]
 
     # Do not allow skip if we are compiling (this is to match BC)
     allow_is_causal_skip = (

src/axolotl/core/builders/base.py

@@ -24,9 +24,7 @@ from pathlib import Path
 from typing import Any
 
 import torch
-from transformers import (
-    TrainerCallback,
-)
+from transformers import TrainerCallback
 from transformers.trainer_pt_utils import AcceleratorConfig
 
 from axolotl.integrations.base import PluginManager
@@ -44,7 +42,7 @@ from axolotl.utils.schemas.enums import CustomSupportedOptimizers
 LOG = logging.getLogger(__name__)
 
 with suppress(ImportError):
-    import torch._dynamo  # pylint: disable=ungrouped-imports
+    import torch._dynamo
 
 
 class TrainerBuilderBase(abc.ABC):
@@ -260,14 +258,14 @@ class TrainerBuilderBase(abc.ABC):
                 adam_kwargs["eps"] = training_args_kwargs.get("adam_epsilon")
 
             if self.cfg.optimizer == "muon":
-                from axolotl.contribs.mit.muon import (  # pylint: disable=no-name-in-module
+                from axolotl.contribs.mit.muon import (
                     MuonOptimizerFactory,
                 )
 
                 optimizer_cls = MuonOptimizerFactory
                 optimizer_kwargs.update(adam_kwargs)
             elif self.cfg.optimizer == "dion":
-                from axolotl.contribs.mit.dion import (  # pylint: disable=no-name-in-module
+                from axolotl.contribs.mit.dion import (
                     DionOptimizerFactory,
                 )
 
@@ -414,12 +412,8 @@ class TrainerBuilderBase(abc.ABC):
 
     def _configure_torch_compile(self, training_args_kwargs: dict):
         if self.cfg.torch_compile and getattr(torch, "_dynamo", None):
-            torch._dynamo.config.suppress_errors = (  # pylint: disable=protected-access
-                True
-            )
-            torch._dynamo.config.accumulated_cache_size_limit = (  # pylint: disable=protected-access
-                256
-            )
+            torch._dynamo.config.suppress_errors = True
+            torch._dynamo.config.accumulated_cache_size_limit = 256
             training_args_kwargs["torch_compile"] = self.cfg.torch_compile
             if self.cfg.torch_compile_backend:
                 training_args_kwargs["torch_compile_backend"] = (
@@ -516,6 +510,7 @@ class TrainerBuilderBase(abc.ABC):
                 self.cfg.eval_batch_size
             )
 
+        training_args_kwargs["include_tkps"] = self.cfg.include_tkps
         training_args_kwargs["max_steps"] = self.cfg.max_steps or total_num_steps or -1
         training_args_kwargs["num_train_epochs"] = self.cfg.num_epochs
 

src/axolotl/core/builders/causal.py

@@ -7,10 +7,7 @@ from pathlib import Path
 from typing import Type, Union
 
 import transformers
-from transformers import (
-    DataCollatorWithFlattening,
-    EarlyStoppingCallback,
-)
+from transformers import DataCollatorWithFlattening, EarlyStoppingCallback
 from trl.trainer.utils import RewardDataCollatorWithPadding
 
 from axolotl.core.builders.base import TrainerBuilderBase
@@ -26,12 +23,12 @@ from axolotl.monkeypatch.relora import ReLoRACallback
 from axolotl.processing_strategies import get_processing_strategy
 from axolotl.utils import is_comet_available, is_mlflow_available
 from axolotl.utils.callbacks import (
-    LossWatchDogCallback,
-    SaveBetterTransformerModelCallback,
     bench_eval_callback_factory,
     causal_lm_bench_eval_callback_factory,
     colab_inference_post_train_callback,
     log_prediction_callback_factory,
+    LossWatchDogCallback,
+    SaveBetterTransformerModelCallback,
 )
 from axolotl.utils.callbacks.lisa import lisa_callback_factory
 from axolotl.utils.callbacks.qat import QATCallback
@@ -42,6 +39,7 @@ from axolotl.utils.collators import (
     MambaDataCollator,
     V2BatchSamplerDataCollatorForSeq2Seq,
 )
+from axolotl.utils.callbacks.tokens_per_second import TokensPerSecondCallback
 from axolotl.utils.collators.mm_chat import MultiModalChatDataCollator
 from axolotl.utils.import_helper import get_cls_from_module_str
 from axolotl.utils.logging import get_logger
@@ -74,6 +72,12 @@ class HFCausalTrainerBuilder(TrainerBuilderBase):
         if self.cfg.qat:
             callbacks.append(QATCallback(self.cfg.qat))
 
+        if self.cfg.include_tkps:
+            callbacks.append(
+                TokensPerSecondCallback(
+                    self.cfg.tensor_parallel_size, self.cfg.context_parallel_size
+                )
+            )
         return callbacks
 
     def get_post_trainer_create_callbacks(self, trainer):
@@ -340,20 +344,22 @@ class HFCausalTrainerBuilder(TrainerBuilderBase):
 
         if self.cfg.reward_model:
             training_args_cls = AxolotlRewardConfig
+            if self.cfg.center_rewards_coefficient is not None:
+                training_arguments_kwargs["center_rewards_coefficient"] = (
+                    self.cfg.center_rewards_coefficient
+                )
         elif self.cfg.process_reward_model:
             training_args_cls = AxolotlPRMConfig
         else:
             training_args_cls = AxolotlTrainingArguments
-        training_args = training_args_cls(  # pylint: disable=unexpected-keyword-arg
+        training_args = training_args_cls(
             **training_arguments_kwargs,
         )
         training_args = self.hook_post_create_training_args(training_args)
 
         # unset run_name so wandb sets up experiment names
         if self.cfg.use_wandb and training_args.run_name == training_args.output_dir:
-            training_args.run_name = (  # pylint: disable=attribute-defined-outside-init
-                None
-            )
+            training_args.run_name = None
 
         data_collator_kwargs = {
             "padding": True,  # True/"longest" is the default
@@ -406,6 +412,9 @@ class HFCausalTrainerBuilder(TrainerBuilderBase):
             **trainer_kwargs,
         )
         trainer = self.hook_post_create_trainer(trainer)
+        # if the trainer has the `axolotl_cfg` property, set it
+        if hasattr(trainer, "axolotl_cfg"):
+            trainer.axolotl_cfg = self.cfg
         for callback in self.get_post_trainer_create_callbacks(trainer):
             trainer.add_callback(callback)
 

src/axolotl/core/builders/rl.py

@@ -168,16 +168,14 @@ class HFRLTrainerBuilder(TrainerBuilderBase):
             if plugin_training_args:
                 training_args_kwargs.update(plugin_training_args)
 
-        training_args = training_args_cls(  # pylint: disable=unexpected-keyword-arg
+        training_args = training_args_cls(
             logging_first_step=True,
             **training_args_kwargs,
         )
 
         # unset run_name so wandb sets up experiment names
         if self.cfg.use_wandb and training_args.run_name == training_args.output_dir:
-            training_args.run_name = (  # pylint: disable=attribute-defined-outside-init
-                None
-            )
+            training_args.run_name = None
 
         return training_args, trainer_kwargs
 

src/axolotl/core/chat/format/chatml.py

@@ -10,7 +10,7 @@ from .shared import wrap_tools
 
 def format_message(
     message: Messages,
-    message_index: Optional[int] = None,  # pylint: disable=unused-argument
+    message_index: Optional[int] = None,
 ) -> Messages:
     if message.is_chat_formatted:
         return message

src/axolotl/core/chat/messages.py

@@ -15,11 +15,11 @@ class MessageRoles(str, Enum):
     Message roles for the system, user, assistant, and tools
     """
 
-    system = "system"  # pylint: disable=invalid-name
-    user = "user"  # pylint: disable=invalid-name
-    assistant = "assistant"  # pylint: disable=invalid-name
-    tool = "tool"  # pylint: disable=invalid-name
-    ipython = (  # pylint: disable=invalid-name
+    system = "system"
+    user = "user"
+    assistant = "assistant"
+    tool = "tool"
+    ipython = (
         # for responses from builtin tools
         "ipython"
     )
@@ -30,12 +30,12 @@ class MessageContentTypes(str, Enum):
     Message content types for text, image, audio, tool calls, and tool responses
     """
 
-    special_token = "special_token"  # pylint: disable=invalid-name  # nosec B105
-    text = "text"  # pylint: disable=invalid-name
-    image = "image"  # pylint: disable=invalid-name
-    audio = "audio"  # pylint: disable=invalid-name
-    tool_call = "tool_call"  # pylint: disable=invalid-name  # to differentiate regular responses from tool calls from the assistant
-    tool_response = "tool_response"  # pylint: disable=invalid-name
+    special_token = "special_token"  # nosec B105
+    text = "text"
+    image = "image"
+    audio = "audio"
+    tool_call = "tool_call"
+    tool_response = "tool_response"
 
 
 class SpecialToken(str, Enum):
@@ -43,8 +43,8 @@ class SpecialToken(str, Enum):
     Special tokens for beginning of string and end of string
     """
 
