Downloads · 30 days
11
16% of all-time downloads
bling-qwen-1.5b-ov
llmware/bling-qwen-1.5b-ov
bling-qwen-1.5b-ov is a machine learning model from llmware. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
bling-qwen-1.5b-ov is a very small, very fast fact-based question-answering model, designed for retrieval augmented generation (RAG) with complex business documents, quantized and packaged in OpenVino int4 for AI PCs…
All-time downloads
70
Public
Repo size
1.2 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin1.2 GB · 99%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Sep 6, 2024
- Updated
- Oct 31, 2024
- SHA
- 7bbb9d4f
Base models
Model card
From the Hugging Face model README
bling-qwen-1.5b-ov
bling-qwen-1.5b-ov is a very small, very fast 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 is one of the smallest in the series, yet offers relatively high accuracy and quality.
Model Description
- Developed by: llmware
- Model type: qwen2
- Parameters: 1.5 billion
- Quantization: int4
- Model Parent: llmware/bling-qwen-1.5b
- Language(s) (NLP): English
- License: Apache 2.0
- Uses: Fact-based question-answering, RAG
- RAG Benchmark Accuracy Score: 93.5
Model Card Contact
- Type
- qwen2
- License
- apache-2.0
- Created
- Sep 6, 2024
- Updated
- Oct 31, 2024