README.md

---
license: llama3.2
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
base_model:
- meta-llama/Llama-3.2-3B-Instruct
pipeline_tag: text-generation
tags:
- gptqmodel
- modelcloud
- llama3.2
- instruct
- int4
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/641c13e7999935676ec7bc03/SCTn0F8MhToDFbdjuPxkw.png)

This model has been quantized using [GPTQModel](https://github.com/ModelCloud/GPTQModel).

- **bits**: 4
- **dynamic**: null
- **group_size**: 32
- **desc_act**: true
- **static_groups**: false
- **sym**: true
- **lm_head**: false
- **true_sequential**: true
- **quant_method**: "gptq"
- **checkpoint_format**: "gptq"
- **meta**：
  - **quantizer**: gptqmodel:1.1.0
  - **uri**: https://github.com/modelcloud/gptqmodel
  - **damp_percent**: 0.1
  - **damp_auto_increment**: 0.0015


## Example:
```python
from transformers import AutoTokenizer
from gptqmodel import GPTQModel

model_name = "ModelCloud/Llama-3.2-3B-Instruct-gptqmodel-4bit-vortex-v3"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = GPTQModel.from_quantized(model_name)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(input_ids=input_tensor.to(model.device), max_new_tokens=512)
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)

print(result)
```