Downloads · 30 days
72
25% of all-time downloads
agentrag-embed-v1
dung6903/agentrag-embed-v1
agentrag-embed-v1 is a sentence similarity model from dung6903. Use it when you need a score for how close two texts are. It is set up for sentence-transformers. The card lists the license as mit.
Vietnamese-medical fine-tune of intfloat/multilingual-e5-base for RAG retrieval in the AgentRag project.
All-time downloads
289
Public
Parameters
278M
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 98%
At a glance
- Task
- Sentence Similarity
- Library
- sentence-transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Jul 4, 2026
- Updated
- Jul 4, 2026
- SHA
- e315f4b2
Base models
Model card
From the Hugging Face model README
agentrag-embed-v1
Vietnamese-medical fine-tune of intfloat/multilingual-e5-base for RAG retrieval in the AgentRag project.
- Pooling: mean (+ L2 normalize)
- Dimensions: 768
- Max sequence length: 512
- Domain: Vietnamese medical documents
- Training: 5.3k (query, positive, negative) triplets, MultipleNegativesRankingLoss, 2 epochs
- Eval: recall@10 +0.20 over base e5 on the project's retrieval benchmark (C1)
Serving with TEI
services:
tei:
image: ghcr.io/huggingface/text-embeddings-inference:cuda-latest
command:
- --model-id=dung6903/agentrag-embed-v1
- --pooling=mean
Query prefix conventions follow e5: query: ... / passage: ....
- Task
- Sentence Similarity
- Library
- sentence-transformers
- Type
- xlm-roberta
- License
- mit
- Languages
- vi
- Created
- Jul 4, 2026
- Updated
- Jul 4, 2026