README.md

metadata

language:
  - en
datasets:
  - liuhaotian/LLaVA-Instruct-150K

Usage

import requests
from PIL import Image

import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration

model_id = "nota-ai/phiva-4b-hf"

prompt = "USER: <image>\nWhat are these?\nASSISTANT:"
image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"

model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True, 
    attn_implementation="eager"
).to(0)

processor = AutoProcessor.from_pretrained(model_id)


raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs = processor(prompt, raw_image, return_tensors='pt').to(0, torch.float16)

output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
print(processor.decode(output[0][inputs['input_ids'].shape[-1]:], skip_special_tokens=True))