Add ruff, remove black, isort, flake8, pylint (#3092)

* black, isort, flake8 -> ruff

* remove unused

* add back needed import

* fix

.bandit

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

.flake8

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

.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
+-   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 25.1.0
+    rev: v0.12.9
     hooks:
-    -   id: black
+    -   id: ruff
--   repo: https://github.com/pycqa/isort
+        args: [--fix]
-    rev: 6.0.1
+    -   id: ruff-format
-    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
 -   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

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
@@ -70,4 +68,4 @@ 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)

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."
             )

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

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/unsloth_install.py

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

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/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

@@ -35,7 +35,7 @@ def get_multi_line_input() -> str:
 
     instruction = ""
     for line in sys.stdin:
-        instruction += line  # pylint: disable=consider-using-join
+        instruction += line
 
     return instruction
 
@@ -167,7 +167,6 @@ 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 +251,7 @@ 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_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

@@ -73,7 +73,7 @@ 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 +95,7 @@ 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/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

@@ -6,6 +6,7 @@ from dataclasses import dataclass
 
 from datasets import Dataset
 
+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

src/axolotl/convert.py

@@ -67,9 +67,7 @@ class JsonToJsonlConverter:
         self.json_parser = json_parser
         self.jsonl_serializer = jsonl_serializer
 
-    def convert(
+    def convert(self, input_file_path, output_file_path):
-        self, input_file_path, output_file_path
-    ):  # pylint: disable=unused-argument
         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(
+        def causal_doc_mask_mod(batch_idx, head_idx, q_idx, kv_idx):
-            batch_idx, head_idx, q_idx, kv_idx
-        ):  # pylint: disable=unused-argument
             """
             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[
+    mask_interface = ALL_MASK_ATTENTION_FUNCTIONS[config._attn_implementation]
-        config._attn_implementation  # pylint: disable=protected-access
-    ]
 
     # Do not allow skip if we are compiling (this is to match BC)
     allow_is_causal_skip = (

src/axolotl/core/builders/base.py

@@ -44,7 +44,7 @@ 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 +260,14 @@ 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 +414,8 @@ 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
+            torch._dynamo.config.suppress_errors = True
-                True
+            torch._dynamo.config.accumulated_cache_size_limit = 256
-            )
-            torch._dynamo.config.accumulated_cache_size_limit = (  # pylint: disable=protected-access
-                256
-            )
             training_args_kwargs["torch_compile"] = self.cfg.torch_compile
             if self.cfg.torch_compile_backend:
                 training_args_kwargs["torch_compile_backend"] = (

src/axolotl/core/builders/causal.py

@@ -344,16 +344,14 @@ class HFCausalTrainerBuilder(TrainerBuilderBase):
             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
+            training_args.run_name = None
-                None
-            )
 
         data_collator_kwargs = {
             "padding": True,  # True/"longest" is the default

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
+            training_args.run_name = None
-                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
+    system = "system"
-    user = "user"  # pylint: disable=invalid-name
+    user = "user"
-    assistant = "assistant"  # pylint: disable=invalid-name
+    assistant = "assistant"
-    tool = "tool"  # pylint: disable=invalid-name
+    tool = "tool"
-    ipython = (  # pylint: disable=invalid-name
+    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
+    special_token = "special_token"  # nosec B105
-    text = "text"  # pylint: disable=invalid-name
+    text = "text"
-    image = "image"  # pylint: disable=invalid-name
+    image = "image"
-    audio = "audio"  # pylint: disable=invalid-name
+    audio = "audio"
-    tool_call = "tool_call"  # pylint: disable=invalid-name  # to differentiate regular responses from tool calls from the assistant
+    tool_call = "tool_call"
-    tool_response = "tool_response"  # pylint: disable=invalid-name
+    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
+    bos_token = "bos_token"  # nosec B105
-    eos_token = "eos_token"  # pylint: disable=invalid-name  # 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_role: str | list[str] | None = None,  # commonly "role"
-    message_field_content: Union[str, list[str]] = [
+    message_field_content: str | list[str] | None = None,  # commonly "content"
-        "value",
+    message_field_training: str | list[str] | None = None,  # commonly "weight"
-        "text",
-        "content",
-    ],  # commonly "content"
-    message_field_training: Union[str, list[str]] = [
-        "train",
-        "weight",
-    ],  # 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
@@ -285,9 +283,9 @@ 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)
@@ -443,7 +441,7 @@ 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,
@@ -524,9 +522,7 @@ 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
+            AcceleratorState._reset_state(reset_partial_state=True)
-                reset_partial_state=True
-            )
 
         super().create_accelerator_and_postprocess()
 
@@ -540,7 +536,6 @@ 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]:

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(
+    def set_trainer_args(cls, cfg: DictDefault) -> list[Any]:
-        cls, cfg: DictDefault
-    ) -> list[Any]:  # pylint: disable=unused-argument
         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
+                            group_leader_rank * len(prompts_text) : (
-                            * len(prompts_text) : (group_leader_rank + 1)
+                                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
+        return_outputs=False,
-        num_items_in_batch=None,  # pylint: disable=unused-argument
+        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

@@ -92,7 +92,7 @@ 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 = smp.DistributedOptimizer(self.optimizer)
-                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."}
     )

src/axolotl/datasets.py

@@ -26,7 +26,7 @@ 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,
@@ -99,7 +99,7 @@ class ConstantLengthDataset(IterableDataset):
         seq_length: Length of token sequences to return.
     """
 
-    def __init__(  # pylint: disable=super-init-not-called
+    def __init__(
         self,
         tokenizer,
         datasets,

