![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
![Visual Informatics Group @ University of Texas at Austin's profile picture](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
Visual Informatics Group @ University of Texas at Austin
AI & ML interests
Machine learning
Visual Informatics Group @ University of Texas at Austin (VITA-Group)
At VITA group, we have unusually broad, and forever-evolving research interests spanning from the theory to the application aspects of machine learning (ML). Our current "research keywords" include, but are not limited to: sparsity (from classical optimization to modern neural networks); efficient training, inference or transfer (especially, of large foundation models); robustness and trustworthiness; learning to optimize (L2O); generative AI; graph learning, and more.
Compressed LLM Model Zone
NOTE: All compressed LLMs are moved to a new repo at compressed-llm.
The models are prepared by Visual Informatics Group @ University of Texas at Austin (VITA-group). Credits to Ajay Jaiswal, Zhenyu Zhang, Zhangheng Li, Lu Yin, Shiwei Liu and Junyuan Hong.
License: MIT License
Setup environment
pip install torch==2.0.0+cu117 torchvision==0.15.1+cu117 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cu117
pip install transformers==4.31.0
pip install accelerate
pip install auto-gptq # for gptq
How to use pruned models
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
base_model = 'llama-2-7b'
comp_method = 'magnitude_unstructured'
comp_degree = 0.2
model_path = f'vita-group/{base_model}_{comp_method}'
model = AutoModelForCausalLM.from_pretrained(
model_path,
revision=f's{comp_degree}',
torch_dtype=torch.float16,
low_cpu_mem_usage=True,
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained('meta-llama/Llama-2-7b-hf')
input_ids = tokenizer('Hello! I am a VITA-compressed-LLM chatbot!', return_tensors='pt').input_ids.cuda()
outputs = model.generate(input_ids, max_new_tokens=128)
print(tokenizer.decode(outputs[0]))
How to use wanda+gptq models
from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM
model_path = 'vita-group/llama-2-7b_wanda_2_4_gptq_4bit_128g'
tokenizer_path = 'meta-llama/Llama-2-7b-hf'
model = AutoGPTQForCausalLM.from_quantized(
model_path,
# inject_fused_attention=False, # or
disable_exllama=True,
device_map='auto',
)
tokenizer = AutoTokenizer.from_pretrained(tokenizer_path, trust_remote_code=True)
input_ids = tokenizer('Hello! I am a VITA-compressed-LLM chatbot!', return_tensors='pt').input_ids.to('cuda')
outputs = model.generate(input_ids=input_ids, max_length=128)
tokenizer.decode(outputs[0])
How to use gptq models
from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM
# model_path = 'vita-group/llama-2-7b_wanda_2_4_gptq_4bit_128g'
# tokenizer_path = 'meta-llama/Llama-2-7b-hf'
model_path = 'vita-group/vicuna-7b-v1.3_gptq'
tokenizer_path = 'lmsys/vicuna-7b-v1.3'
model = AutoGPTQForCausalLM.from_quantized(
model_path,
# inject_fused_attention=False, # or
disable_exllama=True,
device_map='auto',
revision='2bit_128g',
)
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(tokenizer_path, trust_remote_code=True)
input_ids = tokenizer('Hello! I am a VITA-compressed-LLM chatbot!', return_tensors='pt').input_ids.to('cuda')
outputs = model.generate(input_ids=input_ids, max_length=128)
tokenizer.decode(outputs[0])
Citations
If you are using models in this hub, please consider citing our papers.
@article{jaiswal2023emergence,
title={The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter},
author={Jaiswal, Ajay and Liu, Shiwei and Chen, Tianlong and Wang, Zhangyang},
journal={arXiv},
year={2023}
}
@article{jaiswal2023compressing,
title={Compressing LLMs: The Truth is Rarely Pure and Never Simple},
author={Ajay Jaiswal and Zhe Gan and Xianzhi Du and Bowen Zhang and Zhangyang Wang and Yinfei Yang},
year={2023},
journal={arXiv},
}
For any question, please contact Junyuan Hong.
models
12
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
vita-group/welore-rank60-compressed
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
vita-group/welore-rank50-compressed
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
vita-group/welore-rank40-compressed
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
vita-group/welore-rank30-compressed
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
vita-group/welore-rank20-compressed
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
vita-group/welore-rank10-compressed
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
vita-group/vicuna-7b-v1.3_gptq
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)
vita-group/llama-2-7b_wanda_unstructured
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400cf982b67d27affce2d89/6-Y5FtffpEueYTPLDugMU.png)