Skip to content

Fix the pooling method of BGE embedding model #2926

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
merrymercy merged 8 commits into from
Jan 24, 2024
+47 −6
Merged

Fix the pooling method of BGE embedding model #2926

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
ee21ecb
Update model_adapter.py
staoxiao Sep 22, 2023
39fc0b6
Update model_worker.py
staoxiao Sep 22, 2023
389a889
Merge pull request #1 from lm-sys/main
staoxiao Jan 16, 2024
b013949
Update model_adapter.py
staoxiao Jan 16, 2024
ba31c84
Update model_worker.py
staoxiao Jan 16, 2024
2679768
Update model_worker.py
staoxiao Jan 16, 2024
056ffb3
Update model_worker.py
staoxiao Jan 17, 2024
f3bce43
reformat
staoxiao Jan 17, 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
Next Next commit
Update model_adapter.py
  • Loading branch information
@staoxiao
staoxiao authored Sep 22, 2023
commit ee21ecb19cc21fb44578b95223dbc1a98bc08358
2 changes: 2 additions & 0 deletions fastchat/model/model_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1413,6 +1413,8 @@ def load_model(self, model_path: str, from_pretrained_kwargs: dict):
model.config.max_sequence_length = min(
model.config.max_position_embeddings, tokenizer.model_max_length
)
model.is_bge = True
model.eval()
return model, tokenizer

def get_default_conv_template(self, model_path: str) -> Conversation:
Expand Down