set temperature to 0.01 for better llm compatibility #939
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@0Falli0 sorry about the really big delay but which llm/provider are you trying to make this compatible with? |
jjmachan
added
the
waiting
|
The main Issue is the fact that I am trying to make your metrics compatible with Mistral7b and Mixtral8x22 hosted via Huggingface Text Generation Interface(TGI). When provided a low temperature of 1e-8 for example the models just produce blank characters until the Token-Count is reached. |
github-actions
bot
removed
the
waiting
shahules786
approved these changes
Nov 8, 2024
dosubot
bot
added
the
size:S
|
Sorry for the late reply. I fixed the merge conflicts! |
|
Hi @0Falli0 |
anistark
added a commit
that referenced
this pull request
Sep 3, 2025
- Change temperature default from 1e-8 to 0.01 for better LLM compatibility - Fix issues with Mistral7b and Mixtral8x22 hosted via Hugging Face TGI - Apply code formatting fixes
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
#938
Change Temperature from 1e-8 to 0.01 for better llm Compatibility.