INC4AI/neural-chat-7b-v3-1-int4-inc

Model Details: Neural-Chat-7b-v3-1-int4-inc

This model is an int4 model with group_size 128 of Intel/neural-chat-7b-v3-1 generated by intel/auto-round.

How To Use

Reproduce the model

Here is the sample command to reproduce the model

git clone https://github.com/intel/auto-round
cd auto-round/examples/language-modeling
pip install -r requirements.txt
python3 main.py \
--model_name  Intel/neural-chat-7b-v3-1 \
--device 0 \
--group_size 128 \
--bits 4 \
--iters 1000 \
--enable_minmax_tuning \
--disable_quanted_input \
--minmax_lr 0.002 \
--deployment_device 'gpu' \
--scale_dtype 'fp32' \
--eval_bs 32 \
--output_dir "./tmp_autoround" \
--amp 

Use the model

INT4 Inference with ITREX on CPU

Install the latest intel-extension-for-transformers

from intel_extension_for_transformers.transformers import AutoModelForCausalLM
from transformers import AutoTokenizer
quantized_model_dir = "Intel/neural-chat-7b-v3-1-int4-inc"
model = AutoModelForCausalLM.from_pretrained(quantized_model_dir,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             use_neural_speed=False,
                                             )
tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir, use_fast=True)
print(tokenizer.decode(model.generate(**tokenizer("There is a girl who likes adventure,", return_tensors="pt").to(model.device),max_new_tokens=50)[0]))
"""
 <s> There is a girl who likes adventure, who loves to travel, who is always looking for new experiences. She is a dreamer, a doer, a thinker, a believer. She is a girl who is not afraid to take risks, to make mistakes, to learn from
"""

INT4 Inference with AutoGPTQ

Install AutoGPTQ from source first

from transformers import AutoModelForCausalLM, AutoTokenizer
quantized_model_dir = "Intel/neural-chat-7b-v3-1-int4-inc"
model = AutoModelForCausalLM.from_pretrained(quantized_model_dir,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             )
tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir, use_fast=True)
print(tokenizer.decode(model.generate(**tokenizer("There is a girl who likes adventure,", return_tensors="pt").to(model.device),max_new_tokens=50)[0]))

Evaluate the model

Install lm-eval-harness from source, we used the git id f3b7917091afba325af3980a35d8a6dcba03dc3f

lm_eval  --model hf --model_args pretrained="Intel/neural-chat-7b-v3-1-int4-inc",autogptq=True,gptq_use_triton=True --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,rte,arc_easy,arc_challenge,mmlu  --batch_size 128

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}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

arxiv github