JanHutter/verifierreward

import torch
from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

model_id = "JanHutter/verifierreward"

processor = AutoProcessor.from_pretrained(
    model_id, max_pixels=512 * 512, fix_mistral_regex=False,
)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
    attn_implementation="sdpa",
).eval()

import torch
from PIL import Image

image = Image.open("image.jpg").convert("RGB")

instruction = """You are an AI assistant specializing in image analysis and ranking. Your task is to analyze and compare image based on how well they match the given prompt.
The given prompt is:{prompt}. Please consider the prompt and the image to make a decision and response directly with 'yes' or 'no'."""

messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": instruction.format(prompt="a red car in snow")},
    ],
}]

inputs = processor.apply_chat_template(
    [messages],
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.inference_mode():
    logits = model(**inputs, use_cache=False).logits[:, -1, :].float()

yes_ids = processor.tokenizer.encode("yes", add_special_tokens=False)
assert len(yes_ids) == 1
yes_id = yes_ids[0]
reward = torch.softmax(logits, dim=-1)[:, yes_id]
print(reward.item())