Add LLama 3.2 1B and 3B lightweight models descriptions #130
+19
−1
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Outdated suggestions cannot be applied.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 adds ModelConfigurations for the new Llama 3.2 lightweight models with 1B and 3B parameters, and bumps the Xcode project dependency on
swift-transformers
so that it can use the newSequence
processor, required for Llama v3.2.Llama 3.2 introduces two new lightweight versions with 1B and 3B parameters, which speeds the inference considerably when compared to the 3.1 8B version (on my M1 16Gb, it goes from 12 tokens/sec to 66 tokens/sec on the 1B model).