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(
+    def get_collator_cls_and_kwargs(self, cfg: DictDefault, is_eval: bool = False):
-        self, cfg: DictDefault, is_eval: bool = False
-    ):  # pylint: disable=unused-argument):
         """
         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
+        exec(dynamic_input, globals(), namespace)  # nosec B102
-            dynamic_input, globals(), namespace
+        AxolotlInputConfig = namespace["AxolotlInputConfig"]
-        )
+        AxolotlConfigWCapabilities = namespace["AxolotlConfigWCapabilities"]
-        AxolotlInputConfig = namespace[  # pylint: disable=invalid-name
-            "AxolotlInputConfig"
-        ]
-        AxolotlConfigWCapabilities = namespace[  # pylint: disable=invalid-name
-            "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
+        exec(dynamic_input, {**globals(), **local_vars}, namespace)  # nosec B102
-            dynamic_input, {**globals(), **local_vars}, namespace
+        AxolotlTrainingMixins = namespace["AxolotlTrainingMixins"]
-        )
-        AxolotlTrainingMixins = namespace[  # pylint: disable=invalid-name
-            "AxolotlTrainingMixins"
-        ]
         return AxolotlTrainingMixins
     return AxolotlTrainingMixinsBase

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
 
@@ -28,7 +29,7 @@ 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__)
 
@@ -106,9 +107,7 @@ class CutCrossEntropyPlugin(BasePlugin):
         """
         from cut_cross_entropy.transformers.patch import PATCH_FNS
 
-        def patch_generic(
+        def patch_generic(maybe_model, patch_options, model_type: str):
-            maybe_model, patch_options, model_type: str
-        ):  # pylint: disable=unused-argument
             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
+                cut_cross_entropy.transformers.llama._PATCH_OPTS = patch_options
-                    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(
+    def on_pre_optimizer_step(self, args_, state, control, **kwargs):
-        self, args_, state, control, **kwargs
-    ):  # pylint: disable=unused-argument
         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
+    vllm = "vllm"
-    sglang = "sglang"  # pylint: disable=invalid-name
+    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(
+    def on_step_end(self, args, state, control, **kwargs):
-        self, args, state, control, **kwargs
-    ):  # pylint: disable=unused-argument
         # 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
+                for lp, ids, mask in zip(t_logprobs, t_ids, t_mask, strict=False):
-                    t_logprobs, t_ids, t_mask
-                ):
                     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
+        for i, sub_features in enumerate(features):
-            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(
+                            if isinstance(feat[field_name][0], (dict, str)):
-                                feat[field_name][0], (dict, str)
-                            ):  # pylint: disable=too-many-nested-blocks
                                 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
+        B, N, D = student_input.shape
-        K = target_token_ids.shape[-1]  # pylint: disable=invalid-name
+        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
+        raise Exception("Liger Kernel does not support pretraining_tp!!")
-            "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 (
+    assert not (cross_entropy and fused_linear_cross_entropy), (
-        cross_entropy and fused_linear_cross_entropy
+        "cross_entropy and fused_linear_cross_entropy cannot both be True."
-    ), "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 (
+    assert not (cross_entropy and fused_linear_cross_entropy), (
-        cross_entropy and fused_linear_cross_entropy
+        "cross_entropy and fused_linear_cross_entropy cannot both be True."
-    ), "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 (
+    assert not (cross_entropy and fused_linear_cross_entropy), (
-        cross_entropy and fused_linear_cross_entropy
+        "cross_entropy and fused_linear_cross_entropy cannot both be True."
-    ), "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,

src/axolotl/integrations/lm_eval/cli.py

@@ -99,7 +99,6 @@ def lm_eval(config: str, cloud: Optional[str] = None):
         with open(config, encoding="utf-8") as file:
             cfg: DictDefault = DictDefault(yaml.safe_load(file))
 
-        # pylint: disable=duplicate-code
         for lm_eval_args in build_lm_eval_command(
             cfg.lm_eval_tasks,
             bfloat16=cfg.bfloat16 or cfg.bf16,

src/axolotl/integrations/spectrum/__init__.py

@@ -23,7 +23,7 @@ import requests
 from axolotl.integrations.base import BasePlugin
 from axolotl.utils.logging import get_logger
 
-from .args import SpectrumArgs  # pylint: disable=unused-import. # noqa: F401
+from .args import SpectrumArgs as SpectrumArgs
 
 LOG = get_logger(__name__)
 
@@ -46,7 +46,7 @@ def _generate_unfrozen_params_yaml(snr_data, top_fraction=0.5):
         "^lm_head.weight$",
         "^model.embed_tokens.weight$",
     ]
-    for layer_type, layer_names in top_layers_by_type.items():
+    for _, layer_names in top_layers_by_type.items():
         for layer_name in layer_names:
             unfrozen_parameters.append(layer_name)
     return unfrozen_parameters
@@ -84,7 +84,7 @@ class SpectrumPlugin(BasePlugin):
                 snr_data = json.load(fin)
         except FileNotFoundError:
             pass
-        except Exception as exc:  # pylint: disable=broad-exception-caught
+        except Exception as exc:
             LOG.warning(f"Failed to read SNR data from {snr_path}: {exc}")
 
         if not snr_data:

src/axolotl/integrations/spectrum/args.py

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

src/axolotl/kernels/geglu.py

@@ -5,8 +5,6 @@ See "GLU Variants Improve Transformer" (https://arxiv.org/abs/2002.05202).
 Credit to `unsloth` (https://unsloth.ai/) for inspiration for this implementation.
 """
 
-# pylint: disable=invalid-name,unnecessary-lambda-assignment,duplicate-code
-
 import torch
 import triton
 import triton.language as tl

src/axolotl/kernels/lora.py

@@ -7,8 +7,6 @@ See "LoRA: Low-Rank Adaptation of Large Language Models"
 Credit to `unsloth` (https://unsloth.ai/) for inspiration for this implementation.
 """
 
-# pylint: disable=invalid-name
-
 from typing import Callable
 
 import torch

src/axolotl/kernels/quantize.py

@@ -1,7 +1,5 @@
 """Dequantization utilities for `bitsandbytes` integration."""
 
