feat: move to uv first (#3545)
* feat: move to uv first * fix: update doc to uv first * fix: merge dev/tests into uv pyproject * fix: update docker docs to match current config * fix: migrate examples to readme * fix: add llmcompressor to conflict * feat: rec uv sync with lockfile for dev/ci * fix: update docker docs to clarify how to use uv images * chore: docs * fix: use system python, no venv * fix: set backend cpu * fix: only set for installing pytorch step * fix: remove unsloth kernel and installs * fix: remove U in tests * fix: set backend in deps too * chore: test * chore: comments * fix: attempt to lock torch * fix: workaround torch cuda and not upgraded * fix: forgot to push * fix: missed source * fix: nightly upstream loralinear config * fix: nightly phi3 long rope not work * fix: forgot commit * fix: test phi3 template change * fix: no more requirements * fix: carry over changes from new requirements to pyproject * chore: remove lockfile per discussion * fix: set match-runtime * fix: remove unneeded hf hub buildtime * fix: duplicate cache delete on nightly * fix: torchvision being overridden * fix: migrate to uv images * fix: leftover from merge * fix: simplify base readme * fix: update assertion message to be clearer * chore: docs * fix: change fallback for cicd script * fix: match against main exactly * fix: peft 0.19.1 change * fix: e2e test * fix: ci * fix: e2e test
This commit is contained in:
NanoCode012
GitHub
@@ -1,21 +0,0 @@
|
||||
"""Test module for checking whether the integration of Unsloth with Hugging Face Transformers is working as expected."""
|
||||
|
||||
import unittest
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
@pytest.mark.skip(
|
||||
reason="Unsloth integration will be broken going into latest transformers"
|
||||
)
|
||||
class TestUnslothIntegration(unittest.TestCase):
|
||||
"""Unsloth monkeypatch integration tests."""
|
||||
|
||||
def test_is_self_attn_patchable(self):
|
||||
from axolotl.monkeypatch.unsloth_ import check_self_attn_is_patchable
|
||||
|
||||
# ensures the current version of transformers has loss code that matches our patching code
|
||||
self.assertTrue(
|
||||
check_self_attn_is_patchable(),
|
||||
"HF transformers self attention code has changed and isn't patchable",
|
||||
)
|
||||
@@ -1,184 +0,0 @@
|
||||
"""
|
||||
e2e tests for unsloth qlora
|
||||
"""
|
||||
|
||||
import pytest
|
||||
|
||||
from axolotl.common.datasets import load_datasets
|
||||
from axolotl.train import train
|
||||
from axolotl.utils.config import normalize_config, validate_config
|
||||
from axolotl.utils.dict import DictDefault
|
||||
|
||||
from ..utils import check_model_output_exists, check_tensorboard
|
||||
|
||||
|
||||
@pytest.mark.skip(
|
||||
reason="Unsloth integration will be broken going into latest transformers"
|
||||
)
|
||||
class TestUnslothQLoRA:
|
||||
"""
|
||||
Test class for Unsloth QLoRA Llama models
|
||||
"""
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"sample_packing",
|
||||
[True, False],
|
||||
)
|
||||
def test_unsloth_llama_qlora_fa2(self, temp_dir, sample_packing):
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"sequence_len": 1024,
|
||||
"sample_packing": sample_packing,
|
||||
"flash_attention": True,
|
||||
"unsloth_lora_mlp": True,
|
||||
"unsloth_lora_qkv": True,
|
||||
"unsloth_lora_o": True,
|
||||
"load_in_4bit": True,
|
||||
"adapter": "qlora",
|
||||
"lora_r": 16,
|
||||
"lora_alpha": 16,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_target_linear": True,
|
||||
"val_set_size": 0.05,
|
||||
"special_tokens": {
|
||||
"pad_token": "<|endoftext|>",
|
||||
},
|
||||
"datasets": [
|
||||
{
|
||||
"path": "mhenrichsen/alpaca_2k_test",
|
||||
"type": "alpaca",
|
||||
},
|
||||
],
|
||||
"num_epochs": 1,
|
||||
"max_steps": 5,
|
||||
"save_steps": 10,
|
||||
"micro_batch_size": 4,
|
||||
"gradient_accumulation_steps": 2,
|
||||
"output_dir": temp_dir,
|
||||
"learning_rate": 0.00001,
|
||||
"optimizer": "adamw_8bit",
|
||||
"lr_scheduler": "cosine",
|
||||
"use_tensorboard": True,
|
||||
"bf16": "auto",
|
||||
"save_first_step": False,
|
||||
}
|
||||
)
|
||||
|
||||
cfg = validate_config(cfg)
|
||||
normalize_config(cfg)
|
||||
dataset_meta = load_datasets(cfg=cfg)
|
||||
|
||||
train(cfg=cfg, dataset_meta=dataset_meta)
|
||||
check_model_output_exists(temp_dir, cfg)
|
||||
|
||||
check_tensorboard(
|
||||
temp_dir + "/runs", "train/train_loss", 2.0, "Train Loss (%s) is too high"
|
||||
)
|
||||
|
||||
def test_unsloth_llama_qlora_unpacked(self, temp_dir):
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"sequence_len": 1024,
|
||||
"unsloth_lora_mlp": True,
|
||||
"unsloth_lora_qkv": True,
|
||||
"unsloth_lora_o": True,
|
||||
"sample_packing": False,
|
||||
"load_in_4bit": True,
|
||||
"adapter": "qlora",
|
||||
"lora_r": 16,
|
||||
"lora_alpha": 16,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_target_linear": True,
|
||||
"val_set_size": 0.05,
|
||||
"special_tokens": {
|
||||
"pad_token": "<|endoftext|>",
|
||||
},
|
||||
"datasets": [
|
||||
{
|
||||
"path": "mhenrichsen/alpaca_2k_test",
|
||||
"type": "alpaca",
|
||||
},
|
||||
],
|
||||
"num_epochs": 1,
|
||||
"max_steps": 5,
|
||||
"save_steps": 10,
|
||||
"micro_batch_size": 4,
|
||||
"gradient_accumulation_steps": 2,
|
||||
"output_dir": temp_dir,
|
||||
"learning_rate": 0.00001,
|
||||
"optimizer": "adamw_8bit",
|
||||
"lr_scheduler": "cosine",
|
||||
"use_tensorboard": True,
|
||||
"bf16": "auto",
|
||||
"save_first_step": False,
|
||||
}
|
||||
)
|
||||
|
||||
cfg = validate_config(cfg)
|
||||
normalize_config(cfg)
|
||||
dataset_meta = load_datasets(cfg=cfg)
|
||||
|
||||
train(cfg=cfg, dataset_meta=dataset_meta)
|
||||
check_model_output_exists(temp_dir, cfg)
|
||||
|
||||
check_tensorboard(
|
||||
temp_dir + "/runs", "train/train_loss", 2.0, "Train Loss (%s) is too high"
|
||||
)
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"sdp_attention",
|
||||
[True, False],
|
||||
)
|
||||
def test_unsloth_llama_qlora_unpacked_no_fa2_fp16(self, temp_dir, sdp_attention):
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
||||
"sequence_len": 1024,
|
||||
"unsloth_lora_mlp": True,
|
||||
"unsloth_lora_qkv": True,
|
||||
"unsloth_lora_o": True,
|
||||
"sample_packing": False,
|
||||
"load_in_4bit": True,
|
||||
"adapter": "qlora",
|
||||
"lora_r": 16,
|
||||
"lora_alpha": 16,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_target_linear": True,
|
||||
"val_set_size": 0.05,
|
||||
"special_tokens": {
|
||||
"pad_token": "<|endoftext|>",
|
||||
},
|
||||
"datasets": [
|
||||
{
|
||||
"path": "mhenrichsen/alpaca_2k_test",
|
||||
"type": "alpaca",
|
||||
},
|
||||
],
|
||||
"num_epochs": 1,
|
||||
"max_steps": 5,
|
||||
"save_steps": 10,
|
||||
"micro_batch_size": 4,
|
||||
"gradient_accumulation_steps": 2,
|
||||
"sdp_attention": sdp_attention,
|
||||
"output_dir": temp_dir,
|
||||
"learning_rate": 0.00001,
|
||||
"optimizer": "adamw_8bit",
|
||||
"lr_scheduler": "cosine",
|
||||
"use_tensorboard": True,
|
||||
"fp16": True,
|
||||
"save_first_step": False,
|
||||
}
|
||||
)
|
||||
|
||||
cfg = validate_config(cfg)
|
||||
normalize_config(cfg)
|
||||
dataset_meta = load_datasets(cfg=cfg)
|
||||
|
||||
train(cfg=cfg, dataset_meta=dataset_meta)
|
||||
check_model_output_exists(temp_dir, cfg)
|
||||
|
||||
check_tensorboard(
|
||||
temp_dir + "/runs", "train/train_loss", 2.0, "Train Loss (%s) is too high"
|
||||
)
|
||||
Reference in New Issue
Block a user