README.md · PerRing/llava-v1.6-vicuna-13b-hf at fb5a35225ded55dcb7ec1cad5e3c8cc7edf44d18

import requests
from PIL import Image
import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration

model_id = "PerRing/llava-v1.6-vicuna-13b-hf"
model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True, 
).to(0)
processor = AutoProcessor.from_pretrained(model_id)

Q='explain about this image.'
prompt = f"""A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions. USER: <image>
{Q} ASSISTANT:
"""
image_file = "https://images.pexels.com/photos/757889/pexels-photo-757889.jpeg?auto=compress&cs=tinysrgb&w=1260&h=750&dpr=2"

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_length=256, temperature=0.4, do_sample=True)
print(processor.decode(output[0], skip_special_tokens=True))

PerRing
/

llava-v1.6-vicuna-13b-hf

result