xmadai/Llama-3.1-70B-Instruct-xMADai-INT4

This model has been xMADified!

This repository contains meta-llama/Llama-3.1-70B-Instruct quantized from 16-bit floats to 4-bit integers, using xMAD.ai proprietary technology.

Why should I use this model?

1. Accuracy: This xMADified model is the best quantized version of the meta-llama/Llama-3.1-70B-Instruct model (40 GB only). See Table 1 below for model quality benchmarks.

2. Memory-efficiency: The full-precision model is around 140 GB, while this xMADified model is only around 40 GB, making it feasible to run on one 48 GB GPU.

3. Fine-tuning: These models are fine-tunable over the same reduced (48 GB GPUs) hardware in mere 3-clicks. Watch our product demo here

Table 1: xMAD vs. NeuralMagic

Model	LAMBADA Standard	LAMBADA OpenAI	MMLU	PIQA	WinoGrande
xmadai/Llama-3.1-70B-Instruct-xMADai-INT4 (this model)	72.70	76.07	81.75	83.41	78.53
neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w4a16	71.51	75.24	81.71	82.43	77.82

How to Run Model

Loading the model checkpoint of this xMADified model requires around 40 GB of VRAM. Hence it can be efficiently run on a single 48 GB GPU.

Package prerequisites:

1. Run the following *commands to install the required packages.

pip install torch==2.4.0  # Run following if you have CUDA version 11.8: pip install torch==2.4.0 --index-url https://download.pytorch.org/whl/cu118
pip install transformers accelerate optimum
pip install -vvv --no-build-isolation "git+https://github.com/PanQiWei/[email protected]"

Sample Inference Code

from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM
model_id = "xmadai/Llama-3.1-70B-Instruct-xMADai-INT4"
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, use_fast=False)
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=1024)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))

Citation

If you found this model useful, please cite our research paper.

@article{zhang2024leanquant,
  title={LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid},
  author={Zhang, Tianyi and Shrivastava, Anshumali},
  journal={arXiv preprint arXiv:2407.10032},
  year={2024},
  url={https://arxiv.org/abs/2407.10032},
}

Contact Us

For additional xMADified models, access to fine-tuning, and general questions, please contact us at [email protected] and join our waiting list.