---
license: apache-2.0
base_model:
- liuhaotian/llava-v1.6-mistral-7b
---
This is Q8_0 quantization model of Llava1.6.

Run it by llama_cpp

```python
# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Steven0090/llava1.6-Mistral-7B-Instruct-v0.2-gguf",
	filename="Mistral-7B-Instruct-v0.2-Q8_0.gguf",
)
```