-# pylint: disable=invalid-name,global-statement
-
 import ctypes
 
 import bitsandbytes as bnb

src/axolotl/kernels/swiglu.py

@@ -99,7 +99,6 @@ def _swiglu_bwd_kernel(
     tl.store(up_ptr + offsets, grad_up, mask=mask)  # grad wrt up
 
 
-# pylint: disable=unnecessary-lambda-assignment
 def swiglu_forward(gate: torch.Tensor, up: torch.Tensor) -> torch.Tensor:
     """
     SwiGLU forward pass. Computes SwiGLU activation: `x * sigmoid(x) * up`, where
@@ -128,7 +127,6 @@ def swiglu_forward(gate: torch.Tensor, up: torch.Tensor) -> torch.Tensor:
     return out
 
 
-# pylint: disable=unnecessary-lambda-assignment
 def swiglu_backward(
     grad_output: torch.Tensor, gate: torch.Tensor, up: torch.Tensor
 ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor]:

src/axolotl/loaders/__init__.py

@@ -1,6 +1,5 @@
 """Init for axolotl.loaders module"""
 
-# pylint: disable=unused-import
 # flake8: noqa
 
 from .adapter import load_adapter, load_lora

src/axolotl/loaders/adapter.py

@@ -28,14 +28,12 @@ LOG = get_logger(__name__)
 def setup_quantized_meta_for_peft(model: torch.nn.Module):
     """Replaces `quant_state.to` with a dummy function to prevent PEFT from moving `quant_state` to meta device"""
 
-    def temp_to_method(self, *args, **kwargs):  # pylint: disable=unused-argument
+    def temp_to_method(self, *args, **kwargs):
         return self
 
     for param in model.parameters():
         if isinstance(param, Params4bit):
-            param.quant_state._orig_to = (  # pylint: disable=protected-access
+            param.quant_state._orig_to = param.quant_state.to
-                param.quant_state.to
-            )
             param.quant_state.to = types.MethodType(temp_to_method, param.quant_state)
 
 
@@ -43,10 +41,8 @@ def setup_quantized_peft_meta_for_training(model: torch.nn.Module):
     """Replaces dummy `quant_state.to` method with the original function to allow training to continue"""
     for param in model.parameters():
         if isinstance(param, Params4bit) and hasattr(param.quant_state, "_orig_to"):
-            param.quant_state.to = (
+            param.quant_state.to = param.quant_state._orig_to
-                param.quant_state._orig_to  # pylint: disable=protected-access
+            param.quant_state._orig_to = None
-            )
-            param.quant_state._orig_to = None  # pylint: disable=protected-access
 
 
 def find_all_linear_names(model):

src/axolotl/loaders/model.py

@@ -102,7 +102,7 @@ class ModelLoader:
         *,
         inference: bool = False,
         reference_model: bool = False,
-        **kwargs,  # pylint: disable=unused-argument
+        **kwargs,
     ):
         """Initializes the ModelLoader.
 
@@ -134,7 +134,7 @@ class ModelLoader:
 
         # Init model config
         self.model_config = load_model_config(cfg)
-        self.auto_model_loader = AutoModelForCausalLM  # pylint: disable=invalid-name
+        self.auto_model_loader = AutoModelForCausalLM
 
         # Initialize the patch manager
         self.patch_manager = PatchManager(
@@ -607,27 +607,19 @@ class ModelLoader:
             self.model_kwargs["attn_implementation"] = self.cfg.attn_implementation
         elif self.cfg.flex_attention:
             self.model_kwargs["attn_implementation"] = "flex_attention"
-            self.model_config._attn_implementation = (  # pylint: disable=protected-access
+            self.model_config._attn_implementation = "flex_attention"
-                "flex_attention"
-            )
 
         elif self.cfg.flash_attention:
             if not self.cfg.sample_packing and self.cfg.s2_attention:
                 pass
             self.model_kwargs["attn_implementation"] = "flash_attention_2"
-            self.model_config._attn_implementation = (  # pylint: disable=protected-access
+            self.model_config._attn_implementation = "flash_attention_2"
-                "flash_attention_2"
-            )
         elif self.cfg.sdp_attention:
             self.model_kwargs["attn_implementation"] = "sdpa"
-            self.model_config._attn_implementation = (  # pylint: disable=protected-access
+            self.model_config._attn_implementation = "sdpa"
-                "sdpa"
-            )
         elif self.cfg.eager_attention:
             self.model_kwargs["attn_implementation"] = "eager"
-            self.model_config._attn_implementation = (  # pylint: disable=protected-access
+            self.model_config._attn_implementation = "eager"
-                "eager"
-            )
 
         if self.cfg.low_cpu_mem_usage:
             self.model_kwargs["low_cpu_mem_usage"] = True
@@ -767,7 +759,7 @@ class ModelLoader:
                 )
         elif self.model_type == "MambaLMHeadModel":
             # FIXME this is janky at best and hacked together to make it work
-            MambaLMHeadModel = fix_mamba_attn_for_loss()  # pylint: disable=invalid-name
+            MambaLMHeadModel = fix_mamba_attn_for_loss()
 
             self.model_kwargs["dtype"] = self.model_kwargs["torch_dtype"]
             self.model_kwargs["device"] = torch.cuda.current_device()
@@ -816,7 +808,6 @@ class ModelLoader:
         if is_deepspeed_zero3_enabled():
             skip_move_to_device = True
 
