English
Edit model card

Model Details

This model is an int4 model recipe with group_size 128 of microsoft/Phi-3-mini-128k-instruct generated by intel/auto-round. Inference of this model is compatible with AutoGPTQ's Kernel.

Quantize the model

Here is the sample command to reproduce the model

pip install auto-round
auto-round
--model  microsoft/Phi-3-mini-128k-instruct \
--device 0 \
--group_size 128 \
--bits 4 \
--iters 200 \
--nsamples 512 \
--seqlen 4096 \
--minmax_lr 0.01 \
--format 'auto_gptq' \
--gradient_accumulate_steps 2 \
--batch_size 4 \
--output_dir "./tmp_autoround" \

How to use

INT4 Inference with IPEX on Intel CPU

Install the latest Intel Extension for Pytorch and Intel Neural Compressor

pip install torch --index-url https://download.pytorch.org/whl/cpu
pip install intel_extension_for_pytorch
pip install neural_compressor_pt 
from transformers import AutoTokenizer
from neural_compressor.transformers import AutoModelForCausalLM

## note: use quantized model directory name below 
model_name_or_path="./tmp_autoround/<model directory name>"
q_model = AutoModelForCausalLM.from_pretrained(model_name_or_path)

prompt = "Once upon a time, a little girl"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
print(tokenizer.decode(q_model.generate(**tokenizer(prompt, return_tensors="pt").to(q_model.device),max_new_tokens=50)[0]))
##Once upon a time, a little girl named Lily was playing in her backyard. She loved to explore and discover new things. One day, she stumbled upon a beautiful garden filled with colorful flowers andugh the garden, she noticed a

INT4 Inference on Intel Gaudi Accelerator

docker image with Gaudi Software Stack is recommended. More details can be found in Gaudi Guide.

import habana_frameworks.torch.core as htcore
from neural_compressor.torch.quantization import load
from transformers import  AutoTokenizer, AutoModelForCausalLM

## note: use quantized model directory name below
model_name_or_path="./tmp_autoround/<model directory name>"

model = load(
    model_name_or_path=model_name_or_path,
    format="huggingface",
    device="hpu"
)

prompt = "Once upon a time, a little girl"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
print(tokenizer.decode(model.generate(**tokenizer(prompt, return_tensors="pt").to("hpu"),max_new_tokens=50)[0]))

Accuracy Result

Metric FP16 INT4
Avg. 0.6364 0.6300
mmlu 0.6215 0.6237
lambada_openai 0.6656 0.6433
hellaswag 0.5979 0.5859
winogrande 0.7324 0.7230
piqa 0.7884 0.7846
truthfulqa_mc1 0.3574 0.3562
openbookqa 0.3900 0.3800
boolq 0.8572 0.8489
arc_easy 0.8119 0.8199
arc_challenge 0.5418 0.5350

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

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

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train Intel/Phi-3-mini-128k-instruct-int4-inc-recipe