README.md

---
base_model: mistralai/Mistral-7B-Instruct-v0.2
inference: false
license: apache-2.0
model_creator: mistralai
model_name: Mistral-7B-Instruct-v0.2-GPTQ
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
tags:
  - finetuned
  - quantized
  - 4-bit
  - gptq
  - transformers
  - pytorch
  - safetensors
  - mistral
  - text-generation
  - finetuned
  - arxiv:2310.06825
  - license:apache-2.0
  - autotrain_compatible
  - has_space
  - text-generation-inference
  - region:us  
---
# Description
[MaziyarPanahi/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/MaziyarPanahi/Mistral-7B-Instruct-v0.2-GPTQ) is a quantized (GPTQ) version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)

## How to use
### Install the necessary packages

```
pip install --upgrade accelerate auto-gptq transformers
```

### Example Python code


```python
from transformers import AutoTokenizer, pipeline
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import torch

model_id = "MaziyarPanahi/Mistral-7B-Instruct-v0.2-GPTQ"

quantize_config = BaseQuantizeConfig(
        bits=4,
        group_size=128,
        desc_act=False
    )

model = AutoGPTQForCausalLM.from_quantized(
        model_id,
        use_safetensors=True,
        device="cuda:0",
        quantize_config=quantize_config)

tokenizer = AutoTokenizer.from_pretrained(model_id)

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.95,
    repetition_penalty=1.1
)

outputs = pipe("What is a large language model?")
print(outputs[0]["generated_text"])
```