-        # pylint: disable=protected-access
         if self.cfg.tensor_parallel_size > 1:
             # workaround for upstream 4.54.0 not setting _tp_size or _device_mesh
             # TODO(wing): remove once 4.54.1 is released

src/axolotl/loaders/tokenizer.py

@@ -50,7 +50,7 @@ def modify_tokenizer_files(
     tokenizer_dir = os.path.join(output_dir, "tokenizer")
     os.makedirs(tokenizer_dir, exist_ok=True)
 
-    if is_local_main_process():  # pylint: disable=too-many-nested-blocks
+    if is_local_main_process():
         # Load the tokenizer
         temp_tokenizer = AutoTokenizer.from_pretrained(tokenizer_path, use_fast=True)
 
@@ -73,9 +73,9 @@ def modify_tokenizer_files(
                 for token_id, new_value in token_id_mappings.items():
                     token_id_str = str(token_id)
                     if token_id_str in config_data["added_tokens_decoder"]:
-                        config_data["added_tokens_decoder"][token_id_str][
+                        config_data["added_tokens_decoder"][token_id_str]["content"] = (
-                            "content"
+                            new_value
-                        ] = new_value
+                        )
                     else:
                         raise ValueError(
                             f"Token ID {token_id_str} not found in added_tokens_decoder"
@@ -215,7 +215,7 @@ def load_tokenizer(cfg: DictDefault) -> PreTrainedTokenizer:
         for k, val in special_tokens.items():
             # check if new special token is not already in tokenizer and
             # is adapter training to make sure lora_modules_to_save is set
-            # pylint: disable=too-many-boolean-expressions
+
             if (
                 (getattr(tokenizer, k) is None or getattr(tokenizer, k) != val)
                 and (len(tokenizer.encode(val, add_special_tokens=False)) > 2)

src/axolotl/models/mamba/__init__.py

@@ -21,4 +21,4 @@ def fix_mamba_attn_for_loss():
     from .modeling_mamba import MambaLMHeadModel as MambaLMHeadModelFixed
 
     mixer_seq_simple.MambaLMHeadModel = MambaLMHeadModelFixed
-    return mixer_seq_simple.MambaLMHeadModel  # pylint: disable=invalid-name
+    return mixer_seq_simple.MambaLMHeadModel

src/axolotl/models/mamba/modeling_mamba.py

@@ -1,4 +1,3 @@
-# pylint: skip-file
 import os
 from collections import namedtuple
 from functools import partial
@@ -112,7 +111,7 @@ class MambaLMHeadModel(nn.Module, GenerationMixin):
         self,
         save_directory: Union[str, os.PathLike],
         state_dict: Optional[dict] = None,
-        safe_serialization: Optional[bool] = None,  # pylint: disable=unused-argument
+        safe_serialization: Optional[bool] = None,
     ):
         if state_dict is None:
             state_dict = self.state_dict()

src/axolotl/monkeypatch/accelerate/fsdp2.py

@@ -130,9 +130,9 @@ def get_state_dict(self, model, unwrap=True):
                         "Deepspeed TP requires deepspeed >= 0.16.4, Please update DeepSpeed via `pip install deepspeed -U`."
                     )
                 state_dict = (
-                    model._consolidated_16bit_state_dict()  # pylint: disable=protected-access
+                    model._consolidated_16bit_state_dict()
                     if tp_sharding
-                    else model._zero3_consolidated_16bit_state_dict()  # pylint: disable=protected-access
+                    else model._zero3_consolidated_16bit_state_dict()
                 )
             else:
                 raise ValueError(
@@ -231,8 +231,7 @@ def fsdp2_prepare_model(accelerator, model: torch.nn.Module) -> torch.nn.Module:
     )
 
     is_type_fsdp = isinstance(model, FSDPModule) or (
-        is_compiled_module(model)
+        is_compiled_module(model) and isinstance(model._orig_mod, FSDPModule)
-        and isinstance(model._orig_mod, FSDPModule)  # pylint: disable=protected-access
     )
     if is_type_fsdp:
         return model

src/axolotl/monkeypatch/accelerate/parallelism_config.py

@@ -2,7 +2,6 @@
 workaround to allow parallelism config for pure CP
 """
 
-# pylint: disable=protected-access
 import os
 import warnings
 
@@ -30,7 +29,7 @@ def _validate_accelerator(self, accelerator):
     allow_parallelism_config = False
 
     if (
-        self.cp_size > 1  # pylint: disable=chained-comparison
+        self.cp_size > 1
         and self.dp_shard_size <= 1
         and os.environ.get("ACCELERATE_ALLOW_CP_STANDALONE", "false").lower() == "true"
     ):
@@ -55,6 +54,7 @@ def _validate_accelerator(self, accelerator):
         warnings.warn(
             "ParallelismConfig has the following warnings:\n" + "\n".join(_warnings),
             UserWarning,
+            stacklevel=2,
         )
 
