---
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
license: llama3.2
library_name: transformers
tags:
- autoround
- auto-round
- intel
- intel-autoround
- gptq
- woq
- meta
- pytorch
- llama
- llama-3
model_name: Llama 3.2 3B
base_model: meta-llama/Llama-3.2-3B
inference: false
model_creator: meta-llama
pipeline_tag: text-generation
prompt_template: '{prompt}
  '
quantized_by: fbaldassarri
---

## Model Information

Quantized version of [meta-llama/Llama-3.2-3B](meta-llama/Llama-3.2-3B) using torch.float32 for quantization tuning.
- 8 bits (INT8)
- group size = 128
- Symmetrical Quantization
- Method WoQ (AutoRound format)

Fast and low memory, 2-3X speedup (slight accuracy drop at W4G128)

Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round)

Note: this INT8 version of Llama-3.2-3B has been quantized to run inference through CPU.

## Replication Recipe

### Step 1 Install Requirements

I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment. 

```
wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.3.tar.gz
tar -xvzf v0.4.3.tar.gz
cd auto-round-0.4.3
pip install -r requirements-cpu.txt --upgrade
```

### Step 2 Build Intel AutoRound wheel from sources

```
pip install -vvv --no-build-isolation -e .[cpu]
```

### Step 3 Script for Quantization

```
  from transformers import AutoModelForCausalLM, AutoTokenizer
  model_name = "meta-llama/Llama-3.2-3B"
  model = AutoModelForCausalLM.from_pretrained(model_name)
  tokenizer = AutoTokenizer.from_pretrained(model_name)
  from auto_round import AutoRound
  bits, group_size, sym, device, amp = 8, 128, True, 'cpu', False
  autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp)
  autoround.quantize()
  output_dir = "./AutoRound/meta-llama_Llama-3.2-3B-auto_round-int8-gs128-sym"
  autoround.save_quantized(output_dir, format='auto_round', inplace=True)
```

## License

[Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE)

## Disclaimer

This quantized model comes with no warrenty. It has been developed only for research purposes.