-    bos_token = "bos_token"  # pylint: disable=invalid-name  # nosec B105
-    eos_token = "eos_token"  # pylint: disable=invalid-name  # nosec B105
+    bos_token = "bos_token"  # nosec B105
+    eos_token = "eos_token"  # nosec B105
 
 
 class ToolCallFunction(BaseModel):
@@ -73,7 +73,7 @@ class ToolCallContents(BaseModel):
 
     name: str
     arguments: dict[str, Union[str, int]]
-    id: Optional[str] = None  # pylint: disable=invalid-name
+    id: Optional[str] = None
 
     def __str__(self) -> str:
         data = {"name": self.name, "arguments": self.arguments}
@@ -89,7 +89,7 @@ class ToolResponseContents(BaseModel):
 
     name: str
     content: Union[str, dict[str, Union[str, int, float]]]
-    id: Optional[str] = None  # pylint: disable=invalid-name
+    id: Optional[str] = None
 
     def __str__(self) -> str:
         data = {"name": self.name, "content": self.content}

src/axolotl/core/datasets/transforms/chat_builder.py

@@ -1,23 +1,17 @@
 """
-This module contains a function that builds a transform that takes a row from the dataset and converts it to a Chat.
+This module contains a function that builds a transform that takes a row from the
+dataset and converts it to a Chat.
 """
 
-from typing import Any, Mapping, Union
+from typing import Any, Mapping
 
 
-def chat_message_transform_builder(  # pylint: disable=dangerous-default-value
+def chat_message_transform_builder(
     train_on_inputs=False,
     conversations_field: str = "conversations",
-    message_field_role: Union[str, list[str]] = ["role", "from"],  # commonly "role"
-    message_field_content: Union[str, list[str]] = [
-        "value",
-        "text",
-        "content",
-    ],  # commonly "content"
-    message_field_training: Union[str, list[str]] = [
-        "train",
-        "weight",
-    ],  # commonly "weight"
+    message_field_role: str | list[str] | None = None,  # commonly "role"
+    message_field_content: str | list[str] | None = None,  # commonly "content"
+    message_field_training: str | list[str] | None = None,  # commonly "weight"
 ):
     """Builds a transform that takes a row from the dataset and converts it to a Chat
 
@@ -39,6 +33,12 @@ def chat_message_transform_builder(  # pylint: disable=dangerous-default-value
             A function that takes a list of conversations and returns a list of messages.
     """
 
+    if message_field_training is None:
+        message_field_training = ["train", "weight"]
+    if message_field_content is None:
+        message_field_content = ["value", "text", "content"]
+    if message_field_role is None:
+        message_field_role = ["role", "from"]
     message_field_role = (
         [message_field_role]
         if isinstance(message_field_role, str)

src/axolotl/core/trainers/__init__.py

@@ -1,6 +1,5 @@
 """Init for axolotl.core.trainers"""
 
-# pylint: disable=unused-import
 # flake8: noqa
 
 from .base import AxolotlTrainer

src/axolotl/core/trainers/base.py

@@ -1,7 +1,5 @@
 """Module for customized trainers"""
 
-# pylint: disable=too-many-lines
-
 from __future__ import annotations
 
 import os
@@ -44,6 +42,7 @@ from axolotl.core.trainers.utils import (
 )
 from axolotl.utils import get_not_null
 from axolotl.utils.bench import get_gpu_memory_usage
+from axolotl.utils.dict import DictDefault
 from axolotl.utils.distributed import is_main_process
 from axolotl.utils.logging import get_logger
 from axolotl.utils.samplers import MultipackBatchSampler, get_dataset_lengths
@@ -65,6 +64,15 @@ class AxolotlTrainer(
 
     args = None  # type: "AxolotlTrainingArguments"  # type: ignore[name-defined]
     tag_names = ["axolotl"]
+    _axolotl_cfg: DictDefault | None = None
+
+    @property
+    def axolotl_cfg(self):
+        return self._axolotl_cfg
+
+    @axolotl_cfg.setter
+    def axolotl_cfg(self, cfg):
+        self._axolotl_cfg = cfg
 
     def __init__(
         self,
@@ -80,7 +88,6 @@ class AxolotlTrainer(
         self._signature_columns = None  # workaround for pylint
 
         super().__init__(*_args, **kwargs)
-
         self.train_data_collator = self.data_collator
         self._stored_metrics = defaultdict(lambda: defaultdict(list))
         if self.args.orpo_alpha:
@@ -285,9 +292,9 @@ class AxolotlTrainer(
         # fmt: off
         if dataloader_key is not None and self.args.dataloader_persistent_workers:
             if hasattr(self, "_eval_dataloaders"):
-                self._eval_dataloaders[dataloader_key] = dataloader  # type: ignore  # pylint: disable=access-member-before-definition
+                self._eval_dataloaders[dataloader_key] = dataloader  # type: ignore
             else:
-                self._eval_dataloaders = {dataloader_key: dataloader}  # pylint: disable=attribute-defined-outside-init
+                self._eval_dataloaders = {dataloader_key: dataloader}
         # fmt: on
 
         return self.accelerator.prepare(dataloader)
@@ -329,6 +336,17 @@ class AxolotlTrainer(
         #     outputs = model(**inputs)
         #     loss = trainer_weighted_loss(outputs, labels, shift_labels=True)
         #     return (loss, outputs) if return_outputs else loss
+
+        # track number of tokens for tokens per second calculation
+        if self.args.include_tkps:
+            inputs_key = "labels" if "labels" in inputs else "input_ids"
+            if hasattr(self.state, "num_tokens"):
+                self.state.num_tokens = (
+                    self.state.num_tokens + (inputs[inputs_key] != -100).sum().cpu()
+                )
+            else:
+                self.state.num_tokens = (inputs[inputs_key] != -100).sum().cpu()
+
         if self.args.orpo_alpha:
             return self.orpo_compute_loss(
                 model,
@@ -443,7 +461,7 @@ class AxolotlTrainer(
         model,
         inputs,
         return_outputs=False,
-        num_items_in_batch=None,  # pylint: disable=unused-argument
+        num_items_in_batch=None,
     ):
         concat_inputs = AxolotlTrainer.orpo_concatenate_inputs(
             inputs,
@@ -524,15 +542,10 @@ class AxolotlTrainer(
         accelerator_config = self.args.accelerator_config.to_dict()
         use_configured_state = accelerator_config.get("use_configured_state", False)
         if not use_configured_state:
-            AcceleratorState._reset_state(  # pylint: disable=protected-access
-                reset_partial_state=True
-            )
+            AcceleratorState._reset_state(reset_partial_state=True)
 
         super().create_accelerator_and_postprocess()
 
-        # now we need to put parallelism_config back on the PartialState since we rely on that info in other places
-        # PartialState().parallelism_config = self.accelerator.state.parallelism_config
-
         if self.is_fsdp_enabled:
             if (
                 "limit_all_gathers" in self.args.fsdp_config
@@ -540,7 +553,6 @@ class AxolotlTrainer(
             ):
                 self.accelerator.state.fsdp_plugin.limit_all_gathers = True
 
-    # pylint: disable=unused-argument
     def additional_accelerator_args(
         self, fp8: bool = False, enable_fsdp_float8_all_gather: bool = False, **kwargs
     ) -> dict[str, Any]:
@@ -581,12 +593,19 @@ class AxolotlTrainer(
             # Add memory usage
             try:
                 active, allocated, reserved = get_gpu_memory_usage()
-                logs["memory/max_mem_active(gib)"] = round(active, 2)
-                logs["memory/max_mem_allocated(gib)"] = round(allocated, 2)
-                logs["memory/device_mem_reserved(gib)"] = round(reserved, 2)
+                logs["memory/max_active (GiB)"] = round(active, 2)
+                logs["memory/max_allocated (GiB)"] = round(allocated, 2)
+                logs["memory/device_reserved (GiB)"] = round(reserved, 2)
             except (ValueError, TypeError, FileNotFoundError):
                 pass
 
+        if self.args.include_tkps and train_eval == "train":
+            # each rank will log its own tokens per second
+            # for logging_steps > 1 we obtain a moving average of this metric
+            logs["tokens_per_second_per_gpu"] = round(
+                self.state.last_tokens_per_second.item() / self.args.logging_steps, 2
+            )
+
         del self._stored_metrics[train_eval]
 
         return super().log(logs, start_time)
@@ -662,6 +681,11 @@ class AxolotlTrainer(
                 LOG.info(
                     "Saving Trainer.data_collator.tokenizer by default as Trainer.processing_class is `None`"
                 )
-                self.data_collator.tokenizer.save_pretrained(output_dir)
+                save_jinja_files = True
+                if self.axolotl_cfg:
+                    save_jinja_files = self.axolotl_cfg.tokenizer_save_jinja_files
+                self.data_collator.tokenizer.save_pretrained(
+                    output_dir, save_jinja_files=save_jinja_files
+                )
             # Good practice: save your training arguments together with the trained model
             torch.save(self.args, os.path.join(output_dir, TRAINING_ARGS_NAME))

src/axolotl/core/trainers/dpo/trainer.py

@@ -101,11 +101,11 @@ class AxolotlDPOTrainer(
     ) -> dict[str, torch.Tensor]:
         if self.args.dpo_norm_loss:
             # fmt: off
-            loss_type: str = self.loss_type  # type: ignore[has-type]  # pylint: disable=access-member-before-definition
+            loss_type: str = self.loss_type  # type: ignore[has-type]
             # fmt: on
             # concatenated_forward handles avg token logprob for ipo case already
-            self.loss_type = "ipo"  # pylint: disable=attribute-defined-outside-init
+            self.loss_type = "ipo"
             res = super().concatenated_forward(model, batch, is_ref_model=is_ref_model)
-            self.loss_type = loss_type  # pylint: disable=attribute-defined-outside-init
+            self.loss_type = loss_type
             return res
         return super().concatenated_forward(model, batch, is_ref_model=is_ref_model)

src/axolotl/core/trainers/grpo/__init__.py

@@ -128,9 +128,7 @@ class GRPOStrategy:
         return grpo_args_kwargs
 
     @classmethod
-    def set_trainer_args(
-        cls, cfg: DictDefault
-    ) -> list[Any]:  # pylint: disable=unused-argument
+    def set_trainer_args(cls, cfg: DictDefault) -> list[Any]:
         trainer_args = []
         if cfg.trl and cfg.trl.reward_funcs:
             reward_funcs = []
@@ -151,7 +149,7 @@ class GRPOStrategy:
         return trainer_kwargs
 