 

src/axolotl/monkeypatch/attention/flex_attn.py

@@ -65,11 +65,9 @@ def patch_flex_wrapper(**flex_attn_compile_kwargs):
             return self._compiled_flex_attention
 
     transformers.integrations.flex_attention.WrappedFlexAttention = WrappedFlexAttention
-    setattr(
+    sys.modules[
-        sys.modules["transformers.integrations.flex_attention"],
+        "transformers.integrations.flex_attention"
-        "WrappedFlexAttention",
+    ].WrappedFlexAttention = WrappedFlexAttention
-        WrappedFlexAttention,
-    )
 
 
 def patch_flex_make_mask():
@@ -144,9 +142,7 @@ def patch_flex_make_mask():
         # computation prior to the softmax. For sample packing, we need both the
         # logic for both causal mask and document mask. See PyTorch's official
         # blog post for more details: https://pytorch.org/blog/flexattention/#mask-mods
-        def causal_mask_mod(
+        def causal_mask_mod(batch_idx, head_idx, q_idx, kv_idx):
-            batch_idx, head_idx, q_idx, kv_idx
-        ):  # pylint: disable=unused-argument
             """
             Defines the logic of a block causal mask by combining both a standard causal mask
             and a block diagonal document mask.
@@ -198,14 +194,12 @@ def patch_flex_make_mask():
     for n in tuple(sys.modules):
         if ".modeling_" in n:
             if hasattr(sys.modules[n], "make_flex_block_causal_mask"):
-                sys.modules[n].make_flex_block_causal_mask = (
+                sys.modules[
-                    patched_make_flex_block_causal_mask
+                    n
-                )
+                ].make_flex_block_causal_mask = patched_make_flex_block_causal_mask
-                setattr(
+                sys.modules[
-                    sys.modules[n],
+                    n
-                    "make_flex_block_causal_mask",
+                ].make_flex_block_causal_mask = patched_make_flex_block_causal_mask
-                    patched_make_flex_block_causal_mask,
-                )
 
     transformers.integrations.flex_attention.make_flex_block_causal_mask = (
         patched_make_flex_block_causal_mask

src/axolotl/monkeypatch/attention/xformers.py

@@ -23,15 +23,15 @@ def xformers_attention_forward(
     value: torch.Tensor,
     attention_mask: Optional[torch.Tensor] = None,
     position_ids: Optional[torch.LongTensor] = None,
-    dropout: float = 0.0,  # pylint: disable=unused-argument
+    dropout: float = 0.0,
-    scaling: Optional[float] = None,  # pylint: disable=unused-argument
+    scaling: Optional[float] = None,
-    sliding_window: Optional[int] = None,  # pylint: disable=unused-argument
+    sliding_window: Optional[int] = None,
-    softcap: Optional[float] = None,  # pylint: disable=unused-argument
+    softcap: Optional[float] = None,
     cu_seq_lens_q: Optional[torch.LongTensor] = None,
     cu_seq_lens_k: Optional[torch.LongTensor] = None,
     max_length_q: Optional[int] = None,
-    max_length_k: Optional[int] = None,  # pylint: disable=unused-argument
+    max_length_k: Optional[int] = None,
-    **kwargs,  # pylint: disable=unused-argument
+    **kwargs,
 ):
     # Get dimensions
     # query: [batch, heads, seq_len, hidden_dim]

src/axolotl/monkeypatch/btlm_attn_hijack_flash.py

@@ -25,9 +25,7 @@ def replace_btlm_attn_with_flash_attn(model_name="cerebras/btlm-3b-8k-base"):
         ".configuration_btlm", ".modeling_btlm"
     )
     modeling_btlm = importlib.import_module(module_name)
-    modeling_btlm.BTLMAttention._attn = (  # pylint: disable=protected-access
+    modeling_btlm.BTLMAttention._attn = flashattn_attn
-        flashattn_attn
-    )
 
 
 def flashattn_attn(
@@ -35,9 +33,9 @@ def flashattn_attn(
     query: torch.Tensor,
     key: Optional[torch.Tensor] = None,
     value: Optional[torch.Tensor] = None,
-    attention_mask: Optional[torch.Tensor] = None,  # pylint: disable=unused-argument
+    attention_mask: Optional[torch.Tensor] = None,
     head_mask: Optional[torch.Tensor] = None,
-    position_bias: Optional[torch.Tensor] = None,  # pylint: disable=unused-argument
+    position_bias: Optional[torch.Tensor] = None,
 ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
     softmax_scale = (
         1 / (key.size(-1) ** self.attn_scale_power) if self.scale_attn_weights else None

src/axolotl/monkeypatch/data/batch_dataset_fetcher.py

@@ -1,7 +1,5 @@
 """Monkey patches for the dataset fetcher to handle batches of packed indexes."""
 
-# pylint: disable=protected-access
-
 import torch
 from torch.utils.data._utils.fetch import _BaseDatasetFetcher
 from torch.utils.data._utils.worker import _worker_loop

src/axolotl/monkeypatch/fsdp2_qlora.py

@@ -15,7 +15,6 @@ from axolotl.utils.logging import get_logger
 LOG = get_logger(__name__)
 
 
-# pylint: disable=protected-access
 def apply_init_sharded_param_patch():
     """Apply patch to FSDPParam._init_sharded_param to support Params4bit."""
     from torch.distributed.fsdp._fully_shard._fsdp_param import FSDPParam
@@ -66,14 +65,14 @@ def apply_init_sharded_param_patch():
             if item in patched_source:
                 items_to_import.append(item)
 
-        exec(  # pylint: disable=exec-used  # nosec B102
+        exec(  # nosec B102
             f"from {module_name} import ({', '.join(items_to_import)})",
             globals(),
         )
-        exec(patched_source, globals())  # pylint: disable=exec-used  # nosec B102
+        exec(patched_source, globals())  # nosec B102
 
