MetaphorStar-3B

from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
from qwen_vl_utils import process_vision_info
import torch

model_id = "MING-ZCH/MetaphorStar-3B"

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained(model_id)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "path/to/metaphor_image.jpg"},
            {"type": "text", "text": "True-false questions: The wilted plant in the office implies a stressful working environment.

First, describe the image, then analyze the image implication, and finally reason to get the answer. Output the thinking process in <think></think> and the final correct answer in <answer></answer> tags."}
        ]
    }
]

# Inference setup (standard Qwen2.5-VL generation)
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[...], padding=True, return_tensors="pt").to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=2048)
output_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(output_text)