Intel/phi-2-int4-inc

Model Details

This model is an int4 model with group_size128 and sym quantization of microsoft/phi-2 generated by intel/auto-round. If you need AutoGPTQ format, please load the model with revision 5973e3a

How To Use

INT4 Inference

##pip install auto-round
from transformers import AutoModelForCausalLM, AutoTokenizer
quantized_model_dir = "Intel/phi-2-int4-inc"
tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)
model = AutoModelForCausalLM.from_pretrained(quantized_model_dir,
                                             device_map="auto",
                                             trust_remote_code=True,
                                             ## revision="5973e3a" ##AutoGPTQ format
                                            )
text = "There is a girl who likes adventure,"
inputs = tokenizer(text, return_tensors="pt", return_attention_mask=False).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=50)
text = tokenizer.batch_decode(outputs)[0]
print(text)
"""
There is a girl who likes adventure,
She loves to explore and to venture.
She travels to faraway lands,
And meets people from different lands.
She learns new languages and cultures,
And makes friends with all kinds of people.
She is curious and brave and
"""

Intel Gaudi-2 INT4 Inference

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

import habana_frameworks.torch.core as htcore
import habana_frameworks.torch.hpu as hthpu

from auto_round import AutoRoundConfig
from transformers import AutoModelForCausalLM,AutoTokenizer

quantized_model_dir = "Intel/phi-2-int4-inc"
tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)
model = AutoModelForCausalLM.from_pretrained(quantized_model_dir).to('hpu').to(bfloat16)
text = "下面我来介绍一下阿里巴巴公司,"
inputs = tokenizer(text, return_tensors="pt").to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0]))

Evaluate the model

pip install lm-eval==0.4.4

auto-round --eval --model Intel/phi-2-int4-inc --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu --batch_size 16

Metric	FP16	INT4
Avg.	0.6131	0.6087
mmlu	0.5334	0.5417
lambada_openai	0.6243	0.6088
hellaswag	0.5581	0.5520
winogrande	0.7522	0.7577
piqa	0.7867	0.7911
truthfulqa_mc1	0.3097	0.2962
openbookqa	0.4040	0.3900
boolq	0.8346	0.8333
arc_easy	0.8001	0.7980
arc_challenge	0.5282	0.5179

Generate the model

Here is the sample command to generate the model

auto-round \
--model  microsoft/phi-2 \
--device 0 \
--group_size 128 \
--bits 4 \
--iters 1000 \
--nsamples 512 \
--format "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.