DRAGON Models
Collection
Production-grade RAG-optimized 6-7B parameter models - "Delivering RAG on ..." the leading foundation base models
•
23 items
•
Updated
•
46
dragon-yi-9b-ov
dragon-yi-9b-ov is a very high-quality fact-based question-answering model, designed for retrieval augmented generation (RAG) with complex business documents, quantized and packaged in OpenVino int4 for AI PCs using Intel GPU, CPU and NPU.
This model provides high accuracy and generation quality, and is the largest model in the series.
Model Description
- Developed by: llmware
- Model type: yi-1.5v-9b
- Parameters: 8.8 billion
- Quantization: int4
- Model Parent: llmware/dragon-yi-1.5v-9b
- Language(s) (NLP): English
- License: Apache 2.0
- Uses: Fact-based question-answering, RAG
- RAG Benchmark Accuracy Score: 98.0
Model Card Contact
- Downloads last month
- 20
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model authors have turned it off explicitly.
Model tree for llmware/dragon-yi-9b-ov
Base model
llmware/dragon-yi-1.5v-9b