Fix/issue 10113 embeddings use non default tokenizer #10629
Merged
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
… hosted_vllm models
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
|
|
litellm/proxy/proxy_server.py
Outdated
| @@ -3814,14 +3814,15 @@ async def embeddings( # noqa: PLR0915 | |||
| if m["model_name"] == data["model"] and ( | |||
| m["litellm_params"]["model"] in litellm.open_ai_embedding_models | |||
| or m["litellm_params"]["model"].startswith("azure/") | |||
| or m["litellm_params"]["model"].startswith("hosted_vllm/") | |||
There was a problem hiding this comment.
add a unit test for this in test_proxy_server.py in tests/litellm -
So there are no future regressions.
…of lists of tokens (int)" This reverts commit a48acd9.
…t a list of tokens
…accept a arrays of tokens as input When passing a list of tokens as input, verify the provider of the model by going through the list of models (`llm_model_list`). First, it check for model name then get the provider and verify if it accept or not arrays of tokens. If yes, then pass, else decode. Previously, it was verifying provider and model name at the same time resulting in decoding even if the current model checked was not the target one (looping onto `llm_model_list`)
…th input as array of tokens Ref: BerriAI#10113
|
Screenshot of the new test passing locally |
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Outdated suggestions cannot be applied.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.
Title
Embeddings: Not use default
gpt-3.5-turbo's tokenizerRelevant issues
Fixes #10113
Pre-Submission checklist
Please complete all items before asking a LiteLLM maintainer to review your PR
tests/litellm/directory, Adding at least 1 test is a hard requirement - see detailsmake test-unitType
🐛 Bug Fix
Changes