Intel/Qwen2.5-7B-Instruct-int4-inc

Model Details

This model is an int4 model with group_size 128 of Qwen/Qwen2.5-7B-Instruct generated by intel/auto-round, auto-round is needed to run this model

How To Use

INT4 Inference

##git clone https://github.com/intel/auto-round.git
##cd auto-round && pip install -vvv --no-build-isolation -e .
from auto_round import AutoHfQuantizer ##must import
import torch
from transformers import AutoModelForCausalLM,AutoTokenizer
quantized_model_dir = "Intel/Qwen2.5-7B-Instruct-int4-inc"
tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)

model = AutoModelForCausalLM.from_pretrained(
    quantized_model_dir,
    torch_dtype='auto',
    device_map="auto",
)

##import habana_frameworks.torch.core as htcore ## uncommnet it for HPU
##import habana_frameworks.torch.hpu as hthpu ## uncommnet it for HPU
##model = model.to(torch.bfloat16).to("hpu") ## uncommnet it for HPU

prompt = "There is a girl who likes adventure,"
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=50,  ##change this to align with the official usage
    do_sample=False  ##change this to align with the official usage
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

##prompt = "There is a girl who likes adventure,"
##That sounds exciting! What kind of adventures does she enjoy? Is there something specific you'd like to plan or discuss related to her love for adventure?

##prompt = "Which one is bigger, 9.11 or 9.8"
##The number 9.8 is bigger than 9.11. When comparing decimal numbers, you can look at each digit from left to right. Both numbers start with 9, but the second digit after the decimal point is 1 in


##prompt = "Once upon a time,"
##Once upon a time, in a land filled with wonder and magic, there lived a young girl named Elara. She had bright eyes that sparkled like the stars on a clear night and hair as golden as the sun-kissed fields of wheat

##prompt = "请介绍一下阿里巴巴公司"
##阿里巴巴集团是一家总部位于中国杭州的全球领先的电子商务和科技公司，成立于1999年。阿里巴巴集团旗下的业务涵盖了电子商务、零售、金融、物流、云计算等多个领域。
##阿里巴巴集团的主要业务包括：
##1. 电子商务：

Evaluate the model

pip3 install lm-eval==0.4.4

git clone https://github.com/intel/auto-round
cd auto-round
python -m auto_round --model "Intel/Qwen2.5-7B-Instruct-int4-inc" --eval --eval_bs 16  --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu,gsm8k,cmmlu,ceval-valid

Metric	BF16	INT4
Avg	0.6872	0.6863
mmlu	0.7178	0.7131
cmmlu	0.8018	0.7899
ceval-valid	0.7949	0.7741
lambada_openai	0.6978	0.6936
hellaswag	0.6203	0.6152
winogrande	0.7080	0.7056
piqa	0.7943	0.7851
truthfulqa_mc1	0.4786	0.4798
openbookqa	0.3480	0.3560
boolq	0.8636	0.8590
arc_easy	0.8182	0.8215
arc_challenge	0.5273	0.5307
gsm8k 5 shots	0.7635	0.7983

Reproduce the model

Here is the sample command to reproduce the model. We observed a larger accuracy drop in Chinese tasks and recommend using a high-quality Chinese dataset for calibration. However, we did not achieve better accuracy with some public datasets.

git clone https://github.com/intel/auto-round
cd auto-round
python -m auto_round \
--model_name  Qwen/Qwen2.5-7B-Instruct \
--device 0 \
--group_size 128 \
--nsamples 512 \
--bits 4 \
--iter 1000 \
--disable_eval \
--model_dtype "float16" \
--deployment_device 'auto_round' \
--output_dir "./tmp_autoround" 

Ethical Considerations and Limitations

The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Therefore, before deploying any applications of the model, developers should perform safety testing.

Caveats and Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Here are a couple of useful links to learn more about Intel's AI software:

• Intel Neural Compressor link
• Intel Extension for Transformers link

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

Cite

@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

arxiv github