feat: Add support for 01 model platform #1093
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
2 tasks
MuggleJinx
force-pushed
the
add_yi_model
branch
from
e5d8e88
to
eebbc57
Compare
Wendong-Fan
reviewed
Oct 26, 2024
There was a problem hiding this comment.
thanks @MuggleJinx 's contribution! Left some comments below
camel/configs/yi_config.py
Outdated
Comment on lines
51
to
67
| stop (Union[str, Sequence[str], NotGiven], optional): Up to `4` | ||
| sequences where the API will stop generating further tokens. | ||
| (default: :obj:`NOT_GIVEN`) | ||
| presence_penalty (float, optional): Number between :obj:`-2.0` and | ||
| :obj:`2.0`. Positive values penalize new tokens based on whether | ||
| they appear in the text so far, increasing the model's likelihood | ||
| to talk about new topics. (default: :obj:`0.0`) | ||
| frequency_penalty (float, optional): Number between :obj:`-2.0` and | ||
| :obj:`2.0`. Positive values penalize new tokens based on their | ||
| existing frequency in the text so far, decreasing the model's | ||
| likelihood to repeat the same line verbatim. (default: :obj:`0.0`) | ||
| logit_bias (dict, optional): Modify the likelihood of specified tokens | ||
| appearing in the completion. Accepts a json object that maps tokens | ||
| (specified by their token ID in the tokenizer) to an associated | ||
| bias value from :obj:`-100` to :obj:`100`. (default: :obj:`{}`) | ||
| user (str, optional): A unique identifier representing your end-user, | ||
| which can help monitor and detect abuse. (default: :obj:`""`) |
There was a problem hiding this comment.
from yi's doc, I didn't see they mentioned they support these arguments and I think they are not supported yet
camel/utils/token_counting.py
Outdated
| model_type (UnifiedModelType): Model type for which tokens will be | ||
| counted. | ||
| """ | ||
| self._internal_tokenizer = OpenAITokenCounter(model_type) |
There was a problem hiding this comment.
how could Yi's model_type used by OpenAITokenCounter?
MuggleJinx
force-pushed
the
add_yi_model
branch
from
eebbc57
to
cc067bc
Compare
Wendong-Fan
reviewed
Oct 30, 2024
Co-authored-by: Wendong-Fan <133094783+Wendong-Fan@users.noreply.github.com>
lightaime
reviewed
Oct 30, 2024
Comment on lines
+112
to
+113
| elif model_platform.is_yi and model_type.is_yi: | ||
| model_class = YiModel |
There was a problem hiding this comment.
Would be better to move this above the ModelType.STUB.
lightaime
reviewed
Oct 30, 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.
Description
This PR adds support for the Yi-series LLM models, including yi-lightning, yi-large, yi-medium, and yi-large-turbo. The addition of Yi-series models enhances the platform’s capabilities, providing support for a broader range of language models and enabling users to leverage different performance tiers.
Motivation and Context
Closes issue #1066.
Types of changes
What types of changes does your code introduce? Put an
xin all the boxes that apply:Implemented Tasks
Checklist
Go over all the following points, and put an
xin all the boxes that apply.If you are unsure about any of these, don't hesitate to ask. We are here to help!