     @classmethod
-    def get_collator(cls, *args, **kwargs):  # pylint: disable=unused-argument
+    def get_collator(cls, *args, **kwargs):
         # No data collation is needed in GRPO, handled by trl's trainer __init__
         return None
 

src/axolotl/core/trainers/grpo/trainer.py

@@ -1,7 +1,5 @@
 """Axolotl GRPO trainers (with and without sequence parallelism handling)"""
 
-# pylint: disable=too-many-lines,duplicate-code,protected-access,no-member
-
 import warnings
 from functools import partial
 from typing import Any
@@ -52,7 +50,6 @@ from axolotl.core.trainers.mixins.optimizer import OptimizerInitMixin, Optimizer
 from axolotl.monkeypatch.ring_attn import get_ring_attn_group
 
 if is_peft_available():
-    # pylint: disable=unused-import
     from peft import PeftConfig
 
 
@@ -253,7 +250,7 @@ class AxolotlGRPOSequenceParallelTrainer(AxolotlGRPOTrainer):
     def get_train_dataloader(self) -> DataLoader:
         """Get dataloader for training"""
         train_dataset = self.train_dataset
-        # pylint: disable=access-member-before-definition
+
         data_collator = self.data_collator  # type: ignore
 
         # Handle dataset preprocessing
@@ -266,7 +263,7 @@ class AxolotlGRPOSequenceParallelTrainer(AxolotlGRPOTrainer):
                     train_dataset, description="training"
                 )
         else:
-            self.data_collator = self._get_collator_with_removed_columns(  # pylint: disable=attribute-defined-outside-init
+            self.data_collator = self._get_collator_with_removed_columns(
                 data_collator,
                 description="training",
             )
@@ -308,10 +305,10 @@ class AxolotlGRPOSequenceParallelTrainer(AxolotlGRPOTrainer):
         # Generate completions using either vLLM or regular generation
         if self.args.use_vllm:
             # First, have main process load weights if needed
-            # pylint: disable=access-member-before-definition
+
             if self.state.global_step != self._last_loaded_step:  # type: ignore[has-type]
                 self._move_model_to_vllm()
-                # pylint: disable=attribute-defined-outside-init
+
                 self._last_loaded_step = self.state.global_step
 
             # Generate completions using vLLM: gather all prompts and use them in a single call in the main process
@@ -333,8 +330,9 @@ class AxolotlGRPOSequenceParallelTrainer(AxolotlGRPOTrainer):
                         # Extract prompts from this SP group, accounting for num_generations duplicates
                         # We only need prompts from one rank in each SP group
                         group_prompts = all_prompts_text[
-                            group_leader_rank
-                            * len(prompts_text) : (group_leader_rank + 1)
+                            group_leader_rank * len(prompts_text) : (
+                                group_leader_rank + 1
+                            )
                             * len(prompts_text) : self.num_generations
                         ]
 
@@ -485,7 +483,7 @@ class AxolotlGRPOSequenceParallelTrainer(AxolotlGRPOTrainer):
         )
         if is_conversational(inputs[0]):
             completions = []
-            for prompt, completion in zip(prompts, completions_text):
+            for prompt, completion in zip(prompts, completions_text, strict=False):
                 bootstrap = (
                     prompt.pop()["content"] if prompt[-1]["role"] == "assistant" else ""
                 )
@@ -503,6 +501,7 @@ class AxolotlGRPOSequenceParallelTrainer(AxolotlGRPOTrainer):
                 self.reward_funcs,
                 self.reward_processing_classes,
                 self.reward_func_names,
+                strict=False,
             )
         ):
             with profiling_context(self, reward_func_name):
@@ -511,14 +510,17 @@ class AxolotlGRPOSequenceParallelTrainer(AxolotlGRPOTrainer):
                 ):  # Module instead of PretrainedModel for compat with compiled models
                     if is_conversational(inputs[0]):
                         messages = [
-                            {"messages": p + c} for p, c in zip(prompts, completions)
+                            {"messages": p + c}
+                            for p, c in zip(prompts, completions, strict=False)
                         ]
                         texts = [
                             apply_chat_template(x, reward_processing_class)["text"]
                             for x in messages
                         ]
                     else:
-                        texts = [p + c for p, c in zip(prompts, completions)]
+                        texts = [
+                            p + c for p, c in zip(prompts, completions, strict=False)
+                        ]
                     reward_inputs = reward_processing_class(
                         text=texts,
                         return_tensors="pt",
@@ -564,7 +566,8 @@ class AxolotlGRPOSequenceParallelTrainer(AxolotlGRPOTrainer):
             row_reward_kwargs["completion"] = completions[nan_row_idx]
             warnings.warn(
                 f"All reward functions returned None for the following kwargs: {row_reward_kwargs}. "
-                "Please ensure that at least one reward function returns a valid reward."
+                "Please ensure that at least one reward function returns a valid reward.",
+                stacklevel=2,
             )
 
         # Gather the reward per function: this part is crucial, because the rewards are normalized per group and the

src/axolotl/core/trainers/mamba.py

@@ -5,7 +5,6 @@ import torch
 from axolotl.core.trainers.base import AxolotlTrainer
 
 
-# pylint: disable=too-many-ancestors
 class AxolotlMambaTrainer(AxolotlTrainer):
     """Mamba specific trainer to handle loss calculation"""
 
@@ -15,8 +14,8 @@ class AxolotlMambaTrainer(AxolotlTrainer):
         self,
         model,
         inputs,
-        return_outputs=False,  # pylint: disable=unused-argument
-        num_items_in_batch=None,  # pylint: disable=unused-argument
+        return_outputs=False,
+        num_items_in_batch=None,
     ):
         input_ids = inputs.pop("input_ids")
         lm_logits = model(input_ids).logits

src/axolotl/core/trainers/mixins/__init__.py

@@ -1,6 +1,5 @@
 """Init for axolotl.core.trainers.mixins"""
 
-# pylint: disable=unused-import
 # flake8: noqa
 
 from .activation_checkpointing import ActivationOffloadingMixin

src/axolotl/core/trainers/mixins/activation_checkpointing.py

@@ -3,11 +3,14 @@ Trainer mixin for activation checkpointing w offloading
 """
 
 import contextlib
+from functools import partial
 
 from peft import PeftModel
 from torch import nn
 from torch.distributed.algorithms._checkpoint.checkpoint_wrapper import (
     apply_activation_checkpointing,
+    checkpoint_wrapper,
+    CheckpointImpl,
 )
 from torch.distributed.fsdp.wrap import ModuleWrapPolicy
 from transformers import GradientCheckpointingLayer, Trainer
@@ -46,9 +49,20 @@ class ActivationOffloadingMixin(Trainer):
             return super().training_step(*args, **kwargs)
 