         # Replace the method
-        FSDPParam._init_sharded_param = patched_init_sharded_param  # pylint: disable=undefined-variable  # noqa: F821
+        FSDPParam._init_sharded_param = patched_init_sharded_param
         LOG.info("Successfully applied FSDP _init_sharded_param patch")
     else:
         LOG.warning("Could not find target code for _init_sharded_param patching")
@@ -131,14 +130,14 @@ def apply_init_unsharded_param_patch():
             if item in patched_source:
                 items_to_import.append(item)
 
-        exec(  # pylint: disable=exec-used  # nosec B102
+        exec(  # nosec B102
             f"from {module_name} import ({', '.join(items_to_import)})",
             globals(),
         )
-        exec(patched_source, globals())  # pylint: disable=exec-used  # nosec B102
+        exec(patched_source, globals())  # nosec B102
 
         # Replace the method
-        FSDPParam.init_unsharded_param = patched_init_unsharded_param  # pylint: disable=undefined-variable  # noqa: F821
+        FSDPParam.init_unsharded_param = patched_init_unsharded_param
         LOG.info("Successfully applied FSDP init_unsharded_param patch")
     else:
         LOG.warning("Could not find target code for patching")

src/axolotl/monkeypatch/gradient_checkpointing/__init__.py

@@ -25,9 +25,7 @@ else:
         return False
 
 
-def hf_grad_checkpoint_offload_wrapper(
+def hf_grad_checkpoint_offload_wrapper(decoder_layer, *args, use_reentrant=None):
-    decoder_layer, *args, use_reentrant=None
-):  # pylint: disable=unused-argument
     if uses_gc_layers(decoder_layer):
         return CPU_Offloaded_Gradient_Checkpointer.apply(
             decoder_layer,
@@ -44,9 +42,7 @@ def hf_grad_checkpoint_offload_wrapper(
     )
 
 
-def hf_grad_checkpoint_disk_offload_wrapper(
+def hf_grad_checkpoint_disk_offload_wrapper(decoder_layer, *args, use_reentrant=None):
-    decoder_layer, *args, use_reentrant=None
-):  # pylint: disable=unused-argument
     if uses_gc_layers(decoder_layer):
         return Disco.apply(
             decoder_layer,

src/axolotl/monkeypatch/gradient_checkpointing/offload_cpu.py

@@ -35,9 +35,7 @@ else:
     torch_cuda_amp_custom_bwd = torch.amp.custom_bwd(device_type="cuda")
 
 
-class CPU_Offloaded_Gradient_Checkpointer(  # pylint: disable=invalid-name
+class CPU_Offloaded_Gradient_Checkpointer(torch.autograd.Function):
-    torch.autograd.Function
-):
     """
     Saves VRAM by smartly offloading to RAM.
     Tiny hit to performance, since we mask the movement via non blocking calls.
@@ -66,6 +64,4 @@ class CPU_Offloaded_Gradient_Checkpointer(  # pylint: disable=invalid-name
         return (
             None,
             hidden_states.grad,
-        ) + (
+        ) + (None,) * len(ctx.args)
-            None,
-        ) * len(ctx.args)

src/axolotl/monkeypatch/gradient_checkpointing/offload_disk.py

@@ -62,9 +62,9 @@ class DiskOffloadManager:
 
         # Track tensor paths and their status
         self.tensor_paths: deque = deque()  # Ordered history of tensor paths (LIFO)
-        self.file_locks: Dict[str, threading.Lock] = (
+        self.file_locks: Dict[
-            {}
+            str, threading.Lock
-        )  # Maps file_path -> threading.Lock()
+        ] = {}  # Maps file_path -> threading.Lock()
         # Maps file_path -> status ("saving", "ready", "prefetching", "loaded", "deleted")
         self.file_status: Dict[str, str] = {}
 
@@ -236,7 +236,7 @@ class DiskOffloadManager:
             self.tensor_paths.append(file_path)
 
         # Acquire semaphore to limit concurrent save operations
-        self.save_semaphore.acquire()  # pylint: disable=consider-using-with
+        self.save_semaphore.acquire()
         # Queue tensor for saving in background
         self.save_queue.put((tensor.detach(), file_path))
 

src/axolotl/monkeypatch/llama_attn_hijack_flash.py

@@ -2,6 +2,7 @@
 
 # copied from https://github.com/lm-sys/FastChat/blob/main/fastchat/train/llama_flash_attn_monkey_patch.py
 
+import importlib.util
 import warnings
 from typing import Optional, Tuple
 
@@ -19,7 +20,7 @@ from axolotl.monkeypatch.utils import set_module_name
 from axolotl.utils.logging import get_logger
 
 try:
-    from flash_attn.flash_attn_interface import (  # pylint: disable=ungrouped-imports
+    from flash_attn.flash_attn_interface import (
         flash_attn_varlen_qkvpacked_func,
     )
 except ImportError:
@@ -32,12 +33,7 @@ LOG = get_logger(__name__)
 
 
 def is_xformers_available() -> bool:
-    try:
+    return importlib.util.find_spec("xformers") is not None
-        import xformers  # pylint: disable=unused-import  # noqa: F401
-
-        return True
-    except ImportError:
-        return False
 
