Skip to content

fix: make message formatting compatible with tokenizers with no bos/eos token#118

Merged
terrykong merged 3 commits intomainfrom
ashors/fix-qwen-sft
Apr 3, 2025
Merged

fix: make message formatting compatible with tokenizers with no bos/eos token#118
terrykong merged 3 commits intomainfrom
ashors/fix-qwen-sft

Conversation

@ashors1
Copy link
Copy Markdown
Contributor

@ashors1 ashors1 commented Apr 2, 2025

What does this PR do ?

Add a one line overview of what this PR aims to accomplish.

Issues

closes #117

Usage

  • You can potentially add a usage example below
# Add a code snippet demonstrating how to use this 

Before your PR is "Ready for review"

Pre checks:

  • Make sure you read and followed Contributor guidelines
  • Did you write any new necessary tests?
  • Did you run the unit tests and functional tests locally? Visit our Testing Guide for how to run tests
  • Did you add or update any necessary documentation? Visit our Document Development Guide for how to write, build and test the docs.

Additional Information

  • ...

Signed-off-by: ashors1 <ashors@nvidia.com>
Comment thread nemo_reinforcer/data/llm_message_utils.py
Signed-off-by: ashors1 <ashors@nvidia.com>
@ashors1 ashors1 added Run CICD and removed Run CICD labels Apr 3, 2025
@ashors1 ashors1 requested a review from terrykong April 3, 2025 05:26
@terrykong terrykong enabled auto-merge (squash) April 3, 2025 16:50
@terrykong terrykong merged commit 6334494 into main Apr 3, 2025
11 checks passed
@terrykong terrykong deleted the ashors/fix-qwen-sft branch April 3, 2025 17:16
KiddoZhu pushed a commit that referenced this pull request May 6, 2025
…os token (#118)

Signed-off-by: ashors1 <ashors@nvidia.com>
Co-authored-by: Terry Kong <terrycurtiskong@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

SFT training with Qwen/Qwen2-1.5B fails

3 participants