meta-llama

/

Llama-3.2-11B-Vision-Instruct

like 743

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

model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"

model = MllamaForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_id)

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
image = Image.open(requests.get(url, stream=True).raw)

messages = [
    {"role": "user", "content": [
        {"type": "image"},
        {"type": "text", "text": "If I had to write a haiku for this one, it would be: "}
    ]}
]
input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(image, input_text, return_tensors="pt").to(model.device)


print(inputs.input_ids)
print(processor.tokenizer.decode(inputs.input_ids[0, :6]))
output = model.generate(**inputs, max_new_tokens=30)
print(processor.decode(output[0]))

tensor([[128000, 128000, 128006,    882, 128007,    271, 128256,   2746,    358,
           1047,    311,   3350,    264,   6520,  39342,    369,    420,    832,
             11,    433,   1053,    387,     25,    220, 128009, 128006,  78191,
         128007,    271]], device='cuda:0')
'<|begin_of_text|><|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n'

128000 is added twice when running the given example, does it impact the quality of the model?