abhinavkulkarni/VMware-open-llama-13b-open-instruct-w4-g128-awq

VMware/open-llama-13B-open-instruct (4-bit 128g AWQ Quantized)

Instruction-tuned version of the fully trained Open LLama 13B model.

This model is a 4-bit 128 group size AWQ quantized model. For more information about AWQ quantization, please click here.

Model Date

July 5, 2023

Model License

Please refer to original Open Llama model license (link).

Please refer to the AWQ quantization license (link).

CUDA Version

This model was successfully tested on CUDA driver v530.30.02 and runtime v11.7 with Python v3.10.11. Please note that AWQ requires NVIDIA GPUs with compute capability of 8.0 or higher.

For Docker users, the nvcr.io/nvidia/pytorch:23.06-py3 image is runtime v12.1 but otherwise the same as the configuration above and has also been verified to work.

How to Use

git clone https://github.com/mit-han-lab/llm-awq \
&& cd llm-awq \
&& git checkout f084f40bd996f3cf3a0633c1ad7d9d476c318aaa \
&& pip install -e . \
&& cd awq/kernels \
&& python setup.py install

import time
import torch
from awq.quantize.quantizer import real_quantize_model_weight
from transformers import AutoModelForCausalLM, AutoConfig, AutoTokenizer, TextStreamer
from accelerate import init_empty_weights, load_checkpoint_and_dispatch
from huggingface_hub import snapshot_download

model_name = "abhinavkulkarni/VMware-open-llama-13b-open-instruct"

# Config
config = AutoConfig.from_pretrained(model_name, trust_remote_code=True)

# Tokenizer
try:
    tokenizer = AutoTokenizer.from_pretrained(config.tokenizer_name, trust_remote_code=True)
except:
    tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False, trust_remote_code=True)
streamer = TextStreamer(tokenizer, skip_special_tokens=True)

# Model
w_bit = 4
q_config = {
    "zero_point": True,
    "q_group_size": 128,
}

load_quant = snapshot_download(model_name)

with init_empty_weights():
    model = AutoModelForCausalLM.from_config(config=config, 
                                                 torch_dtype=torch.float16, trust_remote_code=True)

real_quantize_model_weight(model, w_bit=w_bit, q_config=q_config, init_only=True)
model.tie_weights()

model = load_checkpoint_and_dispatch(model, load_quant, device_map="balanced")

# Inference
prompt = f'''What is the difference between nuclear fusion and fission?
###Response:'''

input_ids = tokenizer(prompt, return_tensors='pt').input_ids.cuda()
output = model.generate(
    inputs=input_ids, 
    temperature=0.7,
    max_new_tokens=512,
    top_p=0.15,
    top_k=0,
    repetition_penalty=1.1,
    eos_token_id=tokenizer.eos_token_id,
    streamer=streamer)

Evaluation

This evaluation was done using LM-Eval.

Open-LLaMA-13B-Instruct

Task	Version	Metric	Value		Stderr
wikitext	1	word_perplexity	11.6564
		byte_perplexity	1.5829
		bits_per_byte	0.6626

Open-LLaMA-13B-Instruct (4-bit 128-group AWQ)

Task	Version	Metric	Value		Stderr
wikitext	1	word_perplexity	11.9652
		byte_perplexity	1.5907
		bits_per_byte	0.6696

Acknowledgements

If you found OpenLLaMA useful in your research or applications, please cite using the following BibTeX:

@software{openlm2023openllama,
  author = {Geng, Xinyang and Liu, Hao},
  title = {OpenLLaMA: An Open Reproduction of LLaMA},
  month = May,
  year = 2023,
  url = {https://github.com/openlm-research/open_llama}
}

@software{together2023redpajama,
  author = {Together Computer},
  title = {RedPajama-Data: An Open Source Recipe to Reproduce LLaMA training dataset},
  month = April,
  year = 2023,
  url = {https://github.com/togethercomputer/RedPajama-Data}
}

@article{touvron2023llama,
  title={Llama: Open and efficient foundation language models},
  author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and others},
  journal={arXiv preprint arXiv:2302.13971},
  year={2023}
}

The model was quantized with AWQ technique. If you find AWQ useful or relevant to your research, please kindly cite the paper:

@article{lin2023awq,
  title={AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration},
  author={Lin, Ji and Tang, Jiaming and Tang, Haotian and Yang, Shang and Dang, Xingyu and Han, Song},
  journal={arXiv},
  year={2023}
}