---
license: apache-2.0
---

## Introduce

Quantizing the [TIGER-Lab/StructLM-7B-Mistral](https://huggingface.co/TIGER-Lab/StructLM-7B-Mistral) to f16, q2, q3, q4, q5, q6 and q8 with Llama.cpp.


## Prompt Template

```
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.


### Instruction:
{instruction}

{input}

{question}

### Response:
```

IMPORTANT!! - For more details, check out [StructLM-7B-Mistral](https://huggingface.co/TIGER-Lab/StructLM-7B-Mistral).


![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f1c1b9a39cf6f5c63f029a/q7QN1DZSycPx-gv9Peaw8.png)