search

huggingface / text-embeddings-inference

A blazing fast inference solution for text embeddings models
https://huggingface.co/docs/text-embeddings-inference/quick_tour
Apache License 2.0
2.87k stars 184 forks source link

Support NV-Embed-v2 model #419

Open jorgeantonio21 opened 1 month ago

jorgeantonio21 commented 1 month ago

Model description

The model can be found at: https://huggingface.co/nvidia/NV-Embed-v2.

NV-Embed-v2 is a generalist embedding model that ranks No. 1 on the Massive Text Embedding Benchmark (MTEB benchmark)(as of Aug 30, 2024) with a score of 72.31 across 56 text embedding tasks. It also holds the No. 1 in the retrieval sub-category (a score of 62.65 across 15 tasks) in the leaderboard, which is essential to the development of RAG technology.

Open source status

Provide useful links for the implementation

https://huggingface.co/nvidia/NV-Embed-v2

OlivierDehaene commented 1 month ago

Since the model is a modification of Mistral, it should be ok to modify the existing arch if someone wants to have a go at it.