README.md

---
license: mit
language:
- it
---
# Mistral-Ita-7B  GGUF
<!-- README_GGUF.md-provided-files start -->
## Provided files

| Name | Quant method | Bits | Size    | Use case                                         |
|------|--------------|------|---------|--------------------------------------------------|
| [mistal-Ita-7b-q3_k_m.gguf](https://huggingface.co/DeepMount00/Mistral-Ita-7b-GGUF/blob/main/mistal-Ita-7b-q3_k_m.gguf) | Q3_K_M        | 3    | 3.52 GB | very small, high quality loss                    |
| [mistal-Ita-7b-q4_k_m.gguf](https://huggingface.co/DeepMount00/Mistral-Ita-7b-GGUF/blob/main/mistal-Ita-7b-q4_k_m.gguf) | Q4_K_M        | 4    | 4.37 GB | medium, balanced quality - recommended           |
| [mistal-Ita-7b-q5_k_m.gguf](https://huggingface.co/DeepMount00/Mistral-Ita-7b-GGUF/blob/main/mistal-Ita-7b-q5_k_m.gguf) | Q5_K_M        | 5    | 5.13 GB | large, very low quality loss - recommended       |

<!-- README_GGUF.md-provided-files end -->

## How to Use
How to utilize my Mistral for Italian text generation

```python
from ctransformers import AutoModelForCausalLM

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("DeepMount00/Mistral-Ita-7b-GGUF", model_file="mistal-Ita-7b-q3_k_m.gguf", model_type="mistral", gpu_layers=0)

domanda = """Scrivi una funzione python che calcola la media tra questi valori"""
contesto = """
[-5, 10, 15, 20, 25, 30, 35]
"""

system_prompt = ''
prompt = domanda + "\n" + contesto
B_INST, E_INST = "[INST]", "[/INST]"
prompt = f"{system_prompt}{B_INST}{prompt}\n{E_INST}"

print(llm(prompt))
```