---
library_name: transformers
license: llama3.2
base_model:
- meta-llama/Llama-3.2-1B-Instruct
---

# This model has been xMADified!

This repository contains [`meta-llama/Llama-3.2-1B-Instruct`](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) quantized from 16-bit floats to 4-bit integers, using xMAD.ai proprietary technology.

# How to Run Model

Loading the model checkpoint of this xMADified model requires less than 2 GiB of VRAM. Hence it can be efficiently run on most laptop GPUs.

**Package prerequisites**: Run the following commands to install the required packages.
```bash
pip install -q --upgrade transformers accelerate optimum
pip install -q --no-build-isolation auto-gptq
```

**Sample Inference Code**

```python
from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM

model_id = "xmadai/Llama-3.2-1B-Instruct-xMADai-4bit"
prompt = [
  {"role": "system", "content": "You are a helpful assistant, that responds as a pirate."},
  {"role": "user", "content": "What's Deep Learning?"},
]

tokenizer = AutoTokenizer.from_pretrained(model_id)

inputs = tokenizer.apply_chat_template(
  prompt,
  tokenize=True,
  add_generation_prompt=True,
  return_tensors="pt",
  return_dict=True,
).to("cuda")

model = AutoGPTQForCausalLM.from_quantized(
    model_id,
    device_map='auto',
    trust_remote_code=True,
)

outputs = model.generate(**inputs, do_sample=True, max_new_tokens=256)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
```

Model | GPU Memory Requirement
--- | ---
Llama-3.2-3B-Instruct-xMADai-4bit | 6.5 GB → 3.5 GB
Llama-3.2-1B-Instruct-xMADai-4bit | 2.5 → 2 GB
Llama-3.1-405B-Instruct-xMADai-4bit | 800 GB (16 H100s) → 250 GB (8 V100)
Llama-3.1-8B-Instruct-xMADai-4bit | 16 → 7 GB

For additional xMADified models, access to fine-tuning, and general questions, please contact us at support@xmad.ai and join our waiting list.