phi4_text_inference.py

import os
import requests
import torch
from PIL import Image
import soundfile
from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig

model_path = 'LLM-Research/Phi-4-multimodal-instruct'

kwargs = {}
kwargs['torch_dtype'] = torch.bfloat16

processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    trust_remote_code=True,
    torch_dtype='auto',
    _attn_implementation='flash_attention_2',
).cuda()

generation_config = GenerationConfig.from_pretrained(model_path, 'generation_config.json')

user_prompt = '<|user|>'
assistant_prompt = '<|assistant|>'
prompt_suffix = '<|end|>'
 
#################################################### text-only ####################################################
prompt = f'{user_prompt}what is the answer for 1+1? Explain it.{prompt_suffix}{assistant_prompt}'
print(f'>>> Prompt\n{prompt}')
inputs = processor(prompt, images=None, return_tensors='pt').to('cuda:0')

generate_ids = model.generate(
    **inputs,
    max_new_tokens=1000,
    generation_config=generation_config,
)
generate_ids = generate_ids[:, inputs['input_ids'].shape[1] :]
response = processor.batch_decode(
    generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]

print(f'>>> Response\n{response}')