 
-def ac_wrap_hf_model(model: nn.Module, **kwargs):
+def ac_wrap_hf_model(model: nn.Module, use_reentrant=None, **kwargs):
     auto_wrap_policy = ModuleWrapPolicy(set((GradientCheckpointingLayer,)))
-    apply_activation_checkpointing(model, auto_wrap_policy=auto_wrap_policy, **kwargs)
+    if use_reentrant:
+        checkpoint_wrapper_fn = partial(
+            checkpoint_wrapper, checkpoint_impl=CheckpointImpl.REENTRANT
+        )
+    else:
+        checkpoint_wrapper_fn = checkpoint_wrapper
+    apply_activation_checkpointing(
+        model,
+        checkpoint_wrapper_fn=checkpoint_wrapper_fn,
+        auto_wrap_policy=auto_wrap_policy,
+        **kwargs,
+    )
 
 
 def get_lora_act_offloading_ctx_manager(
@@ -92,7 +106,7 @@ def get_lora_act_offloading_ctx_manager(
         `contextlib.ContextDecorator`:
             Activation offloading context manager for the model.
     """
-    # pylint: disable=unnecessary-dunder-call
+
     activations_handling_ctx = OffloadActivations(
         use_pin_memory=use_pin_memory,
         use_streams=use_streams,

src/axolotl/core/trainers/mixins/distributed_parallel.py

@@ -26,7 +26,6 @@ class DistributedParallelMixin(Trainer):
             self.accelerator.distributed_type == "FSDP"
             and self.accelerator.state.fsdp_plugin is None
         ):
-            # pylint: disable=protected-access
             # handle Context Parallelism without FSDP
             self.accelerator.state.distributed_type = "MULTI_GPU"
             self.accelerator.state._shared_state["distributed_type"] = "MULTI_GPU"

src/axolotl/core/trainers/mixins/optimizer.py

@@ -70,11 +70,11 @@ class OptimizerMixin(Trainer):
                 }
             )
         if params["embeddings"]:
-            lr = optimizer_kwargs["lr"]  # pylint: disable=invalid-name
+            lr = optimizer_kwargs["lr"]
             if self.args.embedding_lr_scale:
-                lr *= self.args.embedding_lr_scale  # pylint: disable=invalid-name
+                lr *= self.args.embedding_lr_scale
             elif self.args.embedding_lr:
-                lr = self.args.embedding_lr  # pylint: disable=invalid-name
+                lr = self.args.embedding_lr
             optimizer_grouped_parameters.append(
                 {
                     "params": list(params["embeddings"].values()),
@@ -143,7 +143,7 @@ class OptimizerMixin(Trainer):
                 loraplus_lr_embedding = getattr(
                     self.args, "loraplus_lr_embedding", 1e-6
                 )
-                self.optimizer = create_loraplus_optimizer(  # pylint: disable=attribute-defined-outside-init
+                self.optimizer = create_loraplus_optimizer(
                     opt_model,
                     optimizer_cls,
                     loraplus_lr_ratio=loraplus_lr_ratio,
@@ -185,17 +185,15 @@ class OptimizerMixin(Trainer):
                                 p.data_ptr(): p.numel() for p in module.parameters()
                             }.values()
                         )
-                        LOG.info(f"skipped {module}: {skipped/2**20}M params")
+                        LOG.info(f"skipped {module}: {skipped / 2**20}M params")
                         manager.register_module_override(
                             module, "weight", {"optim_bits": 32}
                         )
                         LOG.debug(f"bitsandbytes: will optimize {module} in fp32")
-                LOG.info(f"skipped: {skipped/2**20}M params")
+                LOG.info(f"skipped: {skipped / 2**20}M params")
 
         if is_sagemaker_mp_enabled():
-            self.optimizer = smp.DistributedOptimizer(  # pylint: disable=attribute-defined-outside-init
-                self.optimizer
-            )
+            self.optimizer = smp.DistributedOptimizer(self.optimizer)
 
         return self.optimizer
 

src/axolotl/core/trainers/mixins/scheduler.py

@@ -46,7 +46,7 @@ class SchedulerMixin(Trainer):
         )
 
         # fmt: off
-        if self.lr_scheduler is None:  # type: ignore  # pylint: disable=access-member-before-definition
+        if self.lr_scheduler is None:  # type: ignore
             # fmt: on
             plugin_manager = PluginManager.get_instance()
             lr_scheduler: LRScheduler | None = plugin_manager.create_lr_scheduler(
@@ -90,7 +90,7 @@ class SchedulerMixin(Trainer):
                     LOG.warning(
                         "Both cosine quadratic warmup and min lr detected. Using quadratic warmup.")
 
-                self.lr_scheduler = get_cosine_schedule_with_quadratic_warmup(  # pylint: disable=attribute-defined-outside-init
+                self.lr_scheduler = get_cosine_schedule_with_quadratic_warmup(
                     optimizer,
                     num_warmup_steps=self.args.get_warmup_steps(num_training_steps),
                     num_training_steps=num_training_steps,
@@ -98,7 +98,7 @@ class SchedulerMixin(Trainer):
             elif self.args.cosine_min_lr_ratio and self.args.cosine_constant_lr_ratio and use_cosine_min_lr:
                 assert 0 <= self.args.cosine_min_lr_ratio <= 1.0, "cosine_min_lr_ratio must be between 0.0 and 1.0"
                 assert 0 <= self.args.cosine_constant_lr_ratio <= 1.0, "cosine_constant_lr_ratio must be between 0.0 and 1.0"
-                self.lr_scheduler = get_cosine_schedule_with_warmup_decay_constant(  # pylint: disable=attribute-defined-outside-init
+                self.lr_scheduler = get_cosine_schedule_with_warmup_decay_constant(
                     optimizer,
                     num_warmup_steps=self.args.get_warmup_steps(num_training_steps),
                     num_training_steps=num_training_steps,
@@ -107,7 +107,7 @@ class SchedulerMixin(Trainer):
                 )
             elif self.args.cosine_min_lr_ratio and use_cosine_min_lr:
                 assert 0 <= self.args.cosine_min_lr_ratio <= 1.0, "cosine_min_lr_ratio must be between 0.0 and 1.0"
-                self.lr_scheduler = get_cosine_schedule_with_min_lr(  # pylint: disable=attribute-defined-outside-init
+                self.lr_scheduler = get_cosine_schedule_with_min_lr(
                     optimizer,
                     num_warmup_steps=self.args.get_warmup_steps(num_training_steps),
                     num_training_steps=num_training_steps,
@@ -133,7 +133,7 @@ class SchedulerMixin(Trainer):
             )
             if not self.lr_scheduler:
                 super().create_scheduler(num_training_steps, optimizer)
-            self.lr_scheduler = JaggedLRRestartScheduler(  # pylint: disable=attribute-defined-outside-init
+            self.lr_scheduler = JaggedLRRestartScheduler(
                 optimizer,
                 self.lr_scheduler,
                 self.args.jagged_restart_steps,

src/axolotl/core/training_args_base.py

@@ -14,7 +14,6 @@ class AxolotlTrainingMixins:
     Mixin class for the Axolotl training args.
     """
 
-    # pylint: disable=duplicate-code
     model_type: Optional[str] = field(
         default=None, metadata={"help": "HF model configuration model_type."}
     )
@@ -50,6 +49,12 @@ class AxolotlTrainingMixins:
         default=False,
         metadata={"help": "Use real batches for efficient training."},
     )
+    include_tkps: bool = field(
+        default=True,
+        metadata={
+            "help": "Whether to include tokens per second in the training metrics."
+        },
+    )
     eval_sample_packing: Optional[bool] = field(
         default=None,
         metadata={"help": "Use sample packing for efficient evals."},

src/axolotl/datasets.py

@@ -1,18 +1,17 @@
-"""Module containing Dataset functionality"""
+"""
+Module containing dataset functionality.
+
+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. We'll use the collators later on to pad the
+datasets.
+"""
 
-import torch
 from datasets import Dataset, IterableDataset
 
 from axolotl.utils.logging import get_logger
 
 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
-# ConstantLengthDataset(ShuffledDataset([TokenizedPromptDataset(alpaca_dataset)]))
-# 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 = get_logger(__name__)
 
 
@@ -26,7 +25,7 @@ class TokenizedPromptDataset(Dataset):
         keep_in_memory: Whether to keep the tokenized dataset in memory.
     """
 
