|
--- |
|
license: cc-by-sa-4.0 |
|
inference: false |
|
base_model: stabilityai/stablelm-zephyr-3b |
|
base_model_relation: quantized |
|
tags: |
|
- green |
|
- p3 |
|
- llmware-chat |
|
- ov |
|
--- |
|
|
|
# stablelm-zephyr-3b-ov |
|
|
|
**stablelm-zephyr-3b-ov** is an OpenVino int4 quantized version of Zephyr finetune of StableLM 3B. |
|
|
|
[**stablelm-zephyr-3b**](https://huggingface.co/stabilityai/stablelm-zephyr-3b) is a popular instruct trained chat model from StabilityAI, using techniques similar to the HuggingFace Zephyr model. |
|
|
|
|
|
### Model Description |
|
|
|
- **Developed by:** stabilityai |
|
- **Quantized by:** llmware |
|
- **Model type:** stablelm-3b |
|
- **Parameters:** 3 billion |
|
- **Model Parent:** stabilityai/stablelm-zephyr-3b |
|
- **Language(s) (NLP):** English |
|
- **License:** CC-By-SA-4.0 |
|
- **Uses:** General chat |
|
- **RAG Benchmark Accuracy Score:** NA |
|
- **Quantization:** int4 |
|
|
|
|
|
## Model Card Contact |
|
|
|
[llmware on github](https://www.github.com/llmware-ai/llmware) |
|
|
|
[llmware on hf](https://www.huggingface.co/llmware) |
|
|
|
[llmware website](https://www.llmware.ai) |
|
|
