feat: ✨ support Llama 3.2 Models with chat/completions request #1213
+171
−21
Conversation
This file contains hidden or 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
This PR adds support for Llama models that are deployed using the chat/completions endpoint instead of the completions endpoint.
Author
|
@HuanzhiMao, I would really appreciate it if you could take a look at this PR. |
Author
|
@ShishirPatil can you please take a look at this PR? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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 adds support for evaluating the Llama3.2-1B model with chat/completions requests. This is helpful in evaluating Llama models that only support chat/completions endpoint. For example, with Protopia where a stained glass transform transforms in the input text to obfuscated embeddings and we evaluate the Llama models on the obfuscated prompt. These are the baseline scores.
The scores comparing Llama 3.2 1B with the completions and chat/completions endpoint that is proposed in the PR.
