Skip to content

Fix Mistral chat template (mistral_v7_tekken)#2710

Merged
NanoCode012 merged 1 commit into
axolotl-ai-cloud:mainfrom
mashdragon:patch-1
May 28, 2025
Merged

Fix Mistral chat template (mistral_v7_tekken)#2710
NanoCode012 merged 1 commit into
axolotl-ai-cloud:mainfrom
mashdragon:patch-1

Conversation

@mashdragon

@mashdragon mashdragon commented May 23, 2025

Copy link
Copy Markdown
Contributor

Per https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/commit/4b8dd8aae705887db5295fcbff4aedbb92d682eb#d2h-482763

Description

The EOS token isn't set properly in the old unfixed chat template included in axolotl.

Motivation and Context

You can't train Mistral instruction models properly without this change since the EOS token is not inserted after the assistant response.

How has this been tested?

Ran on a dataset and observed the output of data preprocessing.

Summary by CodeRabbit

  • Bug Fixes
    • Improved handling of system and message content types in chat, ensuring better support for both string and list formats.
    • Enhanced robustness for user, system, and assistant message processing, especially for messages containing multiple content blocks or images.

@coderabbitai

coderabbitai Bot commented May 23, 2025

Copy link
Copy Markdown
Contributor

Walkthrough

The "mistral_v7_tekken" chat template in the codebase was updated to better handle system and message content that can be either strings or lists of blocks. The logic now checks content types and extracts text accordingly, improving robustness for various message formats without altering public interfaces.

Changes

File(s) Change Summary
src/axolotl/utils/chat_templates.py Updated "mistral_v7_tekken" chat template to handle string or list content types for messages.

Poem

In the warren of code where templates reside,
A rabbit hopped in, with logic as guide.
Now strings or lists, it handles with care,
Extracting the text from messages there.
With checks and exceptions, robust and neat—
This bunny ensures chats never skip a beat! 🐇✨

Note

⚡️ AI Code Reviews for VS Code, Cursor, Windsurf

CodeRabbit now has a plugin for VS Code, Cursor and Windsurf. This brings AI code reviews directly in the code editor. Each commit is reviewed immediately, finding bugs before the PR is raised. Seamless context handoff to your AI code agent ensures that you can easily incorporate review feedback.
Learn more here.


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 5f8f817 and 4d3e274.

📒 Files selected for processing (1)
  • src/axolotl/utils/chat_templates.py (1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (6)
  • GitHub Check: PyTest from Source Dist (3.11, 2.7.0)
  • GitHub Check: PyTest (3.11, 2.7.0)
  • GitHub Check: PyTest from Source Dist (3.11, 2.6.0)
  • GitHub Check: PyTest (3.11, 2.6.0)
  • GitHub Check: PyTest from Source Dist (3.11, 2.5.1)
  • GitHub Check: PyTest (3.11, 2.5.1)
🔇 Additional comments (1)
src/axolotl/utils/chat_templates.py (1)

23-23: Effective fix for the Mistral EOS token issue

The updated mistral_v7_tekken chat template now correctly appends the eos_token after the assistant's content, whether that content is a string or a list of blocks. This is crucial for proper training of Mistral instruction models as mentioned in the PR objectives.

Additionally, the template has been enhanced to handle different message content types (strings vs. lists of blocks) more robustly throughout the template, improving the overall versatility.

✨ Finishing Touches
  • 📝 Generate Docstrings

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@codecov

codecov Bot commented May 23, 2025

Copy link
Copy Markdown

Codecov Report

All modified and coverable lines are covered by tests ✅

📢 Thoughts on this report? Let us know!

@NanoCode012 NanoCode012 left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you!

@NanoCode012 NanoCode012 self-assigned this May 27, 2025
@NanoCode012 NanoCode012 merged commit add2025 into axolotl-ai-cloud:main May 28, 2025
16 checks passed
@mashdragon mashdragon deleted the patch-1 branch June 1, 2025 03:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants