feat: use model name as adapter id in chat endpoints #2128
Merged
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
Narsil
reviewed
Jul 1, 2024
| @@ -673,7 +674,7 @@ async fn completions( | |||
| seed, | |||
| top_n_tokens: None, | |||
| grammar: None, | |||
| ..Default::default() | |||
| adapter_id: model.as_ref().filter(|m| *m != "tgi").map(String::from), | |||
There was a problem hiding this comment.
Can we remove this special value ? It should exist in the first place.
if openai requires a model id, then we should actually match it against the actual deployed model id, no ?
Narsil
approved these changes
Jul 8, 2024
ErikKaum
pushed a commit
that referenced
this pull request
Jul 26, 2024
yuanwu2017
pushed a commit
to yuanwu2017/tgi-gaudi
that referenced
this pull request
Sep 26, 2024
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Outdated suggestions cannot be applied.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 allows users to specify lora adapter ids as the
modelvalue in the/v1/chat/completionsand/v1/completionsendpoints.This feature aligns with other lora implementations and was mentioned here during the initial lora PR #2010 (comment)
curl localhost:3000/v1/chat/completions -s \ -H 'Content-Type: application/json' \ -X POST \ -d '{ "model": "predibase/customer_support", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "What is deep learning?" } ], "stream": false, "max_tokens": 20, "seed": 42 }' | jq .