-    def __init__(  # pylint: disable=super-init-not-called
+    def __init__(
         self,
         prompt_tokenizer: PromptTokenizingStrategy,
         dataset: Dataset,
@@ -86,133 +85,3 @@ def wrap_dataset_for_tokenized_prompt(
             **map_kwargs,
         )
     return TokenizedPromptDataset(prompt_tokenizer, dataset, **kwargs)
-
-
-# TODO this isn't the best since it can't interleave datasets
-class ConstantLengthDataset(IterableDataset):
-    """Iterable dataset that returns constant length chunks of tokens from stream of
-    text files.
-
-    Args:
-        tokenizer: The processor used for processing the data.
-        dataset: Dataset with text files.
-        seq_length: Length of token sequences to return.
-    """
-
-    def __init__(  # pylint: disable=super-init-not-called
-        self,
-        tokenizer,
-        datasets,
-        seq_length=2048,
-    ):
-        self.tokenizer = tokenizer
-        self.concat_token_id = tokenizer.eos_token_id
-        self.datasets: list[IterableDataset] = datasets
-        self.seq_length = seq_length
-
-        vocab_size = len(tokenizer.get_vocab())
-
-        if vocab_size <= torch.iinfo(torch.int16).max:
-            self.tokens_dtype = torch.int16
-        elif vocab_size <= torch.iinfo(torch.int32).max:
-            self.tokens_dtype = torch.int32
-        else:
-            self.tokens_dtype = torch.int64
-
-    def __iter__(self):
-        buffer = {
-            "input_ids": [],
-            "attention_mask": [],
-            "labels": [],
-            "position_ids": [],
-        }
-        buffer_len = 0
-        for dataset in self.datasets:
-            idx = 0
-            iterator = iter(dataset)
-            more_examples = True
-            while more_examples:
-                try:
-                    example = next(iterator)
-                    idx += 1
-                except StopIteration:
-                    more_examples = False
-                    example = None
-
-                add_concat_token = False
-                if example:
-                    example_len = len(example["input_ids"])
-                    add_concat_token = example["input_ids"][-1] != self.concat_token_id
-                else:
-                    example_len = 0
-
-                if not example_len or (
-                    buffer_len + int(add_concat_token) + example_len > self.seq_length
-                ):
-                    if buffer["input_ids"]:
-                        input_ids = torch.cat(buffer["input_ids"], dim=-1)[
-                            : self.seq_length
-                        ]
-                        attention_mask = torch.cat(buffer["attention_mask"], dim=-1)[
-                            : self.seq_length
-                        ]
-                        position_ids = torch.cat(buffer["position_ids"], dim=-1)[
-                            : self.seq_length
-                        ]
-                        labels = torch.cat(buffer["labels"], dim=-1)[: self.seq_length]
-                        if labels.size() == input_ids.size() and (
-                            attention_mask.size() == input_ids.size()
-                        ):
-                            yield {
-                                "input_ids": input_ids,
-                                "labels": labels,
-                                "attention_mask": attention_mask,
-                                "position_ids": position_ids,
-                            }
-                        else:
-                            LOG.warning(
-                                "Dropping batch due to tensor size mismatch "
-                                f"input_ids: {input_ids.size()}, "
-                                f"labels: {labels.size()}, "
-                                f"attention_mask: {attention_mask.size()}"
-                            )
-                    buffer = {
-                        "input_ids": [],
-                        "attention_mask": [],
-                        "labels": [],
-                        "position_ids": [],
-                    }
-                    buffer_len = 0
-                    idx = 1
-
-                if example:
-                    # FIXME
-                    # just going to drop data points that are too long
-                    if len(example["input_ids"]) <= self.seq_length:
-                        input_ids = example["input_ids"]
-                        attention_mask = example["attention_mask"]
-                        labels = example["labels"]
-
-                        if add_concat_token:
-                            input_ids.append(self.concat_token_id)
-                            attention_mask.append(1)
-                            labels.append(self.concat_token_id)
-
-                        input_ids_with_concat = torch.tensor(
-                            input_ids, dtype=self.tokens_dtype
-                        )
-                        attention_mask_with_concat = torch.tensor(
-                            [idx * m for m in attention_mask], dtype=torch.int16
-                        )
-                        labels_with_concat = torch.tensor(
-                            labels, dtype=self.tokens_dtype
-                        )
-                        position_ids = torch.arange(
-                            len(input_ids), dtype=self.tokens_dtype
-                        )
-
-                        buffer["input_ids"].append(input_ids_with_concat)
-                        buffer["attention_mask"].append(attention_mask_with_concat)
-                        buffer["labels"].append(labels_with_concat)
-                        buffer["position_ids"].append(position_ids)
-                        buffer_len += len(input_ids)

src/axolotl/evaluate.py

@@ -79,7 +79,7 @@ def evaluate(*, cfg: DictDefault, dataset_meta: TrainDatasetMeta) -> Dict[str, f
     model, tokenizer, _, processor = setup_model_and_tokenizer(cfg)
 
     # Get datasets
-    # pylint: disable=duplicate-code
+
     train_dataset = dataset_meta.train_dataset
     eval_dataset = dataset_meta.eval_dataset
     total_num_steps = dataset_meta.total_num_steps

src/axolotl/integrations/base.py

@@ -76,7 +76,7 @@ class BasePlugin:
     def __init__(self):
         """Initializes the BasePlugin."""
 
-    def register(self, cfg: dict):  # pylint: disable=unused-argument
+    def register(self, cfg: dict):
         """Registers the plugin with the given configuration as an unparsed dict.
 
         Args:
@@ -104,14 +104,13 @@ class BasePlugin:
             dataset_meta: The metadata for the training dataset.
         """
 
-    def pre_model_load(self, cfg: DictDefault):  # pylint: disable=unused-argument
+    def pre_model_load(self, cfg: DictDefault):
         """Performs actions before the model is loaded.
 
         Args:
             cfg: The configuration for the plugin.
         """
 
-    # pylint: disable=unused-argument
     def post_model_build(self, cfg: DictDefault, model: PreTrainedModel):
         """Performs actions after the model is built/loaded, but before any adapters are applied.
 
@@ -119,7 +118,6 @@ class BasePlugin:
             cfg: The configuration for the plugin.
         """
 
-    # pylint: disable=unused-argument
     def pre_lora_load(self, cfg: DictDefault, model: PreTrainedModel):
         """Performs actions before LoRA weights are loaded.
 
@@ -128,7 +126,6 @@ class BasePlugin:
             model: The loaded model.
         """
 
-    # pylint: disable=unused-argument
     def post_lora_load(self, cfg: DictDefault, model: PreTrainedModel | PeftModel):
         """Performs actions after LoRA weights are loaded.
 
@@ -137,7 +134,6 @@ class BasePlugin:
             model: The loaded model.
         """
 
-    # pylint: disable=unused-argument
     def post_model_load(self, cfg: DictDefault, model: PreTrainedModel | PeftModel):
         """Performs actions after the model is loaded.
 
@@ -146,7 +142,6 @@ class BasePlugin:
             model: The loaded model.
         """
 
-    # pylint: disable=unused-argument
     def get_trainer_cls(self, cfg: DictDefault) -> Trainer | None:
         """Returns a custom class for the trainer.
 
@@ -157,7 +152,6 @@ class BasePlugin:
             The first non-`None` trainer class returned by a plugin.
         """
 
-    # pylint: disable=unused-argument
     def post_trainer_create(self, cfg: DictDefault, trainer: Trainer):
         """Performs actions after the trainer is created.
 
@@ -166,7 +160,7 @@ class BasePlugin:
             trainer: The trainer object for training.
         """
 
-    def get_training_args(self, cfg: DictDefault):  # pylint: disable=unused-argument):
+    def get_training_args(self, cfg: DictDefault):
         """
         Returns custom training arguments to set on TrainingArgs.
 
@@ -177,9 +171,7 @@ class BasePlugin:
             object: dict containing the training arguments.
         """
 
-    def get_collator_cls_and_kwargs(
-        self, cfg: DictDefault, is_eval: bool = False
-    ):  # pylint: disable=unused-argument):
+    def get_collator_cls_and_kwargs(self, cfg: DictDefault, is_eval: bool = False):
         """
         Returns a custom class for the collator.
 
@@ -191,7 +183,6 @@ class BasePlugin:
             class: The class for the collator.
         """
 
-    # pylint: disable=unused-argument
     def create_optimizer(self, cfg: DictDefault, trainer: Trainer) -> Optimizer | None:
         """Creates and returns an optimizer for training.
 
@@ -203,7 +194,6 @@ class BasePlugin:
             The created optimizer.
         """
 
-    # pylint: disable=unused-argument
     def create_lr_scheduler(
         self,
         cfg: DictDefault,
@@ -223,7 +213,6 @@ class BasePlugin:
             The created learning rate scheduler.
         """
 
-    # pylint: disable=unused-argument
     def add_callbacks_pre_trainer(
         self, cfg: DictDefault, model: PreTrainedModel
     ) -> list[Callable]:
@@ -238,7 +227,6 @@ class BasePlugin:
         """
         return []
 
-    # pylint: disable=unused-argument
     def add_callbacks_post_trainer(
         self, cfg: DictDefault, trainer: Trainer
     ) -> list[Callable]:
@@ -254,7 +242,6 @@ class BasePlugin:
         """
         return []
 
-    # pylint: disable=unused-argument
     def post_train(self, cfg: DictDefault, model: PreTrainedModel | PeftModel):
         """Performs actions after training is complete.
 
@@ -263,7 +250,7 @@ class BasePlugin:
             model: The loaded model.
         """
 
-    def post_train_unload(self, cfg: DictDefault):  # pylint: disable=unused-argument
+    def post_train_unload(self, cfg: DictDefault):
         """Performs actions after training is complete and the model is unloaded.
 
         Args:
@@ -311,7 +298,7 @@ def load_plugin(plugin_name: str) -> BasePlugin:
     return plugin
 
 
-class PluginManager:  # pylint: disable=too-many-public-methods
+class PluginManager:
     """The `PluginManager` class is responsible for loading and managing plugins. It
     should be a singleton so it can be accessed from anywhere in the codebase.
 

src/axolotl/integrations/config.py

@@ -50,15 +50,9 @@ def merge_input_args():
         dynamic_input += f"class AxolotlInputConfig(AxolotlInputConfigBase, {', '.join(plugin_classes)}):\n    pass\n"
 
         namespace: Dict[Any, Any] = {}
-        exec(  # pylint: disable=exec-used  # nosec B102
-            dynamic_input, globals(), namespace
-        )
-        AxolotlInputConfig = namespace[  # pylint: disable=invalid-name
-            "AxolotlInputConfig"
-        ]
-        AxolotlConfigWCapabilities = namespace[  # pylint: disable=invalid-name
-            "AxolotlConfigWCapabilities"
-        ]
+        exec(dynamic_input, globals(), namespace)  # nosec B102
+        AxolotlInputConfig = namespace["AxolotlInputConfig"]
+        AxolotlConfigWCapabilities = namespace["AxolotlConfigWCapabilities"]
         return AxolotlConfigWCapabilities, AxolotlInputConfig
     return AxolotlConfigWCapabilitiesBase, AxolotlInputConfigBase
 
@@ -74,7 +68,7 @@ def merge_training_args() -> Type:
     Returns:
     tuple: A tuple containing the newly created classes, AxolotlTrainingMixins.
     """
-    # pylint: disable=duplicate-code
+
     from axolotl.core.training_args_base import (
         AxolotlTrainingMixins as AxolotlTrainingMixinsBase,
     )
@@ -93,11 +87,7 @@ def merge_training_args() -> Type:
 
         namespace: Dict[Any, Any] = {}
         local_vars = {"AxolotlTrainingMixinsBase": AxolotlTrainingMixinsBase}
-        exec(  # pylint: disable=exec-used  # nosec B102
-            dynamic_input, {**globals(), **local_vars}, namespace
-        )
-        AxolotlTrainingMixins = namespace[  # pylint: disable=invalid-name
-            "AxolotlTrainingMixins"
-        ]
+        exec(dynamic_input, {**globals(), **local_vars}, namespace)  # nosec B102
+        AxolotlTrainingMixins = namespace["AxolotlTrainingMixins"]
         return AxolotlTrainingMixins
     return AxolotlTrainingMixinsBase

src/axolotl/integrations/cut_cross_entropy/README.md

@@ -19,7 +19,7 @@ python scripts/cutcrossentropy_install.py | sh
 
 - If you are installing from pip
 ```bash
-pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@0ee9ee8"
+pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@c6a32c5"
 ```
 
 ## Usage

src/axolotl/integrations/cut_cross_entropy/__init__.py

@@ -18,6 +18,7 @@ Module for the Plugin for Cut Cross Entropy integration with Axolotl.
 Cut Cross Entropy is an optimized implementation of cross entropy loss
 from Apple's ML team.
 """
+
 import importlib
 from functools import partial
 
@@ -28,13 +29,13 @@ from axolotl.utils import get_pytorch_version
 from axolotl.utils.callbacks.models import get_causal_lm_model_cls_prefix
 from axolotl.utils.logging import get_logger
 
-from .args import CutCrossEntropyArgs  # pylint: disable=unused-import. # noqa: F401
+from .args import CutCrossEntropyArgs as CutCrossEntropyArgs
 
 LOG = get_logger(__name__)
 
 _CCE_INSTALL_MESSAGE = (
     "Please install Axolotl's fork of cut_cross_entropy with transformers support using "
-    '`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@0ee9ee8"`'
+    '`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@c6a32c5"`'
 )
 
 
@@ -106,9 +107,7 @@ class CutCrossEntropyPlugin(BasePlugin):
         """
         from cut_cross_entropy.transformers.patch import PATCH_FNS
 
-        def patch_generic(
-            maybe_model, patch_options, model_type: str
-        ):  # pylint: disable=unused-argument
+        def patch_generic(maybe_model, patch_options, model_type: str):
             import cut_cross_entropy.transformers.llama
             from cut_cross_entropy.transformers.llama import cce_forward
 
@@ -121,12 +120,10 @@ class CutCrossEntropyPlugin(BasePlugin):
                 )
                 model_cls = getattr(module, f"{model_cls_prefix}ForCausalLM")
 
-                cut_cross_entropy.transformers.llama._PATCH_OPTS = (  # pylint: disable=protected-access
-                    patch_options
-                )
+                cut_cross_entropy.transformers.llama._PATCH_OPTS = patch_options
 
                 model_cls.forward = cce_forward
-            # pylint: disable=duplicate-code
+
             except (ImportError, AttributeError) as e:
                 raise RuntimeError(
                     f"Could not import ForCausalLM class for model_type: {model_type}. "

src/axolotl/integrations/cut_cross_entropy/args.py

@@ -15,6 +15,7 @@
 """
 Module for handling Cut Cross Entropy input arguments.
 """
+
 from typing import Optional
 
 from pydantic import BaseModel, model_validator

src/axolotl/integrations/grokfast/__init__.py

@@ -7,7 +7,7 @@ from transformers.trainer_callback import TrainerCallback
 from axolotl.utils.logging import get_logger
 
 from ..base import BasePlugin
-from .args import GrokfastArgs  # pylint: disable=unused-import. # noqa: F401
+from .args import GrokfastArgs as GrokfastArgs
 from .optimizer import gradfilter_ema
 
 LOG = get_logger(__name__)
@@ -24,12 +24,10 @@ class GrokfastCallbackHandler(TrainerCallback):
         self.alpha = alpha
         self.lamb = lamb
 
-    def on_train_begin(self, *args_, **kwargs):  # pylint: disable=unused-argument
+    def on_train_begin(self, *args_, **kwargs):
         self.grads = None
 
-    def on_pre_optimizer_step(
-        self, args_, state, control, **kwargs
-    ):  # pylint: disable=unused-argument
+    def on_pre_optimizer_step(self, args_, state, control, **kwargs):
         model = kwargs.pop("model")
         self.grads = gradfilter_ema(model, self.grads, alpha=self.alpha, lamb=self.lamb)
         return control

src/axolotl/integrations/grokfast/optimizer.py

@@ -1,7 +1,6 @@
 # Copyright: MIT License (c) 2024 Jaerin Lee, Bong Gyun Kang, Kihoon Kim, Kyoung Mu Lee
 # Reference: https://github.com/ironjr/grokfast
 
-# pylint: skip-file
 from collections import deque
 from typing import Dict, Literal, Optional
 

src/axolotl/integrations/kd/__init__.py

@@ -15,6 +15,7 @@
 """
 Plugin init to add KD support to Axolotl.
 """
+
 from typing import Any
 
 from transformers import Trainer
@@ -22,7 +23,7 @@ from transformers import Trainer
 from axolotl.integrations.base import BasePlugin
 from axolotl.integrations.kd.callbacks import KDTemperatureSchedulerCallback
 
-from .args import KDArgs  # pylint: disable=unused-import. # noqa: F401
+from .args import KDArgs as KDArgs
 
 
 class KDPlugin(BasePlugin):

src/axolotl/integrations/kd/args.py

@@ -15,6 +15,7 @@
 """
 Plugin args for KD support.
 """
+
 from dataclasses import dataclass
 from enum import Enum
 
@@ -26,8 +27,8 @@ class InferenceServerType(str, Enum):
     Online inferences server types to handle different request args
     """
 
-    vllm = "vllm"  # pylint: disable=invalid-name
-    sglang = "sglang"  # pylint: disable=invalid-name
+    vllm = "vllm"
+    sglang = "sglang"
 
 
 class KDArgs(BaseModel):

src/axolotl/integrations/kd/callbacks.py

@@ -19,9 +19,7 @@ class KDTemperatureSchedulerCallback(TrainerCallback):
 
         self.trainer = trainer
 
-    def on_step_end(
-        self, args, state, control, **kwargs
-    ):  # pylint: disable=unused-argument
+    def on_step_end(self, args, state, control, **kwargs):
         # cosine decay temperature over the max steps
 
         progress = state.global_step / state.max_steps

src/axolotl/integrations/kd/chat_template.py

@@ -15,6 +15,7 @@
 """
 Chat template prompt strategy loader with KD support
 """
+
 import logging
 from typing import Any, Dict
 
@@ -192,7 +193,6 @@ class ChatTemplateStrategyWithKDv2(ChatTemplateStrategyWithKD):
         """
         Transform logprobs to target format for KD training
         """
-        # pylint: disable=duplicate-code
 
         logprobs = sample.pop(self.logprobs_field)
         target_seq_len = len(logprobs)
@@ -240,7 +240,7 @@ class ChatTemplateStrategyWithKDv2(ChatTemplateStrategyWithKD):
                 target_mask.append([1] * top_k)
 
         for token_pos_logprobs, pos_target_token_ids in zip(
-            logprobs, sample["target_token_ids"]
+            logprobs, sample["target_token_ids"], strict=False
         ):
             # Convert to a tensor for easier manipulation
             position_logprobs_tensor = torch.tensor(
@@ -299,7 +299,7 @@ class KDStrategyLoader(StrategyLoader):
     Load ChatTemplateStrategy with KD support using StrategyLoader.
     """
 
-    def _get_strategy_cls(self, cfg):  # pylint: disable=unused-argument
+    def _get_strategy_cls(self, cfg):
         return ChatTemplateStrategyWithKD
 
     def _get_strategy_params(self, cfg, ds_cfg: Dict[str, Any]):
@@ -319,7 +319,7 @@ class KDStrategyLoaderV2(KDStrategyLoader):
     Load KD chat template datasets with pre-tokenized logprob data
     """
 
-    def _get_strategy_cls(self, cfg):  # pylint: disable=unused-argument
+    def _get_strategy_cls(self, cfg):
         return ChatTemplateStrategyWithKDv2
 
 

src/axolotl/integrations/kd/collator.py

@@ -37,7 +37,6 @@ class DataCollatorForKD(DataCollatorForSeq2Seq):
     target_logprobs. It also creates a teacher_mask to indicate which entries are valid.
     """
 
-    # pylint: disable=duplicate-code
     tokenizer: PreTrainedTokenizerBase
     model: Optional[Any] = None
     padding: Union[bool, str, PaddingStrategy] = True
@@ -72,7 +71,7 @@ class DataCollatorForKD(DataCollatorForSeq2Seq):
                         // self.pad_to_multiple_of
                     ) * self.pad_to_multiple_of
 
