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

community[patch]: Fix HuggingFace LLM to not repeat the prompt as part of the result #17363

Closed
wants to merge 8 commits into from
Closed

community[patch]: Fix HuggingFace LLM to not repeat the prompt as part of the result #17363

Changes from 2 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
9cc88b0
Let huggingface llm don't repeat prompt
lin-calvin Feb 10, 2024
721ec2e
Update huggingface_hub.py
lin-calvin Feb 10, 2024
2f84941
put `return_full_text` the first item so that user can change it
lin-calvin Feb 11, 2024
8edba45
Fix a typo
lin-calvin Feb 12, 2024
7feea66
Update libs/community/langchain_community/llms/huggingface_hub.py
eyurtsev Feb 13, 2024
e24a607
Make it only for 'text-generation'
lin-calvin Feb 13, 2024
26e5f8a
Fix format
lin-calvin Feb 13, 2024
d1c8254
Update huggingface_hub.py
lin-calvin Feb 15, 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
2 changes: 1 addition & 1 deletion libs/community/langchain_community/llms/huggingface_hub.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,7 @@ def _call(
response = hf("Tell me a joke.")
"""
_model_kwargs = self.model_kwargs or {}
parameters = {**_model_kwargs, **kwargs}
parameters = {**_model_kwargs, **kwargs, "return_full_text": False}
lin-calvin marked this conversation as resolved.
Show resolved Hide resolved

response = self.client.post(
json={"inputs": prompt, "parameters": parameters}, task=self.task
Expand Down
Loading