Instructions to use theblackcat102/Molmo2-4B-Pairwise-Judge-Direct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theblackcat102/Molmo2-4B-Pairwise-Judge-Direct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="theblackcat102/Molmo2-4B-Pairwise-Judge-Direct", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("theblackcat102/Molmo2-4B-Pairwise-Judge-Direct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use theblackcat102/Molmo2-4B-Pairwise-Judge-Direct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "theblackcat102/Molmo2-4B-Pairwise-Judge-Direct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theblackcat102/Molmo2-4B-Pairwise-Judge-Direct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/theblackcat102/Molmo2-4B-Pairwise-Judge-Direct

SGLang

How to use theblackcat102/Molmo2-4B-Pairwise-Judge-Direct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "theblackcat102/Molmo2-4B-Pairwise-Judge-Direct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theblackcat102/Molmo2-4B-Pairwise-Judge-Direct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "theblackcat102/Molmo2-4B-Pairwise-Judge-Direct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theblackcat102/Molmo2-4B-Pairwise-Judge-Direct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use theblackcat102/Molmo2-4B-Pairwise-Judge-Direct with Docker Model Runner:
```
docker model run hf.co/theblackcat102/Molmo2-4B-Pairwise-Judge-Direct
```

Molmo2-4B Pairwise Judge (Direct, merged)

Standalone BF16 Molmo2-4B for pairwise judging of AI-generated videos. Given a user's preference questionnaire, a generation prompt, and two candidate videos, it emits exactly one token: 1, 2, or Tie.

Merged from LoRA vlm_preference_judge/outputs/molmo2_pairwise_judge/checkpoint-3450 (rank 16, alpha 32, dropout 0.05; targets att_proj, attn_out, ff_proj, ff_out) into the local Molmo2-4B base. Direct-answer format (no rating CoT).

Loading

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "theblackcat102/Molmo2-4B-Pairwise-Judge-Direct"
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    trust_remote_code=True,
    dtype=torch.bfloat16,
    device_map="auto",
)

Use the Molmo2 chat-template with type="video" content. Constrain or post-process the answer to 1, 2, or Tie.

Prompt format

user: judge instructions + questionnaire + Generation task: t2v/i2v. Prompt used to generate both videos: "..." + Video 1: + video + Video 2: + video + Which video would this person prefer: 1, 2, or Tie? Answer with exactly one token. assistant: 1 | 2 | Tie

Downloads last month: 30

Safetensors

Model size

5B params

Tensor type

BF16

F32

Model tree for theblackcat102/Molmo2-4B-Pairwise-Judge-Direct

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

allenai/Molmo2-4B

Finetuned

(14)

this model