# Model Card for Mistral-7B-Instruct-v0.2-8bit

The Mistral-7B-Instruct-v0.2-8bit is a 8bit quantize version with torch_dtype=torch.float16, I just load in 8bit and push here [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).

For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/la-plateforme/).

```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "mistralai/Mistral-7B-Instruct-v0.2"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    load_in_8bit=True,
    use_flash_attention_2=True,
    torch_dtype=torch.float16,
    )

model.push_to_hub("LsTam/Mistral-7B-Instruct-v0.2-8bit")
```

To use it:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tok_name = "mistralai/Mistral-7B-Instruct-v0.2"
model_name = "LsTam/Mistral-7B-Instruct-v0.2-8bit"

tokenizer = AutoTokenizer.from_pretrained(tok_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    use_flash_attention_2=True,
    )
```