tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

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

Browse Source 
* black, isort, flake8 -> ruff

* remove unused

* add back needed import

* fix
This commit is contained in:
Dan Saunders
2025-08-23 23:37:33 -04:00
committed by GitHub
parent eea7a006e1
commit 79ddaebe9a
286 changed files with 10979 additions and 11435 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
tests/e2e/patched/lora_kernels/test_lora_kernel_patching.py
View File

@@ -1,7 +1,5 @@
"""Integration tests for LoRA activation and attention kernels."""
# pylint: disable=redefined-outer-name
from pathlib import Path
import pytest
@@ -88,7 +86,7 @@ def test_attention_patching_integration(model_name, attention_cls):
cfg = DictDefault({"base_model": model_name})
# Store the original implementation
original_forward = getattr(attention_cls, "forward")
original_forward = attention_cls.forward
# Apply patch
patch_self_attn_lora(cfg)
@@ -104,7 +102,7 @@ def test_attention_patching_integration(model_name, attention_cls):
assert hasattr(attention_cls, "_original_forward")
# Clean up
setattr(attention_cls, "forward", original_forward)
attention_cls.forward = original_forward
delattr(attention_cls, "_original_forward")
@@ -379,9 +377,9 @@ def test_model_architecture(model_config):
# Verify correct activation function
layer = patched_model.model.model.layers[0]
assert (
layer.mlp.forward.__func__ is model_config["expected_activation"]
), f"Wrong activation for {model_config['name']}"
assert layer.mlp.forward.__func__ is model_config["expected_activation"], (
f"Wrong activation for {model_config['name']}"
)
# Test forward pass
inputs = get_test_inputs(model)
@@ -390,12 +388,11 @@ def test_model_architecture(model_config):
patched_output = patched_model(inputs).logits
# Check outputs match
assert torch.allclose(
original_output, patched_output, rtol=1e-4
), f"Outputs don't match for {model_config['name']}"
assert torch.allclose(original_output, patched_output, rtol=1e-4), (
f"Outputs don't match for {model_config['name']}"
)
# pylint: disable=duplicate-code
def test_kernel_training_integration(temp_dir):
"""Test model loading with kernel patches enabled."""
from axolotl.cli.utils import load_model_and_tokenizer
@@ -563,15 +560,13 @@ def test_kernel_training_integration_dropout_non_zero(temp_dir):
model_loader = ModelLoader(cfg, tokenizer)
# Apply patch
model_loader.patch_manager._apply_self_attention_lora_patch() # pylint: disable=protected-access
model_loader.patch_manager._apply_self_attention_lora_patch()
# Verify patch was not applied
assert attention_cls.forward == original_forward_method
# Apply apply_lora_kernel_patches
model_loader.patch_manager._apply_lora_kernel_patch( # pylint: disable=protected-access
model
)
model_loader.patch_manager._apply_lora_kernel_patch(model)
# Verify patch was not applied
layers = get_layers(model)

2
tests/e2e/patched/test_4d_multipack_llama.py
View File

@@ -19,7 +19,6 @@ class Test4dMultipackLlama(unittest.TestCase):
@with_temp_dir
def test_sdp_lora_packing(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",
@@ -67,7 +66,6 @@ class Test4dMultipackLlama(unittest.TestCase):
@with_temp_dir
def test_torch_lora_packing(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",

3
tests/e2e/patched/test_activation_checkpointing.py
View File

@@ -32,10 +32,9 @@ class TestActivationCheckpointing:
def test_activation_checkpointing_offload(
self,
temp_dir,
fix_checkpoint_after_test, # pylint: disable=unused-argument,redefined-outer-name
fix_checkpoint_after_test,
gradient_checkpointing,
):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",

1
tests/e2e/patched/test_cli_integrations.py
View File

@@ -10,7 +10,6 @@ from axolotl.cli.config import load_cfg
from axolotl.utils.dict import DictDefault
# pylint: disable=duplicate-code
class TestPluginArgs:
"""
test class for plugin args loaded from the config file

1
tests/e2e/patched/test_fa_xentropy.py
View File

@@ -23,7 +23,6 @@ class TestFAXentropyLlama:
[1, 4],
)
def test_lora_packing_fa_cross_entropy(self, temp_dir, gradient_accumulation_steps):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",

2
tests/e2e/patched/test_falcon_samplepack.py
View File

@@ -22,7 +22,6 @@ class TestFalconPatched(unittest.TestCase):
@pytest.mark.skip(reason="no tiny models for testing with safetensors")
@with_temp_dir
def test_qlora(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "illuin/tiny-random-FalconForCausalLM",
@@ -71,7 +70,6 @@ class TestFalconPatched(unittest.TestCase):
@pytest.mark.skip(reason="no tiny models for testing with safetensors")
@with_temp_dir
def test_ft(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "illuin/tiny-random-FalconForCausalLM",

