-
Notifications
You must be signed in to change notification settings - Fork 189
Unpin to support transformers==4.52.3
#1479
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review. Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed. |
Signed-off-by: Kyle Sayers <[email protected]>
83cd7aa
to
4285c9f
Compare
Signed-off-by: Kyle Sayers <[email protected]>
Could you stack this PR on top of #1411 ? It'll be easier to review |
@rahul-tuli This was pointed to main so CI would run |
Signed-off-by: Kyle Sayers <[email protected]>
Signed-off-by: Kyle Sayers <[email protected]>
Signed-off-by: Kyle Sayers <[email protected]>
transformers==4.52.3
Signed-off-by: Kyle Sayers <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
one nit
This closes #1457 |
Signed-off-by: Kyle Sayers <[email protected]>
@brian-dellabetta Sounds good, I've reverted the breakout |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
looks great, thanks!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Awesome! Looks good to me
## Purpose ## * Add support for mistral3 * Related: #1343 ## Prerequisites ## * #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 <[email protected]>
## Purpose ## * Support the latest transformers release ## Prerequisites ## * vllm-project#1481 * vllm-project#1411 ## Fixes ## * vllm-project#1457 ## Changes ## * Unpin transformers version * Add `torchvision`, `librosa`, and `soundfile` to dev dependencies (needed to test models) * Fix default ignore list for tracing debugger * Add back llama4 model tests --------- Signed-off-by: Kyle Sayers <[email protected]>
## 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 <[email protected]>
Purpose
Prerequisites
Fixes
Changes
torchvision
,librosa
, andsoundfile
to dev dependencies (needed to test models)