---
license: mit
---

# Compressed LLM Model Zone

The models are prepared by [Visual Informatics Group @ University of Texas at Austin (VITA-group)](https://vita-group.github.io/). Credits to Ajay Jaiswal, Zhenyu Zhang, Zhangheng Li, Lu Yin, Shiwei Liu and Junyuan Hong.

License: [MIT License](https://opensource.org/license/mit/)

Setup environment
```shell
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
pip install sentencepiece
```

How to use pruned models
```python
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
```python
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
```python
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])
```


|    | Base Model   | Model Size   | Compression Method                                                                            | Compression Degree                                                                    |
|---:|:-------------|:-------------|:----------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
|  0 | Llama-2      | 7b           | [magnitude_unstructured](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured) | [s0.1](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured/tree/s0.1) |
|  1 | Llama-2      | 7b           | [magnitude_unstructured](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured) | [s0.2](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured/tree/s0.2) |
|  2 | Llama-2      | 7b           | [magnitude_unstructured](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured) | [s0.3](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured/tree/s0.3) |
|  3 | Llama-2      | 7b           | [magnitude_unstructured](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured) | [s0.5](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured/tree/s0.5) |
|  4 | Llama-2      | 7b           | [magnitude_unstructured](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured) | [s0.6](https://huggingface.co/vita-group/llama-2-7b_magnitude_unstructured/tree/s0.6) |
|  5 | Llama-2      | 7b           | [sparsegpt_unstructured](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured) | [s0.1](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured/tree/s0.1) |
|  6 | Llama-2      | 7b           | [sparsegpt_unstructured](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured) | [s0.2](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured/tree/s0.2) |
|  7 | Llama-2      | 7b           | [sparsegpt_unstructured](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured) | [s0.3](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured/tree/s0.3) |
|  8 | Llama-2      | 7b           | [sparsegpt_unstructured](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured) | [s0.5](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured/tree/s0.5) |
|  9 | Llama-2      | 7b           | [sparsegpt_unstructured](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured) | [s0.6](https://huggingface.co/vita-group/llama-2-7b_sparsegpt_unstructured/tree/s0.6) |
| 10 | Llama-2      | 7b           | [wanda_gptq](https://huggingface.co/vita-group/llama-2-7b_wanda_2_4_gptq_4bit_128g)           | 4bit_128g                                                                             |
| 11 | Llama-2      | 7b           | [wanda_unstructured](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured)         | [s0.1](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured/tree/s0.1)     |
| 12 | Llama-2      | 7b           | [wanda_unstructured](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured)         | [s0.2](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured/tree/s0.2)     |
| 13 | Llama-2      | 7b           | [wanda_unstructured](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured)         | [s0.3](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured/tree/s0.3)     |
| 14 | Llama-2      | 7b           | [wanda_unstructured](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured)         | [s0.5](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured/tree/s0.5)     |
| 15 | Llama-2      | 7b           | [wanda_unstructured](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured)         | [s0.6](https://huggingface.co/vita-group/llama-2-7b_wanda_unstructured/tree/s0.6)     |
| 16 | vicuna-v1.3  | 13b          | [gptq](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq)                                | [10bit_128g](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq/tree/10bit_128g)  |
| 17 | vicuna-v1.3  | 13b          | [gptq](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq)                                | [12bit_128g](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq/tree/12bit_128g)  |
| 18 | vicuna-v1.3  | 13b          | [gptq](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq)                                | [14bit_128g](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq/tree/14bit_128g)  |
| 19 | vicuna-v1.3  | 13b          | [gptq](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq)                                | [2bit_128g](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq/tree/2bit_128g)    |
| 20 | vicuna-v1.3  | 13b          | [gptq](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq)                                | [3bit_128g](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq/tree/3bit_128g)    |
| 21 | vicuna-v1.3  | 13b          | [gptq](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq)                                | [4bit_128g](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq/tree/4bit_128g)    |
| 22 | vicuna-v1.3  | 13b          | [gptq](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq)                                | [6bit_128g](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq/tree/6bit_128g)    |
| 23 | vicuna-v1.3  | 13b          | [gptq](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq)                                | [8bit_128g](https://huggingface.co/vita-group/vicuna-13b-v1.3_gptq/tree/8bit_128g)    |
| 24 | vicuna-v1.3  | 7b           | [gptq](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq)                                 | [10bit_128g](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq/tree/10bit_128g)   |
| 25 | vicuna-v1.3  | 7b           | [gptq](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq)                                 | [12bit_128g](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq/tree/12bit_128g)   |
| 26 | vicuna-v1.3  | 7b           | [gptq](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq)                                 | [14bit_128g](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq/tree/14bit_128g)   |
| 27 | vicuna-v1.3  | 7b           | [gptq](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq)                                 | [2bit_128g](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq/tree/2bit_128g)     |
| 28 | vicuna-v1.3  | 7b           | [gptq](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq)                                 | [3bit_128g](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq/tree/3bit_128g)     |
| 29 | vicuna-v1.3  | 7b           | [gptq](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq)                                 | [4bit_128g](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq/tree/4bit_128g)     |
| 30 | vicuna-v1.3  | 7b           | [gptq](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq)                                 | [6bit_128g](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq/tree/6bit_128g)     |
| 31 | vicuna-v1.3  | 7b           | [gptq](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq)                                 | [8bit_128g](https://huggingface.co/vita-group/vicuna-7b-v1.3_gptq/tree/8bit_128g)     |