lvkaokao's picture
Update README.md
77439b2 verified
|
raw
history blame
3.63 kB
metadata
license: apache-2.0
tags:
  - LLMs
  - mistral
  - Intel
language:
  - en

Model Details: Neural-Chat-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
pip install -r requirements.txt
cd 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 \
--minmax_lr 0.0002 \
--deployment_device 'gpu' \
--scale_dtype 'fp32' \
--eval_bs 32 \
--output_dir "./tmp_autoround" \
--amp 

Use the model

INT4 Inference with AutoGPTQ

Install AutoGPTQ from source first

from transformers import AutoModelForCausalLM, AutoTokenizer
quantized_model_dir = "Intel/neural-chat-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-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  --batch_size 128
Metric FP16 INT4
Avg. 0.6769 0.6721
mmlu 0.5919 0.5862
lambada_openai 0.7394 0.7337
hellaswag 0.6323 0.6272
winogrande 0.7687 0.7577
piqa 0.8161 0.8150
truthfulqa_mc1 0.4431 0.4394
openbookqa 0.3760 0.3700
boolq 0.8783 0.8743
rte 0.7690 0.7726
arc_easy 0.8413 0.8384
arc_challenge 0.5896 0.5785

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.