Skip to content

[Model] Mistral3 example and test#1490

Merged
kylesayrs merged 16 commits intomainfrom
kylesayrs/add-mistral3-tests
Jun 3, 2025
Merged

[Model] Mistral3 example and test#1490
kylesayrs merged 16 commits intomainfrom
kylesayrs/add-mistral3-tests

Conversation

@kylesayrs
Copy link
Copy Markdown
Collaborator

@kylesayrs kylesayrs commented May 29, 2025

Purpose

Prerequisites

Changes

  • Added mistral3 example
  • This model does not automatically change the dtype of pixel_values to match the dtype of the model, so I had to do so manually in the collator and sample generation
  • This model has a very verbose chat template by default, which may be less conducive to calibration, so I added a custom shortened version

Testing

kylesayrs added 8 commits May 27, 2025 22:27
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Copy link
Copy Markdown
Collaborator

@brian-dellabetta brian-dellabetta left a comment

Choose a reason for hiding this comment

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

awesome that we get this for free now! nice

kylesayrs added 3 commits May 29, 2025 15:59
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Base automatically changed from kylesayrs/unpin-transformers to main May 29, 2025 21:50
@kylesayrs kylesayrs dismissed brian-dellabetta’s stale review May 29, 2025 21:50

The base branch was changed.

@kylesayrs kylesayrs added the ready When a PR is ready for review label May 30, 2025
kylesayrs added 3 commits May 30, 2025 10:30
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Copy link
Copy Markdown
Collaborator

@shanjiaz shanjiaz left a comment

Choose a reason for hiding this comment

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

Nice! Just one question, do we usually add test in tests/examples for each example?

@kylesayrs kylesayrs enabled auto-merge (squash) June 3, 2025 15:58
@kylesayrs kylesayrs merged commit 39a0a11 into main Jun 3, 2025
4 checks passed
@kylesayrs kylesayrs deleted the kylesayrs/add-mistral3-tests branch June 3, 2025 15:58
aireilly pushed a commit to aireilly/llm-compressor that referenced this pull request Jul 30, 2025
## Purpose ##
* Add support for mistral3
* Related: vllm-project#1343

## Prerequisites ##
* vllm-project#1479

## Changes ##
* Added mistral3 example
* This model does not automatically change the dtype of pixel_values to
match the dtype of the model, so I had to do so manually in the collator
and sample generation
* This model has a [very verbose chat template by
default](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/blob/main/chat_template.json),
which may be less conducive to calibration, so I added a custom
shortened version

## Testing ##
* Ran example to completion:
[nm-testing/Mistral-Small-3.1-24B-Instruct-2503-W4A16-G128](https://huggingface.co/nm-testing/Mistral-Small-3.1-24B-Instruct-2503-W4A16-G128)

---------

Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ready When a PR is ready for review

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants