Skip to content

fix lm-eval & vllm check tokenizer type #1287

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

Merged
merged 1 commit into from
Feb 18, 2025
Merged

fix lm-eval & vllm check tokenizer type #1287

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 4 additions & 4 deletions gptqmodel/models/auto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -328,12 +328,13 @@ def eval(
if isinstance(model, BaseGPTQModel):
tokenizer = model.tokenizer
elif isinstance(model, PreTrainedModel) or model_id_or_path.strip():
tokenizer = Tokenicer.load(model_id_or_path)
tokenizer = Tokenicer.load(model_id_or_path).tokenizer # lm-eval checks if tokenizer's type is PretrainedTokenizer

if tokenizer is None:
raise ValueError("Tokenizer: Auto-loading of tokenizer failed with `model_or_id_or_path`. Please pass in `tokenizer` as argument.")

model_args["tokenizer"] = tokenizer
if backend=="gptqmodel": # vllm loads tokenizer
model_args["tokenizer"] = tokenizer

if framework == EVAL.LM_EVAL:
for task in tasks:
Expand Down Expand Up @@ -473,5 +474,4 @@ def push_to_hub(repo_id: str,
folder_path=quantized_path,
repo_id=repo_id,
repo_type=repo_type,
)

)