Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat:Updated Together AI models #336

Merged
merged 2 commits into from
Jun 10, 2024

Conversation

HavenDV
Copy link
Contributor

@HavenDV HavenDV commented Jun 10, 2024

Created by Github Actions

Summary by CodeRabbit

  • New Features

    • Introduced new chat models: Qwen2Instruct72B, ReservedDbrxInstruct, and MetaLlama370BChat.
    • Added unique identifiers for each new model for better tracking and configuration.
  • Enhancements

    • Updated configurations for the MetaLlama370BChat model for improved performance and accuracy.

Copy link
Contributor

coderabbitai bot commented Jun 10, 2024

Walkthrough

The recent changes introduce new models and update existing ones in the TogetherAI provider. Specifically, new classes for Qwen2Instruct72BModel, ReservedDbrxInstructModel, and MetaLlama370BChatModel have been added, each linked with unique model IDs. Corresponding updates were also made in the TogetherAiModelIds enum and the TogetherAiModelProvider class to accommodate these new models.

Changes

File Path Change Summary
src/Providers/TogetherAI/src/Predefined/AllModels.cs Added new classes for Qwen2Instruct72BModel, ReservedDbrxInstructModel, and MetaLlama370BChatModel.
src/Providers/TogetherAI/src/TogetherAiModelIds.cs Added new model IDs Qwen2Instruct72B and ReservedDbrxInstruct, and updated details for MetaLlama370BChat.
src/Providers/TogetherAI/src/TogetherAiModelProvider.cs Added configurations for new models and modified configurations for MetaLlama370BChat.

Poem

In the land of code, where models play,
New friends have joined the fray today.
Qwen and Reserved, with MetaLlama in tow,
TogetherAI’s brilliance continues to grow.
With IDs and configs set just right,
Our models shine ever so bright. 🌟


Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share
Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai generate interesting stats about this repository and render them as a table.
    • @coderabbitai show all the console.log statements in this repository.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (invoked as PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Additionally, you can add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.

CodeRabbit Configration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@github-actions github-actions bot enabled auto-merge June 10, 2024 06:36
Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between 6239436 and b6058e0.

Files selected for processing (3)
  • src/Providers/TogetherAI/src/Predefined/AllModels.cs (4 hunks)
  • src/Providers/TogetherAI/src/TogetherAiModelIds.cs (4 hunks)
  • src/Providers/TogetherAI/src/TogetherAiModelProvider.cs (3 hunks)
Additional comments not posted (9)
src/Providers/TogetherAI/src/TogetherAiModelProvider.cs (3)

31-31: The addition of Qwen2Instruct72B model configuration looks correct and aligns with the PR's objective to update and add new models.


57-57: The configuration for ReservedDbrxInstruct is added correctly. However, ensure that the memory allocation (0) is intentional and appropriate for this model.


79-79: The updated configuration for MetaLlama370BChat appears to be in line with the intended enhancements. Confirm that the updated parameters meet the expected performance and resource usage criteria.

src/Providers/TogetherAI/src/Predefined/AllModels.cs (3)

98-100: The class Qwen2Instruct72BModel has been added correctly and follows the established pattern for model class declarations.


228-230: The class ReservedDbrxInstructModel is correctly declared. Ensure that the provider instance passed to it is configured to handle the specific needs of this model.


338-340: The update to MetaLlama370BChatModel is appropriate. Verify that the provider instance is correctly configured to support the new parameters of this model.

src/Providers/TogetherAI/src/TogetherAiModelIds.cs (3)

218-227: The addition of Qwen2Instruct72B is well-documented and follows the established metadata format. Good job maintaining consistency.


504-513: The addition of ReservedDbrxInstruct is complete with all required metadata. Consider adding a note or comment in the documentation to explain the "Reserved" status if it has specific implications or restrictions.


746-755: The addition of MetaLlama370BChat is well-documented. Ensure that the modified configurations mentioned in the AI-generated summary are reflected and verified in the model provider's configuration file.

Verification successful

The addition of MetaLlama370BChat is well-documented. Ensure that the modified configurations mentioned in the AI-generated summary are reflected and verified in the model provider's configuration file.

#!/bin/bash
# Description: Verify the configuration changes for `MetaLlama370BChat` in the model provider's configuration file.

# Test: Search for the configuration details. Expect: Updated configuration details for `MetaLlama370BChat`.
rg --type csharp $'MetaLlama370BChat' src/Providers/TogetherAI/src/TogetherAiModelProvider.cs

-->
The configuration details for MetaLlama370BChat have been found in the TogetherAiModelProvider.cs file, confirming the update:

  • { TogetherAiModelIds.MetaLlama370BChat, new ChatModels("meta-llama/Llama-3-70b-chat-hf",8192,9.000000000000001E-07,9.000000000000001E-07)}

This indicates that the model ID and its associated configurations have been correctly added.

Scripts executed

The following scripts were executed for the analysis:


Script:

#!/bin/bash
# Description: Verify the configuration changes for `MetaLlama370BChat` in the model provider's configuration file.

# Test: Search for the configuration details. Expect: Updated configuration details for `MetaLlama370BChat`.
rg --type csharp $'MetaLlama370BChat' src/Providers/TogetherAI/src/TogetherAiModelProvider.cs

Length of output: 240

@github-actions github-actions bot merged commit 52ef032 into main Jun 10, 2024
3 checks passed
@github-actions github-actions bot deleted the bot/update-together_202406100632 branch June 10, 2024 07:16
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant