salamandra-7b-vision

from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration
import torch
from PIL import Image

path = "BSC-LT/salamandra-7b-vision"

processor = AutoProcessor.from_pretrained(path) 
model = LlavaOnevisionForConditionalGeneration.from_pretrained(path, torch_dtype=torch.float16, low_cpu_mem_usage=True).to("cuda")

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"

image = Image.open(url)

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Describe la imagen con el mayor detalle posible."},
        ],
    },
]
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt").to("cuda", torch.float16)

output = model.generate(**inputs,
    temperature=0.7,
    max_new_tokens=1024)

output_tokens = output[0].tolist()

print(processor.decode(output[0], skip_special_tokens=True))