Add model card and loading example

README.md

@@ -1,3 +1,76 @@
 ---
-license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+base_model: Qwen/Qwen3-VL-8B-Instruct
+tags:
+  - qwen3-vl
+  - vision-language
+  - reward-model
+  - image-ranking
 ---
+
+# VerifierReward Qwen3-VL 8B
+
+This is a Qwen3-VL-8B-Instruct checkpoint fine-tuned as a yes/no image-text
+alignment verifier. It was trained with mixed pairwise preference data and can
+be loaded directly with Hugging Face Transformers.
+
+## Load from Hugging Face
+
+```python
+import torch
+from transformers import AutoProcessor, Qwen3VLForConditionalGeneration
+
+model_id = "JanHutter/verifierreward"
+
+processor = AutoProcessor.from_pretrained(model_id)
+model = Qwen3VLForConditionalGeneration.from_pretrained(
+    model_id,
+    dtype=torch.bfloat16,
+    device_map="auto",
+)
+```
+
+The repository ID is the Hugging Face-native identifier corresponding to
+<https://huggingface.co/JanHutter/verifierreward>.
+
+## Score image-prompt alignment
+
+The model was trained to answer `yes` or `no`. The scalar reward used during
+evaluation is the full-vocabulary probability of the next token being `yes`.
+
+```python
+import torch
+
+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": "https://example.com/image.jpg"},
+        {"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_id = processor.tokenizer.encode("yes", add_special_tokens=False)[0]
+reward = torch.softmax(logits, dim=-1)[:, yes_id]
+print(reward.item())
+```
+
+## Checkpoint
+
+This repository contains the final checkpoint from training step 8,796. Only
+inference artifacts are published; optimizer, scheduler, RNG, trainer, and FSDP
+resume-state files are intentionally excluded.