Step3-VL-10B-Base

from transformers import AutoProcessor, AutoModelForCausalLM
from PIL import Image
import requests

key_mapping = {
    "^vision_model": "model.vision_model",
    r"^model(?!\.(language_model|vision_model))": "model.language_model",
    "vit_large_projector": "model.vit_large_projector",
}

model_path = "stepfun-ai/Step3-VL-10B-Base"

processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
prompt = "<im_patch> What's the content of the image?"
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"
image = Image.open(requests.get(url, stream=True).raw)

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    trust_remote_code=True,
    device_map="auto",
    torch_dtype="auto",
    key_mapping=key_mapping).eval()

inputs = processor(images=image, text=prompt, return_tensors="pt").to(model.device)

generate_ids = model.generate(**inputs, max_new_tokens=1024, do_sample=False)
decoded = processor.decode(generate_ids[0, inputs["input_ids"].shape[-1] :], skip_special_tokens=True)

print(decoded)