|
--- |
|
license: llama3 |
|
inference: false |
|
base_model: gradientai/Llama-3-8B-Instruct-Gradient-1048k |
|
base_model_relation: quantized |
|
tags: |
|
- green |
|
- p8 |
|
- llmware-chat |
|
- ov |
|
--- |
|
|
|
# gradientai-llama3-8b-1048k-ov |
|
|
|
|
|
**gradientai-llama3-8b-1048k-ov** is an OpenVino int4 quantized version of GradientAI finetune of Llama3, providing a fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU. |
|
|
|
[**gradientai-llama3-8b-1048k**](https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-1048k) is a context window expansion finetune of leading open source general foundation model from Meta. |
|
|
|
|
|
### Model Description |
|
|
|
- **Developed by:** gradientai |
|
- **Quantized by:** llmware |
|
- **Model type:** llama-3.1 |
|
- **Parameters:** 8 billion |
|
- **Model Parent:** gradientai/Llama-3-8B-Instruct-Gradient-1048K |
|
- **Language(s) (NLP):** English |
|
- **License:** Llama 3.1 Community License |
|
- **Uses:** General chat use cases |
|
- **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) |
