added "tie_word_emebeddings" setting necessary for Llama 3.2 #1895
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Outdated suggestions cannot be applied.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.
Starting from Llama 3.2, the models use tied embeddings which means that the checkpoints no longer have a separate set of weights for reverse embeddings. This change allows the Transformer "tie_word_embeddings" setting to be read from config.json and instantiates the Llama3
ReversibleEmbedding
class with the correcttie_weights
setting.Without this, loading Llama 3.2 errors out with the following error message:
"SafetensorError: File does not contain tensor lm_head.weight"