 
 def is_xformers_swiglu_available() -> bool:
@@ -83,7 +79,7 @@ def patch_fa_llama_cross_entropy():
         num_items_in_batch: int = None,
         ignore_index: int = -100,
         **kwargs,
-    ):  # pylint: disable=unused-argument
+    ):
         reduction = "sum" if num_items_in_batch is not None else "mean"
         loss, _ = flash_attn_cross_entropy_loss(
             source, target, ignore_index=ignore_index
@@ -120,9 +116,7 @@ def replace_llama_attn_with_flash_attn(
     rms_norm: Optional[bool] = False,
     use_shifted_sparse_attn: Optional[bool] = False,
 ):
-    transformers.models.llama.modeling_llama.LlamaModel._prepare_decoder_attention_mask = (  # pylint: disable=protected-access
+    transformers.models.llama.modeling_llama.LlamaModel._prepare_decoder_attention_mask = _prepare_decoder_attention_mask
-        _prepare_decoder_attention_mask
-    )
     if use_shifted_sparse_attn:
         transformers.models.llama.modeling_llama.LlamaAttention.forward = (
             flashattn_forward_with_s2attn
@@ -145,7 +139,7 @@ def _prepare_decoder_attention_mask(
     input_shape,
     inputs_embeds,
     past_key_values_length,
-):  # pylint: disable=unused-argument
+):
     # [bsz, seq_len]
     return attention_mask
 
@@ -161,9 +155,9 @@ def flashattn_forward_with_s2attn(
     past_key_value: Optional[Tuple[torch.Tensor]] = None,
     output_attentions: bool = False,
     use_cache: bool = False,
-    padding_mask: Optional[torch.LongTensor] = None,  # pylint: disable=unused-argument
+    padding_mask: Optional[torch.LongTensor] = None,
-    cu_seqlens: Optional[torch.Tensor] = None,  # pylint: disable=unused-argument
+    cu_seqlens: Optional[torch.Tensor] = None,
-    max_seqlen: Optional[torch.Tensor] = None,  # pylint: disable=unused-argument
+    max_seqlen: Optional[torch.Tensor] = None,
 ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
     """Input shape: Batch x Time x Channel
 
@@ -176,7 +170,8 @@ def flashattn_forward_with_s2attn(
     """
     if output_attentions:
         warnings.warn(
-            "Output attentions is not supported for patched `LlamaAttention`, returning `None` instead."
+            "Output attentions is not supported for patched `LlamaAttention`, returning `None` instead.",
+            stacklevel=2,
         )
 
     bsz, q_len, _ = hidden_states.size()
@@ -198,7 +193,6 @@ def flashattn_forward_with_s2attn(
     )
     # [bsz, q_len, nh, hd]
     # [bsz, nh, q_len, hd]
-    # pylint: disable=duplicate-code
 
     cos, sin = self.rotary_emb(value_states, position_ids=position_ids)
     query_states, key_states = apply_rotary_pos_emb(
@@ -244,9 +238,7 @@ def flashattn_forward_with_s2attn(
         .permute(0, 3, 1, 2, 4, 5)
         .reshape(bsz * 2, q_len, 3, self.num_heads // 2, self.head_dim)
     )
-    x = rearrange(  # pylint: disable=invalid-name
+    x = rearrange(qkv, "b s three h d -> b s (three h d)")
-        qkv, "b s three h d -> b s (three h d)"
-    )
     x_unpad, indices, cu_q_lens, max_s = unpad_input(x, key_padding_mask)
     cu_q_len_tmp = torch.arange(
         0, max_s, group_size, device=key_padding_mask.device, dtype=cu_q_lens.dtype

src/axolotl/monkeypatch/llama_attn_hijack_xformers.py

@@ -32,10 +32,9 @@ def xformers_forward(
     past_key_value: Optional[Tuple[torch.Tensor]] = None,
     output_attentions: bool = False,
     use_cache: bool = False,
-    padding_mask: Optional[torch.LongTensor] = None,  # pylint: disable=unused-argument
+    padding_mask: Optional[torch.LongTensor] = None,
-    **kwargs,  # pylint: disable=unused-argument
+    **kwargs,
 ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
-    # pylint: disable=duplicate-code
     bsz, q_len, _ = hidden_states.size()
 
     if not hasattr(self, "pretraining_tp"):
@@ -102,7 +101,8 @@ def xformers_forward(
 
     if output_attentions:
         warnings.warn(
-            "Output attentions is not supported for patched `LlamaAttention`, returning `None` instead."
+            "Output attentions is not supported for patched `LlamaAttention`, returning `None` instead.",
+            stacklevel=2,
         )
 
     #

src/axolotl/monkeypatch/llama_expand_mask.py

@@ -21,6 +21,4 @@ def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int]
 def hijack_expand_mask():
     import transformers
 
-    transformers.models.llama.modeling_llama._expand_mask = (  # pylint: disable=protected-access
+    transformers.models.llama.modeling_llama._expand_mask = _expand_mask
-        _expand_mask
-    )

src/axolotl/monkeypatch/llama_patch_multipack.py

@@ -12,15 +12,15 @@ def hijack_llama_prepare_4d_mask():
     from transformers import modeling_attn_mask_utils
     from transformers.models.llama import modeling_llama
 