1
tests/e2e/patched/test_flattening.py
View File

@@ -23,7 +23,6 @@ class TestFAFlattening:
[1, 4],
)
def test_lora_packing_flattening(self, temp_dir, gradient_accumulation_steps):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",

15
tests/e2e/patched/test_fsdp2_qlora.py
View File

@@ -15,7 +15,6 @@ class TestFSDPPatchIntegration:
apply_init_unsharded_param_patch,
)
# pylint: disable=protected-access
original_init_sharded = FSDPParam._init_sharded_param
original_init_unsharded = FSDPParam.init_unsharded_param
@@ -23,11 +22,9 @@ class TestFSDPPatchIntegration:
apply_init_sharded_param_patch()
apply_init_unsharded_param_patch()
assert (
# pylint: disable=protected-access
FSDPParam._init_sharded_param
!= original_init_sharded
), "_init_sharded_param was not patched"
assert (
FSDPParam.init_unsharded_param != original_init_unsharded
), "init_unsharded_param was not patched"
assert FSDPParam._init_sharded_param != original_init_sharded, (
"_init_sharded_param was not patched"
)
assert FSDPParam.init_unsharded_param != original_init_unsharded, (
"init_unsharded_param was not patched"
)

1
tests/e2e/patched/test_fused_llama.py
View File

@@ -23,7 +23,6 @@ class TestFusedLlama(unittest.TestCase):
@with_temp_dir
def test_fft_packing(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",

2
tests/e2e/patched/test_llama_s2_attention.py
View File

@@ -22,7 +22,6 @@ class TestLlamaShiftedSparseAttention(unittest.TestCase):
@with_temp_dir
def test_lora_s2_attn(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",
@@ -71,7 +70,6 @@ class TestLlamaShiftedSparseAttention(unittest.TestCase):
@with_temp_dir
def test_fft_s2_attn(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",

2
tests/e2e/patched/test_lora_llama_multipack.py
View File

@@ -22,7 +22,6 @@ class TestLoraLlama(unittest.TestCase):
@with_temp_dir
def test_lora_packing(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",
@@ -73,7 +72,6 @@ class TestLoraLlama(unittest.TestCase):
@pytest.mark.skipif(not is_auto_gptq_available(), reason="auto-gptq not available")
@with_temp_dir
def test_lora_gptq_packed(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "lilmeaty/SmolLM2-135M-Instruct-GPTQ",

2
tests/e2e/patched/test_mistral_samplepack.py
View File

@@ -20,7 +20,6 @@ class TestMistral(unittest.TestCase):
@require_torch_2_6_0
@with_temp_dir
def test_lora_packing(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "trl-internal-testing/tiny-MistralForCausalLM-0.2",
@@ -68,7 +67,6 @@ class TestMistral(unittest.TestCase):
@with_temp_dir
def test_ft_packing(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "trl-internal-testing/tiny-MistralForCausalLM-0.2",

2
tests/e2e/patched/test_mixtral_samplepack.py
View File

@@ -19,7 +19,6 @@ class TestMixtral(unittest.TestCase):
@with_temp_dir
def test_qlora(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "hf-internal-testing/Mixtral-tiny",
@@ -64,7 +63,6 @@ class TestMixtral(unittest.TestCase):
@with_temp_dir
def test_ft(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "hf-internal-testing/Mixtral-tiny",

2
tests/e2e/patched/test_model_patches.py
View File

@@ -89,5 +89,5 @@ class TestModelPatches(unittest.TestCase):
assert (
"torch.jit"
in transformers.modeling_flash_attention_utils._get_unpad_data.__module__ # pylint: disable=protected-access
in transformers.modeling_flash_attention_utils._get_unpad_data.__module__
)

1
tests/e2e/patched/test_peft_embeddings.py
View File

@@ -15,7 +15,6 @@ class TestLlamaPeftEmbeddings:
"""
def test_peft_embeddings_upcast(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",

2
tests/e2e/patched/test_phi_multipack.py
View File

@@ -19,7 +19,6 @@ class TestPhiMultipack(unittest.TestCase):
@with_temp_dir
def test_ft_packed(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "microsoft/phi-1_5",
@@ -67,7 +66,6 @@ class TestPhiMultipack(unittest.TestCase):
@with_temp_dir
def test_qlora_packed(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "microsoft/phi-1_5",

1
tests/e2e/patched/test_resume.py
View File

@@ -22,7 +22,6 @@ class TestResumeLlama:
@require_torch_2_6_0
def test_resume_lora_packed(self, temp_dir):
# pylint: disable=duplicate-code
cfg = DictDefault(
{
"base_model": "HuggingFaceTB/SmolLM2-135M",

1
tests/e2e/patched/test_unsloth_qlora.py
View File

@@ -12,7 +12,6 @@ from axolotl.utils.dict import DictDefault
from ..utils import check_model_output_exists, check_tensorboard
# pylint: disable=duplicate-code
@pytest.mark.skip(
reason="Unsloth integration will be broken going into latest transformers"
)