Llama3.1 #56
Merged
Llama3.1 #56
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
farzadab
force-pushed
the
farzad-llama3.1
branch
from
797c44f to
708cde4
Compare
farzadab
commented
Jul 25, 2024
zqhuang211
reviewed
Jul 25, 2024
zqhuang211
reviewed
Jul 25, 2024
|
Huh, the transformers version change was note pushed. |
zqhuang211
reviewed
Jul 25, 2024
zqhuang211
approved these changes
Jul 25, 2024
akshat0311
pushed a commit
to jiviai/audio-llm
that referenced
this pull request
Jan 30, 2025
* upgrade transformers for llama 3.1 * fix cache on new version * TRAIN_ARGS instead of UV_CONFIG * remove matchtrain validation
zqhuang211
added a commit
that referenced
this pull request
Feb 12, 2025
- add fleurs data set - update WER calculation to use whisper normalization to be consistent with the whisper paper - update several datasets to include proper lang_id that is needed for whisper-normalization - add new eval configs for commonvoice, fleurs, and covost2 - add test cases for wer and bleu
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Outdated suggestions cannot be applied.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.
This PR enables Llama 3.1 training and loading.
Using Llama 3.1 required us to upgrade transformers. The new version changes caching so there are some changes related to that as well.