Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix gguf loading via Transformers #2596

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Fix gguf loading via Transformers #2596

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
58348a2
hf support load gguf file
CL-ModelCloud Dec 25, 2024
9d90d7d
code review
CL-ModelCloud Dec 25, 2024
e425566
code review
CL-ModelCloud Dec 25, 2024
026c70c
code clean up
CL-ModelCloud Dec 25, 2024
fad22cd
note about use_fast compat with gguf
Qubitium Dec 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 21 additions & 8 deletions lm_eval/models/huggingface.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,6 +90,7 @@ def __init__(
delta: Optional[str] = None,
autogptq: Optional[Union[bool, str]] = False,
gptqmodel: Optional[bool] = False,
gguf_file: Optional[str] = None,
**kwargs,
) -> None:
super().__init__()
Expand Down Expand Up @@ -164,6 +165,7 @@ def __init__(
pretrained,
revision=revision,
trust_remote_code=trust_remote_code,
gguf_file=gguf_file,
)

# determine which of 'causal' and 'seq2seq' backends to use for HF models
Expand All @@ -178,6 +180,7 @@ def __init__(
revision=revision,
trust_remote_code=trust_remote_code,
use_fast_tokenizer=use_fast_tokenizer,
gguf_file=gguf_file,
)

# if we passed `pretrained` as a string, initialize our model now
Expand All @@ -196,6 +199,7 @@ def __init__(
delta=delta,
autogptq=autogptq,
gptqmodel=gptqmodel,
gguf_file=gguf_file,
**kwargs,
)

Expand Down Expand Up @@ -508,12 +512,14 @@ def _get_config(
pretrained: str,
revision: str = "main",
trust_remote_code: bool = False,
gguf_file: Optional[str] = None,
) -> None:
"""Return the model config for HuggingFace models"""
self._config = transformers.AutoConfig.from_pretrained(
pretrained,
revision=revision,
trust_remote_code=trust_remote_code,
gguf_file=gguf_file,
)

def _create_model(
Expand All @@ -535,6 +541,7 @@ def _create_model(
delta: Optional[str] = None,
autogptq: Optional[Union[bool, str]] = False,
gptqmodel: Optional[bool] = False,
gguf_file: Optional[str] = None,
**kwargs,
) -> None:
"""
Expand Down Expand Up @@ -579,6 +586,7 @@ def _create_model(
revision=revision,
torch_dtype=get_dtype(dtype),
trust_remote_code=trust_remote_code,
gguf_file=gguf_file,
**model_kwargs,
)
else:
Expand Down Expand Up @@ -676,21 +684,29 @@ def _create_tokenizer(
revision: Optional[str] = "main",
trust_remote_code: Optional[bool] = False,
use_fast_tokenizer: Optional[bool] = True,
gguf_file: Optional[str] = None,
) -> None:
"""
Helper method during initialization.

Create a tokenizer object corresponding to the correct
tokenizer for value of `pretrained`, or use the pre-initialized tokenizer passed.
"""
kwargs = {
"revision": revision,
"trust_remote_code": trust_remote_code,
}

# gguf format embeds tokenizer and is not compatible with hf tokenizer `use_fast` param
if gguf_file is not None:
kwargs["gguf_file"] = gguf_file
else:
kwargs["use_fast"] = use_fast_tokenizer

if tokenizer:
if isinstance(tokenizer, str):
self.tokenizer = transformers.AutoTokenizer.from_pretrained(
tokenizer,
revision=revision,
trust_remote_code=trust_remote_code,
use_fast=use_fast_tokenizer,
tokenizer, **kwargs
)
else:
assert isinstance(
Expand All @@ -705,10 +721,7 @@ def _create_tokenizer(
# get the HF hub name via accessor on model
model_name = self.model.name_or_path
self.tokenizer = transformers.AutoTokenizer.from_pretrained(
model_name,
revision=revision,
trust_remote_code=trust_remote_code,
use_fast=use_fast_tokenizer,
model_name, **kwargs
)
return None

Expand Down
Loading