Provence: lightweight context pruning models for retrieval-augmented generation. Blogpost: https://huggingface.co/blog/nadiinchi/provence
NAVER LABS Europe
company
Verified
AI & ML interests
3D vision, speech, NLP, neural retrieval, computer vision, LLM, FMs, visual localization, robotics
Recent Activity
Organization Card
Edit this README.md markdown file to author your organization card.
Collections
6
Compression Models for RAG
-
Context Embeddings for Efficient Answer Generation in RAG
Paper • 2407.09252 • Published • 2 -
naver/cocom-v1-128-mistral-7b
Feature Extraction • Updated • 58 • 4 -
naver/cocom-v1-16-mistral-7b
Feature Extraction • Updated • 8 -
naver/cocom-v1-4-mistral-7b
Feature Extraction • Updated • 36 • 2
spaces
5
models
50
naver/provence-reranker-debertav3-v1
Text Ranking
•
Updated
•
1.46k
•
13
naver/trecdl22-crossencoder-electra
Text Ranking
•
Updated
•
5
•
1
naver/trecdl22-crossencoder-albert
Text Ranking
•
Updated
•
5
naver/trecdl22-crossencoder-debertav2
Text Ranking
•
Updated
•
7
naver/trecdl22-crossencoder-rankT53b-repro
Text Ranking
•
Updated
•
5
naver/trecdl22-crossencoder-debertav3
Text Ranking
•
Updated
•
4.26k
•
1
naver/oscar-mistral-small-24b
Updated
•
38
•
1
naver/oscar-qwen2-7B
Updated
•
76
•
1
naver/oscar-mistral-7B
Updated
•
116
•
1
naver/pisco-llama
Updated
•
23
•
3