-                for f in features:  # pylint: disable=invalid-name
+                for f in features:
                     remainder = [pad_token_id] * (max_len - len(f[feature_name]))
                     if isinstance(f[feature_name], list):
                         f[feature_name] = (
@@ -101,7 +100,7 @@ class DataCollatorForKD(DataCollatorForSeq2Seq):
 
         if has_teacher_data:
             # Extract and remove from features
-            for f in features:  # pylint: disable=invalid-name
+            for f in features:
                 target_logprobs_list.append(f.pop("target_logprobs"))
                 target_token_ids_list.append(f.pop("target_token_ids"))
                 target_mask_list.append(f.pop("target_mask"))
@@ -117,24 +116,25 @@ class DataCollatorForKD(DataCollatorForSeq2Seq):
             padded_teacher_mask_list = []
 
             for t_logprobs, t_ids, t_mask in zip(
-                target_logprobs_list, target_token_ids_list, target_mask_list
+                target_logprobs_list,
+                target_token_ids_list,
+                target_mask_list,
+                strict=False,
             ):
                 t_logprobs_padded = []
                 t_ids_padded = []
                 t_mask_padded = []
 
-                for lp, ids, mask in zip(  # pylint: disable=invalid-name
-                    t_logprobs, t_ids, t_mask
-                ):
+                for lp, ids, mask in zip(t_logprobs, t_ids, t_mask, strict=False):
                     lp_len = len(lp)
                     if lp_len < max_k:
                         # Use -1e9 for padding logprobs and 0 for token_ids
                         pad_len = max_k - lp_len
-                        lp = lp + [-1e9] * pad_len  # pylint: disable=invalid-name
+                        lp = lp + [-1e9] * pad_len
                         ids = ids + [0] * pad_len
                         mask = mask + [0] * pad_len
                     else:
-                        lp = lp[:max_k]  # pylint: disable=invalid-name
+                        lp = lp[:max_k]
                         ids = ids[:max_k]
                         mask = mask[:max_k]
 
@@ -216,9 +216,7 @@ class KDBatchSamplerDataCollatorForSeq2Seq(DataCollatorForKD):
         #    We want to produce a single "merged" feature dict for each sub-batch.
         out_features = [{} for _ in features]
 
-        for i, sub_features in enumerate(  # pylint: disable=too-many-nested-blocks
-            features
-        ):
+        for i, sub_features in enumerate(features):
             # sub_features is a list of dicts, each dict = one sequence’s features
             # We'll merge them into out_features[i].
             #
@@ -255,9 +253,7 @@ class KDBatchSamplerDataCollatorForSeq2Seq(DataCollatorForKD):
                         if field_name in feat and isinstance(
                             feat[field_name], (list, torch.Tensor)
                         ):
-                            if isinstance(
-                                feat[field_name][0], (dict, str)
-                            ):  # pylint: disable=too-many-nested-blocks
+                            if isinstance(feat[field_name][0], (dict, str)):
                                 continue
                             arr = np.array(feat[field_name])
                             arrays.append(arr)

src/axolotl/integrations/kd/collator_online_teacher.py

@@ -144,7 +144,7 @@ class OnlineTeacherCollator(KDBatchSamplerDataCollatorForSeq2Seq):
                 }
 
             for sequence_data, seq_input_ids, seq_labels in zip(
-                api_data, batch_input_ids, labels
+                api_data, batch_input_ids, labels, strict=False
             ):
                 current_target_logprobs = []
                 current_target_token_ids = []
@@ -165,7 +165,7 @@ class OnlineTeacherCollator(KDBatchSamplerDataCollatorForSeq2Seq):
                 assert len(seq_input_ids) == len(input_top_logprobs)
 
                 for i, _, label in zip(
-                    range(len(seq_input_ids)), seq_input_ids, seq_labels
+                    range(len(seq_input_ids)), seq_input_ids, seq_labels, strict=False
                 ):
                     if i < len(input_top_logprobs) and input_top_logprobs[i] is None:
                         # this is always the case for the first token.
@@ -202,7 +202,8 @@ class OnlineTeacherCollator(KDBatchSamplerDataCollatorForSeq2Seq):
 
                         # pos_top_logprobs: list of logprobs, pos_token_ids: list of token_ids
                         pos_logprobs_raw, pos_token_ids, _ = [
-                            list(row) for row in zip(*pos_top_logprobs_data)
+                            list(row)
+                            for row in zip(*pos_top_logprobs_data, strict=False)
                         ]
 
                         # Ensure correct length (top_k)
@@ -317,7 +318,7 @@ class OnlineTeacherCollator(KDBatchSamplerDataCollatorForSeq2Seq):
                 }
 
             for sequence_data, seq_input_ids, seq_labels in zip(
-                choices, batch_input_ids, labels
+                choices, batch_input_ids, labels, strict=False
             ):
                 # seq_input_ids: List[int]
                 # seq_labels: List[int]
@@ -342,7 +343,9 @@ class OnlineTeacherCollator(KDBatchSamplerDataCollatorForSeq2Seq):
 
                 seq_len = len(seq_input_ids)
 
-                for i, _, label in zip(range(seq_len), seq_input_ids, seq_labels):
+                for i, _, label in zip(
+                    range(seq_len), seq_input_ids, seq_labels, strict=False
+                ):
                     if i < len(input_top_logprobs) and input_top_logprobs[i] is None:
                         # this is always the case for the first token.
                         # there is never logprob data for the first token since that's a true input
@@ -424,7 +427,7 @@ class OnlineTeacherCollator(KDBatchSamplerDataCollatorForSeq2Seq):
                             list(range(self.kd_online_topk))
                         )
                         current_target_mask.append([0] * self.kd_online_topk)
-                for i in range(max(0, seq_len - len(current_target_logprobs))):
+                for _ in range(max(0, seq_len - len(current_target_logprobs))):
                     current_target_logprobs.append(
                         [-float("inf")] * self.kd_online_topk
                     )

src/axolotl/integrations/kd/kernels/liger.py

@@ -197,7 +197,7 @@ class LigerFusedLinearKLTopKLogprobFunction(LigerFusedLinearDistillationBase):
         compute_ce_loss: bool = True,
         normalize_topk: bool = True,
     ):
-        CHUNK_SIZE = chunk_size  # pylint: disable=invalid-name
+        CHUNK_SIZE = chunk_size
         grad_weight_acc = torch.zeros_like(student_lm_head_weight)
         grad_inputs_list = []
         grad_bias_acc = (
@@ -298,8 +298,8 @@ class LigerFusedLinearKLTopKLogprobFunction(LigerFusedLinearDistillationBase):
             accumulate_chunk_grads_compiled = accumulate_chunk_grads
 
         # Use the same chunking logic as LigerFusedLinearDistillationBase.forward
-        B, N, D = student_input.shape  # pylint: disable=invalid-name
-        K = target_token_ids.shape[-1]  # pylint: disable=invalid-name
+        B, N, D = student_input.shape
+        K = target_token_ids.shape[-1]
 
         student_input_flat = student_input.reshape(-1, student_input.shape[-1])
         target_token_ids_flat = target_token_ids.reshape(-1, target_token_ids.shape[-1])

src/axolotl/integrations/kd/kernels/models.py

@@ -40,10 +40,9 @@ def kldiv_forward_llama_like(
     output_attentions: Optional[bool] = None,
     output_hidden_states: Optional[bool] = None,
     cache_position: Optional[torch.LongTensor] = None,
-    logits_to_keep: Union[int, torch.Tensor] = 0,  # pylint: disable=unused-argument
+    logits_to_keep: Union[int, torch.Tensor] = 0,
     **kwargs: Unpack[TransformersKwargs],  # type: ignore[misc]
 ) -> CausalLMOutputWithPast:
-    # pylint: disable=duplicate-code
     output_attentions = (
         output_attentions
         if output_attentions is not None

src/axolotl/integrations/kd/topk_logprob/forward_kl.py

@@ -15,6 +15,7 @@
 """
 loss for top_k KL divergence
 """
+
 import torch
 from torch import nn
 
@@ -117,7 +118,6 @@ class ChunkedTopKKDLoss(nn.Module):
         target_mask: torch.Tensor,  # [B, seq_len, K]
         num_items_in_batch: int = -1,  # optional batch size for normalization
     ) -> torch.Tensor:
-
         # 1. Split along the "token" dimension (dim=1).
         student_logits_chunks = student_logits.chunk(self.num_output_chunks, dim=1)
         token_ids_chunks = target_token_ids.chunk(self.num_output_chunks, dim=1)
@@ -131,7 +131,11 @@ class ChunkedTopKKDLoss(nn.Module):
 
         # 2. Loop over each chunk and compute a chunk-specific loss.
         for st_chunk, tid_chunk, lp_chunk, msk_chunk in zip(
-            student_logits_chunks, token_ids_chunks, logprobs_chunks, mask_chunks
+            student_logits_chunks,
+            token_ids_chunks,
+            logprobs_chunks,
+            mask_chunks,
+            strict=False,
         ):
             # We pass num_items_in_batch=-1 so that the kd_loss
             # will average over *this chunk's* valid tokens only.

src/axolotl/integrations/kd/trainer.py

@@ -21,7 +21,6 @@ from axolotl.core.trainers.base import AxolotlTrainer
 from .kernels.liger import LigerFusedLinearKLTopKLogprobLoss
 
