metadata
{}
How to Get Started with the Model
Use the code below to get started with the model.
import requests
from PIL import Image
from transformers import AutoProcessor, AutoModelForVision2Seq
model = AutoModelForVision2Seq.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
prompt = "<grounding>An image of"
url = "https://huggingface.co/ydshieh/kosmos-2-patch14-224/resolve/main/snowman.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(text=prompt, images=image, return_tensors="pt")
generated_ids = model.generate(
pixel_values=inputs["pixel_values"],
input_ids=inputs["input_ids"][:, :-1],
attention_mask=inputs["attention_mask"][:, :-1],
img_features=None,
img_attn_mask=inputs["img_attn_mask"][:, :-1],
use_cache=True,
max_new_tokens=64,
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
processed_text = processor.post_processor_generation(generated_text, cleanup_and_extract=False)
print(processed_text)
processed_text, entities = processor.post_processor_generation(generated_text)
print(processed_text)
print(entities)