Task
Other
C
nomic-ai/CodeRankEmbed
Other·nomic-ai· 686.2K· 74
sentence-transformers
mit
136.7M params
arxiv:2412.01007base_model:Snowflake/snowflake-arctic-embed-m-longbase_model:finetune:Snowflake/snowflake-arctic-embed-m-longlicense:mitregion:us
CodeRankEmbed is a 137M bi-encoder supporting 8192 context length for code retrieval. It significantly outperforms various open-source and proprietary code embedding models on various code retrieval tasks.
# pull & run locally
pip install mlforge-sdk && mlforge pull nomic-ai/CodeRankEmbed
pip install mlforge-sdk && mlforge pull nomic-ai/CodeRankEmbed
Model details
Provider
nomic-ai
Framework
sentence-transformers
Parameters
136.7M
Size
522 MB
License
mit
Downloads
686.2K
Likes
74
Paper
arXiv:2412.01007
Updated
2025-06-24
About nomic-ai/CodeRankEmbed
CodeRankEmbed is a 137M bi-encoder supporting 8192 context length for code retrieval. It significantly outperforms various open-source and proprietary code embedding models on various code retrieval tasks.