fix: fix the chat stuck in infinite loop #1755
Merged
Conversation
This file contains 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
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hi @zoe27! Welcome to the ai16z community. Thanks for submitting your first pull request; your efforts are helping us accelerate towards AGI. We'll review it shortly. You are now a ai16z contributor!
|
@zoe27 The PR is failing with the check against the |
odilitime
changed the title
odilitime
reviewed
Jan 3, 2025
odilitime
requested changes
Jan 3, 2025
|
@zoe27 Nice! I also figured out this problem, but you have already fixed it! Thanks! |
odilitime
approved these changes
Jan 12, 2025
mgunnin
added a commit
to mgunnin/eliza-agent
that referenced
this pull request
Jan 12, 2025
* main: (704 commits) bump version (elizaOS#2193) feat(security): Implement comprehensive file upload security measures - Add FileSecurityValidator, file type restrictions, size limits, path traversal prevention, enhanced logging and security documentation (elizaOS#1753) (elizaOS#1806) fix(client-twitter): clean up mention deduplication (elizaOS#2185) fix postgres adapter migration extension creation which already exists at this point (elizaOS#2188) Update types.ts fix json format typo fix quai deps fix path Add Persian README File chore: lint and fix pass on develop (elizaOS#2180) bump version to 0,1,8 bump clean up unused var in catch comment out unused AkashMessage interface bump eslint so it doesn't crash remove duplicate TOGETHER in case, lint/unused var convert imageDescriptionsArray from let to const per lint fix: Koloxarto/fix ragknowledge for postgres (elizaOS#2153) fix: fix the chat stuck in infinite loop (elizaOS#1755) fix: remove problematic redundant uuid conversion and add api input param validations to api server (elizaOS#2051) ...
Tadeuchi
added a commit
to redstone-finance/eliza
that referenced
this pull request
Jan 13, 2025
0xpi-ai
pushed a commit
to 0xpi-ai/NayariAI
that referenced
this pull request
Jan 15, 2025
* fix the chat stuck in infinite loop * perfect the PR and keep the temprature and wordsToPunish in the generate response * Update README.md * Trigger CI checks --------- Co-authored-by: Odilitime <janesmith@airmail.cc>
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.
Relates to:
the chat stuck in infinite loop when using model_local #1213
Risks
Low
Background
What does this PR do?
This PR aim to fix the loop chat of the ai agent self when using the model_local
What kind of change is this?
modify the way of response generate in llama.ts
before this PR:
in this PR:
investigation step:
have not go to deeply to see what is the exactly different between
sequence.evaluateandchatsession, maybe can fix loop bug first, and for now, have not found any risk.Documentation changes needed?
Testing
Where should a reviewer start?
Detailed testing steps
Before
it loop the response and sometimes, the response is hard to understood
After
seems in a normal way to chat