Forward-merge release/1.4 into develop #1470
Merged
+13
−25
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
#1464) ## Description This PR completes the model migration started in PR #1425 by updating the remaining 6 examples that were causing CI test failures. Updated 6 config files to use Nemotron 30B Updated READMEs to reflect model changes. ## Fixes 20 CI test failures : - mixture_of_agents (2 failures - timeout/hang) - tool_calling-reasoning (1 failure - parsing error) - simple_calculator (13 failures - recursion/parsing errors) - simple_calculator_eval (1 failure - workflow interrupted) - simple_web_query (1 failure - missing Action) - simple_web_query_eval (1 failure - missing intermediate_steps) ## Root Cause Llama 3.1/3.3 models struggle with the current ReAct prompt format, causing parsing errors, recursion limits, and timeouts. ## Solution Migrate to Nemotron models (proven to work in PR #1425): - `meta/llama-3.1-405b-instruct` -> `nvidia/nemotron-3-nano-30b-a3b` - `meta/llama-3.3-70b-instruct` -> `nvidia/nemotron-3-nano-30b-a3b` - `meta/llama-3.1-70b-instruct` -> `nvidia/nemotron-3-nano-30b-a3b` ## Testing Tested locally with mixture_of_agents example, completes successfully instead of hanging/timing out. ## By Submitting this PR I confirm: - I am familiar with the [Contributing Guidelines](https://github.com/NVIDIA/NeMo-Agent-Toolkit/blob/develop/docs/source/resources/contributing/index.md). - We require that all contributors "sign-off" on their commits. This certifies that the contribution is your original work, or you have rights to submit it under the same license, or a compatible license. - Any contribution which contains commits that are not Signed-Off will not be accepted. - When the PR is ready for review, new or existing tests cover these changes. - When the PR is ready for review, the documentation is up to date with these changes. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Chores** * Updated example configurations to use NVIDIA Nemotron models across multiple examples; other settings (temperature, token limits, and related parameters) remain unchanged. * **Documentation** * Updated example README content and evaluation docs to replace references to previous Llama variants with NVIDIA Nemotron models and removed corresponding legacy evaluation entries. <sub>✏️ Tip: You can customize this high-level summary in your review settings.</sub> <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: mnajafian-nv <mnajafian@nvidia.com>
Author
|
SUCCESS - forward-merge complete. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Forward-merge triggered by push to release/1.4 that creates a PR to keep develop up-to-date. If this PR is unable to be immediately merged due to conflicts, it will remain open for the team to manually merge. See forward-merger docs for more info.