-    modeling_llama._prepare_4d_causal_attention_mask_for_sdpa = (  # pylint: disable=protected-access
+    modeling_llama._prepare_4d_causal_attention_mask_for_sdpa = (
         patched_prepare_4d_causal_attention_mask_for_sdpa
     )
-    modeling_attn_mask_utils._prepare_4d_causal_attention_mask_for_sdpa = (  # pylint: disable=protected-access
+    modeling_attn_mask_utils._prepare_4d_causal_attention_mask_for_sdpa = (
         patched_prepare_4d_causal_attention_mask_for_sdpa
     )
-    modeling_llama._prepare_4d_causal_attention_mask = (  # pylint: disable=protected-access
+    modeling_llama._prepare_4d_causal_attention_mask = (
         patched_prepare_4d_causal_attention_mask
     )
-    modeling_attn_mask_utils._prepare_4d_causal_attention_mask = (  # pylint: disable=protected-access
+    modeling_attn_mask_utils._prepare_4d_causal_attention_mask = (
         patched_prepare_4d_causal_attention_mask
     )

src/axolotl/monkeypatch/lora_kernels.py

@@ -30,48 +30,36 @@ QKV_PATCHES = [
     query_states = self.q_proj(hidden_states).view(hidden_shape).transpose(1, 2)
     key_states = self.k_proj(hidden_states).view(hidden_shape).transpose(1, 2)
     value_states = self.v_proj(hidden_states).view(hidden_shape).transpose(1, 2)
-""".lstrip(
+""".lstrip("\n"),
-            "\n"
-        ),
         """
     query_states, key_states, value_states = self.apply_qkv(hidden_states)
     query_states = query_states.view(hidden_shape).transpose(1, 2)
     key_states = key_states.view(hidden_shape).transpose(1, 2)
     value_states = value_states.view(hidden_shape).transpose(1, 2)
-""".lstrip(
+""".lstrip("\n"),
-            "\n"
-        ),
     ),
     (
         """
     query_states = self.q_norm(self.q_proj(hidden_states).view(hidden_shape)).transpose(1, 2)
     key_states = self.k_norm(self.k_proj(hidden_states).view(hidden_shape)).transpose(1, 2)
     value_states = self.v_proj(hidden_states).view(hidden_shape).transpose(1, 2)
-""".lstrip(
+""".lstrip("\n"),
-            "\n"
-        ),
         """
     query_states, key_states, value_states = self.apply_qkv(hidden_states)
     query_states = self.q_norm(query_states.view(hidden_shape)).transpose(1, 2)
     key_states = self.k_norm(key_states.view(hidden_shape)).transpose(1, 2)
     value_states = value_states.view(hidden_shape).transpose(1, 2)
-""".lstrip(
+""".lstrip("\n"),
-            "\n"
-        ),
     ),
 ]
 
 ORIGINAL_O_CODE = """
     attn_output = self.o_proj(attn_output)
-""".lstrip(
+""".lstrip("\n")
-    "\n"
-)
 
 PATCHED_O_CODE = """
     attn_output = self.apply_o(attn_output)
-""".lstrip(
+""".lstrip("\n")
-    "\n"
-)
 
 SUPPORTED_ACTIVATIONS = ["silu", "gelu"]
 APPLY_FN_MAPPING = {
@@ -176,7 +164,6 @@ def get_attention_cls_from_config(cfg: DictDefault) -> Type[nn.Module]:
         ) from e
 
 
-# pylint: disable=protected-access
 def patch_self_attn_lora(cfg: DictDefault):
     """
     Given an `axolotl` config, this method patches the inferred attention class forward
@@ -203,9 +190,9 @@ def patch_self_attn_lora(cfg: DictDefault):
     attention_cls._original_forward = self_attn_forward
     self_attn_forward, _ = detab_code(self_attn_forward)
 
-    assert any(
+    assert any(qkv_options[0] in self_attn_forward for qkv_options in QKV_PATCHES), (
-        qkv_options[0] in self_attn_forward for qkv_options in QKV_PATCHES
+        "Original QKV code not found"
-    ), "Original QKV code not found"
+    )
     assert ORIGINAL_O_CODE in self_attn_forward, "Original O code not found"
 
     for qkv_orig, qkv_patched in QKV_PATCHES:
@@ -231,16 +218,14 @@ def patch_self_attn_lora(cfg: DictDefault):
         if item in self_attn_forward:
             items_to_import.append(item)
 
-    exec(  # pylint: disable=exec-used  # nosec B102
+    exec(
         f"from {module_name} import ({', '.join(items_to_import)})",
         globals(),
     )
-    exec(self_attn_forward, globals())  # pylint: disable=exec-used  # nosec B102
+    exec(self_attn_forward, globals())
 
     LOG.info(f"Patched attention class with LoRA optims: {attention_cls.__name__}")
-    attention_cls.forward = (
+    attention_cls.forward = axolotl_attn_forward
-        axolotl_attn_forward  # pylint: disable=undefined-variable  # noqa: F821
-    )
 
 
 def find_self_attn_in_layer(
@@ -277,9 +262,13 @@ def find_mlp_in_layer(
                 layer.feedforward.experts.gate_projs,
                 layer.feedforward.experts.up_projs,
                 layer.feedforward.experts.down_projs,
+                strict=False,
             ):
-                yield gate_proj, up_proj, down_proj, FakeMLP(
+                yield (
-                    gate_proj, up_proj, down_proj
+                    gate_proj,
+                    up_proj,
+                    down_proj,
+                    FakeMLP(gate_proj, up_proj, down_proj),
                 )
 
 
@@ -337,9 +326,9 @@ def apply_lora_kernel_patches(
 
     # Get active LoRA adapter config
     if hasattr(model, "active_adapters"):
-        assert (
+        assert len(model.active_adapters) == 1, (
-            len(model.active_adapters) == 1
+            "Axolotl currently does not support LoRA Triton kernels for multiple adapters"
-        ), "Axolotl currently does not support LoRA Triton kernels for multiple adapters"
+        )
         active_adapter = model.active_adapters[0]
     else:
         active_adapter = model.active_adapter