Phi-4-mini-OV-INT4

Phi-4-mini OpenVINO INT4 Model

<b><span style="text-decoration:underline">Note: This is unoffical version,just for test and dev.</span></b>

This is the OpenVINO format INT 4 quantized version of the Microsoft Phi-4-mini . You can use it with the Intel OpenVINO SDK.

optimum-cli export openvino --model .\Your Phi-4-mini path --task text-generation-with-past --weight-format int4 --sym --group-size 128 --ratio 0.6 --sym  --trust-remote-code .\Your output Phi-4 OpenVINO location

Sample Code

from transformers import AutoConfig, AutoTokenizer
from optimum.intel.openvino import OVModelForCausalLM

model_dir = 'Your Phi-4-mini OpenVINO Path'

ov_config = {"PERFORMANCE_HINT": "LATENCY", "NUM_STREAMS": "1", "CACHE_DIR": ""}

ov_model = OVModelForCausalLM.from_pretrained(
    model_dir,
    device='GPU',
    ov_config=ov_config,
    config=AutoConfig.from_pretrained(model_dir, trust_remote_code=True),
    trust_remote_code=True,
)

tok = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)

tokenizer_kwargs =  {"add_special_tokens": False}

prompt = "<|user|>\nI have $20,000 in my savings account, where I receive a 4% profit per year and payments twice a year. Can you please tell me how long it will take for me to become a millionaire? Also, can you please explain the math step by step as if you were explaining it to an uneducated person?\n<|end|><|assistant|>\n"

input_tokens = tok(prompt, return_tensors="pt", **tokenizer_kwargs)

answer = ov_model.generate(**input_tokens, max_new_tokens=1024)

tok.batch_decode(answer, skip_special_tokens=True)[0]