R1-Track-GRPO-wo-Think-5k

Demo

from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info


model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "WangBiao/R1-Track-GRPO-wo-Think", torch_dtype="auto", device_map="auto"
)


min_pixels = 336*336
max_pixels = 336*336
processor = AutoProcessor.from_pretrained("WangBiao/R1-Track-GRPO-wo-Think", min_pixels=min_pixels, max_pixels=max_pixels)


messages = [
    {
        "role": "system",
        "content": "You are a helpful assistant.",
    },
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "image_1.jpg",
            },
            {
                "type": "image",
                "image": "image_2.jpg",
            },
            {"type": "text", "text": "Please identify the target specified by the bounding box [241,66,329,154] in the first image and locate it in the second image. Return the coordinates in [x_min,y_min,x_max,y_max] format."},
        ],
    }
]



text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to(model.device)

generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)