Add support for new models #1393
Conversation
|
Caution Review failedThe pull request is closed. WalkthroughThe recent updates enhance the Changes
Poem
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? TipsChatThere are 3 ways to chat with CodeRabbit:
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)
Additionally, you can add CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Files ignored due to path filters (1)
api/src/serge/data/models.jsonis excluded by!**/*.json
Files selected for processing (2)
- README.md (2 hunks)
- scripts/serge.env (1 hunks)
Files skipped from review due to trivial changes (1)
- scripts/serge.env
Additional comments not posted (2)
README.md (2)
55-57: Approved: Formatting changes for environment variables.The formatting adjustments improve readability and consistency.
76-99: Approved: Additions to model specifications.The additions of new models and variants enhance the comprehensiveness of the documentation.
However, verify the accuracy of the model names and variants to ensure correctness.
Verification successful
Verified: The model names and variants are accurately listed and used consistently across the codebase.
The model names and variants in the README.md file match those found in the
api/src/serge/data/models.jsonfile, confirming their accuracy.
- README.md
- api/src/serge/data/models.json
Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Verify the accuracy of the model names and variants. # Test: Search for the model names and variants in the codebase. Expect: Correct model names and variants. rg --type markdown -A 5 $'Gemma|Falcon|Med42|Meta-LlaMA-3|Phi'Length of output: 1485
Script:
#!/bin/bash # Description: Cross-reference the model names and variants in the README.md with other parts of the codebase or documentation. # Search for model names and variants in all markdown files to ensure they are accurately listed. rg --type markdown 'Gemma|Falcon|Med42|Meta-LlaMA-3|Phi'Length of output: 634
Script:
#!/bin/bash # Description: Cross-reference the model names and variants in the README.md with other parts of the codebase. # Search for model names and variants in the entire codebase to ensure they are accurately listed and used. rg 'Gemma|Falcon|Med42|Meta-LlaMA-3|Phi'Length of output: 3721
|
Blocked by abetlen/llama-cpp-python#1627 |
|
@Smartappli I'm closing this, open a new PR when changes are ready. |
Add support for Falcon 11B
Add support for Gemma-2-9B
Add support for Gemma-2-9B-Instruct
Add support for Gemma-2-27B
Add support for Gemma-2-27B-Instruct
Add support for Mathastral 7B
Add support for Meta-Llama-3.1 8B
Add support for Meta-Llama-3.1 8B-Instruct
Add support for Meta-Llama-3.1-70B
Add support for Meta-Llama-3.1 70B-Instruct
Add support for Mistral-Nemo-Instruct-2407
Add support for OpenChat 3.6
Add support for Phi 3.1-mini-4k-instruct
Add support for Phi 3.1-mini-128k-instruct