fc4e37920b
* Prepare for transformers v5 upgrade * fix hf cli * update for hf hub changes * fix tokenizer apply_chat_template args * remap include_tokens_per_second * fix tps * handle migration for warmup * use latest hf hub * Fix scan -> ls * fix import * fix for renaming of mistral common tokenizer -> backend * update for fixed tokenziation for llama * Skip phi35 tests for now * remove mistral patch fixed upstream in huggingface/transformers#41439 * use namespacing for patch * don't rely on sdist for e2e tests for now * run modal ci without waiting too * Fix dep for ci * fix imports * Fix fp8 check * fsdp2 fixes * fix version handling * update fsdp version tests for new v5 behavior * Fail multigpu tests after 3 failures * skip known v5 broken tests for now and cleanup * bump deps * unmark skipped test * re-enable test_fsdp_qlora_prequant_packed test * increase multigpu ci timeout * skip broken gemma3 test * reduce timout back to original 120min now that the hanging test is skipped * fix for un-necessary collator for pretraining with bsz=1 * fix: safe_serialization deprecated in transformers v5 rc01 (#3318) * torch_dtype deprecated * load model in float32 for consistency with tests * revert some test fixtures back * use hf cache ls instead of scan * don't strip fsdp_version more fdsp_Version fixes for v5 fix version in fsdp_config fix aliasing fix fsdp_version check check fsdp_version is 2 in both places * Transformers v5 rc2 (#3347) * bump dep * use latest fbgemm, grab model config as part of fixture, un-skip test * import AutoConfig * don't need more problematic autoconfig when specifying config.json manually * add fixtures for argilla ultrafeedback datasets * download phi4-reasoning * fix arg * update tests for phi fast tokenizer changes * use explicit model types for gemma3 --------- Co-authored-by: Wing Lian <wing@axolotl.ai> * fix: AutoModelForVision2Seq -> AutoModelForImageTextToText * chore: remove duplicate * fix: attempt fix gemma3 text mode * chore: lint * ga release of v5 * need property setter for name_or_path for mistral tokenizer * vllm not compatible with transformers v5 * setter for chat_template w mistral too --------- Co-authored-by: NanoCode012 <nano@axolotl.ai> Co-authored-by: salman <salman.mohammadi@outlook.com>
63 lines
2.0 KiB
Python
63 lines
2.0 KiB
Python
"""
|
|
Test case for handling embeddings when using peft
|
|
"""
|
|
|
|
import torch
|
|
|
|
from axolotl.train import setup_model_and_tokenizer
|
|
from axolotl.utils.config import normalize_config, validate_config
|
|
from axolotl.utils.dict import DictDefault
|
|
|
|
|
|
class TestLlamaPeftEmbeddings:
|
|
"""
|
|
test class for handling embeddings when using peft
|
|
"""
|
|
|
|
def test_peft_embeddings_upcast(self, temp_dir):
|
|
cfg = DictDefault(
|
|
{
|
|
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
|
"load_in_4bit": True,
|
|
"adapter": "qlora",
|
|
"lora_r": 8,
|
|
"lora_alpha": 16,
|
|
"lora_target_linear": True,
|
|
"trust_remote_code": True,
|
|
"sequence_len": 512,
|
|
"val_set_size": 0.01,
|
|
"special_tokens": {
|
|
"pad_token": "<|endoftext|>",
|
|
},
|
|
"datasets": [
|
|
{
|
|
"path": "mhenrichsen/alpaca_2k_test",
|
|
"type": "alpaca",
|
|
},
|
|
],
|
|
"num_epochs": 1,
|
|
"max_steps": 2,
|
|
"micro_batch_size": 1,
|
|
"gradient_accumulation_steps": 1,
|
|
"output_dir": temp_dir,
|
|
"learning_rate": 0.00001,
|
|
"optimizer": "adamw_8bit",
|
|
"lr_scheduler": "cosine",
|
|
"flash_attention": True,
|
|
"sample_packing": False,
|
|
"bf16": "auto",
|
|
"embeddings_skip_upcast": True,
|
|
"save_first_step": False,
|
|
}
|
|
)
|
|
|
|
cfg = validate_config(cfg)
|
|
normalize_config(cfg)
|
|
|
|
model, _, _, _ = setup_model_and_tokenizer(cfg)
|
|
|
|
# Check if the embeddings are upcast correctly
|
|
# only embed_tokens is a parameter that may be upcast
|
|
assert model.base_model.model.model.embed_tokens.weight.dtype == torch.bfloat16
|
|
assert model.base_model.model.lm_head.weight.dtype == torch.bfloat16
|