VectorDB-Plugin-for-LM-Studio icon indicating copy to clipboard operation
VectorDB-Plugin-for-LM-Studio copied to clipboard

evaluate code-specific embedding models

Open BBC-Esq opened this issue 10 months ago • 3 comments

https://huggingface.co/cornstack/CodeRankEmbed https://huggingface.co/codesage/codesage-large-v2 https://huggingface.co/codesage/codesage-base-v2 https://huggingface.co/codesage/codesage-small-v2 https://huggingface.co/Salesforce/SFR-Embedding-Code-2B_R https://huggingface.co/Salesforce/SFR-Embedding-Code-400M_R

BBC-Esq avatar Jan 18 '25 10:01 BBC-Esq

Also necessitates splitting .py or other programming language with langchain's code-specific splitting logic. Also add various programming file extensions to accepted list, use appropriate loaders, etc.

BBC-Esq avatar Mar 25 '25 14:03 BBC-Esq

https://code-representation-learning.github.io/codesage-v2.html

BBC-Esq avatar Apr 06 '25 03:04 BBC-Esq

https://huggingface.co/nomic-ai/nomic-embed-code

BBC-Esq avatar Apr 06 '25 03:04 BBC-Esq