Add HF model support inc. DS-R1-Distill, Qwen needs yarn support #17421
Conversation
This file contains 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
yieldthought
requested review from
cglagovichTT,
mtairum and
uaydonat
as code owners
cglagovichTT
approved these changes
Jan 31, 2025
models/demos/llama3/tests/reference_outputs/Qwen2.5-7B-Instruct.refpt
Outdated
Show resolved
Hide resolved
|
@yieldthought Re-generated all Llama3 cache files in CI for N150 / N300 / T3K. TG will need to be regenerated at a later date through CI. Re-running all pipelines. The T3K old one was not even building correctly. |
mtairum
reviewed
Jan 31, 2025
mtairum
approved these changes
Jan 31, 2025
6 tasks
|
Ready to merge when tests pass |
|
All passing locally. Running the latest CI pipelines here. If they pass we're good to merge. |
This reverts commit bd491a2.
|
Updated the issues on the description. Investigating the remaining ones that consistently fail. |
2 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Problem description
Existing codebase loads the meta checkpoint format but many derivative models are only available on huggingface.
What's changed
Add support for loading HuggingFace model formats, paving the way for full Qwen support (pending yarn rope implementation) and adding DeepSeek-R1-Distill-Llama-70B support.
Checklist
All passing locally.