---
language:
- it
license: apache-2.0
tags:
- text-generation-inference
- text generation
---

# Mistral-7B-v0.1 for Italian Language Text Generation

## Model Architecture
The Mistral-7B-v0.1 model is a transformer-based model that can handle a variety of tasks including but not limited to translation, summarization, and text completion. It's particularly designed for the Italian language and can be fine-tuned for specific tasks.


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

```python
import transformers
from transformers import TextStreamer
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

MODEL_NAME = "DeepMount00/Mistral-Ita-7b"

model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.bfloat16).eval()
model.to(device)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)

def generate_answer(prompt):
    encoded_input = tokenizer.apply_chat_template([{"role": "user", "content": prompt}], return_tensors="pt").to(device)
    generated_ids = model.generate(**encoded_input, max_new_tokens=200, do_sample=True, temperature=0.001, eos_token_id=tokenizer.eos_token_id)
    answer = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
    return answer

prompt = "Se un mattone pesa 1kg più metà di se stesso, quanto pesa il mattone? Rispondi impostando l'equazione matematica"
print(generate_answer(prompt))

```
---
## Developer
[Michele Montebovi]