 
-# pylint: disable=too-many-ancestors
 class AxolotlKDTrainer(AxolotlTrainer):
     """
     Custom trainer subclass for Knowledge Distillation (KD)

src/axolotl/integrations/liger/__init__.py

@@ -18,6 +18,7 @@ Module for the Plugin for LIGER integraton with Axolotl.
 Liger Kernel is the collection of Triton-native kernels for LLM Training.
 It is designed to be performant, correct, and light-weight.
 """
+
 from .args import LigerArgs
 from .plugin import LigerPlugin
 

src/axolotl/integrations/liger/models/base.py

@@ -41,7 +41,6 @@ def lce_forward(
             This is useful when using packed tensor format (single dimension for batch and sequence length).
     """
 
-    # pylint: disable=duplicate-code
     output_attentions = (
         output_attentions
         if output_attentions is not None
@@ -181,7 +180,7 @@ def patch_lce_forward(
         model_cls = getattr(module, f"{model_cls_prefix}ForCausalLM")
 
         model_cls.forward = lce_forward
-    # pylint: disable=duplicate-code
+
     except (ImportError, AttributeError) as e:
         raise RuntimeError(
             f"Could not import ForCausalLM class for model_type: {model_type}. "

src/axolotl/integrations/liger/models/deepseekv2.py

@@ -2,8 +2,6 @@
 DeepseekV2 model with LigerFusedLinearCrossEntropyLoss
 """
 
-# pylint: disable=duplicate-code
-
 from typing import List, Optional, Tuple, Union
 
 import torch

src/axolotl/integrations/liger/models/jamba.py

@@ -2,8 +2,6 @@
 Jamba model with LigerFusedLinearCrossEntropyLoss
 """
 
-# pylint: disable=duplicate-code
-
 from typing import Optional, Tuple, Union
 
 import torch

src/axolotl/integrations/liger/models/llama4.py

@@ -46,7 +46,6 @@ def lce_forward(
     Returns:
     """
 
-    # pylint: disable=duplicate-code
     output_attentions = (
         output_attentions
         if output_attentions is not None
@@ -78,9 +77,7 @@ def lce_forward(
     hidden_states = outputs[0]
 
     if hasattr(self.config, "pretraining_tp") and self.config.pretraining_tp > 1:
-        raise Exception(  # pylint: disable=broad-exception-raised
-            "Liger Kernel does not support pretraining_tp!!"
-        )
+        raise Exception("Liger Kernel does not support pretraining_tp!!")
 
     logits = None
     loss = None
@@ -128,7 +125,7 @@ def apply_liger_kernel_to_llama4(
     rms_norm: bool = False,
     glu_activation: bool = False,
     layer_norm: bool = False,
-    **kwargs,  # pylint: disable=unused-argument
+    **kwargs,
 ) -> None:
     """
     Apply Liger kernels to replace original implementation in HuggingFace Llama models (2 and 3)
@@ -144,15 +141,15 @@ def apply_liger_kernel_to_llama4(
         layer_norm (bool): Whether to apply Liger's LayerNorm. Default is False.
     """
 
-    import transformers.models.llama4.modeling_llama4  # noqa: F401  # pylint: disable=unused-import
+    import transformers.models.llama4.modeling_llama4  # noqa: F401
     from liger_kernel.transformers.functional import liger_cross_entropy
     from liger_kernel.transformers.layer_norm import LigerLayerNorm
     from liger_kernel.transformers.rms_norm import LigerRMSNorm
     from liger_kernel.transformers.swiglu import LigerSwiGLUMLP
 
-    assert not (
-        cross_entropy and fused_linear_cross_entropy
-    ), "cross_entropy and fused_linear_cross_entropy cannot both be True."
+    assert not (cross_entropy and fused_linear_cross_entropy), (
+        "cross_entropy and fused_linear_cross_entropy cannot both be True."
+    )
 
     modeling_llama4 = sys.modules["transformers.models.llama4.modeling_llama4"]
 
@@ -165,7 +162,7 @@ def apply_liger_kernel_to_llama4(
             # clone config to avoid modifying the original
             config = deepcopy(config)
             if intermediate_size:
-                setattr(config, "intermediate_size", intermediate_size)
+                config.intermediate_size = intermediate_size
             return LigerSwiGLUMLP(config, **kwargs)
 
         modeling_llama4.Llama4TextMLP = _liger_swiglu_mlp_wrapper

src/axolotl/integrations/liger/models/qwen3.py

@@ -43,7 +43,6 @@ def lce_forward(
     Returns:
     """
 
-    # pylint: disable=duplicate-code
     output_attentions = (
         output_attentions
         if output_attentions is not None
@@ -113,9 +112,8 @@ def apply_liger_kernel_to_qwen3(
     rms_norm: bool = False,
     glu_activation: bool = False,
     layer_norm: bool = False,
-    **kwargs,  # pylint: disable=unused-argument
+    **kwargs,
 ) -> None:
-    # pylint: disable=duplicate-code
     """
     Apply Liger kernels to replace original implementation in HuggingFace Llama models (2 and 3)
 
@@ -130,15 +128,15 @@ def apply_liger_kernel_to_qwen3(
         layer_norm (bool): Whether to apply Liger's LayerNorm. Default is False.
     """
 
-    import transformers.models.qwen3.modeling_qwen3  # noqa: F401  # pylint: disable=unused-import
+    import transformers.models.qwen3.modeling_qwen3  # noqa: F401
     from liger_kernel.transformers.functional import liger_cross_entropy
     from liger_kernel.transformers.layer_norm import LigerLayerNorm
     from liger_kernel.transformers.rms_norm import LigerRMSNorm
     from liger_kernel.transformers.swiglu import LigerSwiGLUMLP
 
-    assert not (
-        cross_entropy and fused_linear_cross_entropy
-    ), "cross_entropy and fused_linear_cross_entropy cannot both be True."
+    assert not (cross_entropy and fused_linear_cross_entropy), (
+        "cross_entropy and fused_linear_cross_entropy cannot both be True."
+    )
 
     modeling_qwen3 = sys.modules["transformers.models.qwen3.modeling_qwen3"]
 

src/axolotl/integrations/liger/models/qwen3_moe.py

@@ -45,7 +45,6 @@ def lce_forward(
     Returns:
     """
 
-    # pylint: disable=duplicate-code
     output_attentions = (
         output_attentions
         if output_attentions is not None
@@ -135,9 +134,8 @@ def apply_liger_kernel_to_qwen3_moe(
     rms_norm: bool = False,
     glu_activation: bool = False,
     layer_norm: bool = False,
-    **kwargs,  # pylint: disable=unused-argument
+    **kwargs,
 ) -> None:
-    # pylint: disable=duplicate-code
     """
     Apply Liger kernels to replace original implementation in HuggingFace Llama models (2 and 3)
 
@@ -152,15 +150,15 @@ def apply_liger_kernel_to_qwen3_moe(
         layer_norm (bool): Whether to apply Liger's LayerNorm. Default is False.
     """
 
-    import transformers.models.qwen3_moe.modeling_qwen3_moe  # noqa: F401  # pylint: disable=unused-import
+    import transformers.models.qwen3_moe.modeling_qwen3_moe  # noqa: F401
     from liger_kernel.transformers.functional import liger_cross_entropy
     from liger_kernel.transformers.layer_norm import LigerLayerNorm
     from liger_kernel.transformers.rms_norm import LigerRMSNorm
     from liger_kernel.transformers.swiglu import LigerSwiGLUMLP
 
-    assert not (
-        cross_entropy and fused_linear_cross_entropy
-    ), "cross_entropy and fused_linear_cross_entropy cannot both be True."
+    assert not (cross_entropy and fused_linear_cross_entropy), (
+        "cross_entropy and fused_linear_cross_entropy cannot both be True."
+    )
 
     modeling_qwen3_moe = sys.modules["transformers.models.qwen3_moe.modeling_qwen3_moe"]
 
@@ -174,7 +172,7 @@ def apply_liger_kernel_to_qwen3_moe(
             # clone config to avoid modifying the original
             config = deepcopy(config)
             if intermediate_size:
-                setattr(config, "intermediate_size", intermediate_size)
+                config.intermediate_size = intermediate_size
             return LigerSwiGLUMLP(config, **kwargs)
 
         modeling_qwen3_moe.Qwen3MoeMLP = _liger_swiglu_mlp_wrapper

src/axolotl/integrations/lm_eval/__init__.py

@@ -7,7 +7,7 @@ import subprocess  # nosec
 from axolotl.integrations.base import BasePlugin
 from axolotl.integrations.lm_eval.cli import build_lm_eval_command
 
-from .args import LMEvalArgs  # pylint: disable=unused-import. # noqa: F401
+from .args import LMEvalArgs as LMEvalArgs
 
 
 class LMEvalPlugin(BasePlugin):
@@ -20,7 +20,6 @@ class LMEvalPlugin(BasePlugin):
 
     def post_train_unload(self, cfg):
         if cfg.lm_eval_post_train:
-            # pylint: disable=duplicate-code
             for lm_eval_args in build_lm_eval_command(
                 cfg.lm_eval_tasks,
                 bfloat16=cfg.bfloat16 or cfg.bf16,