Instructions to use ZJUSCL/SeekJudge-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZJUSCL/SeekJudge-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ZJUSCL/SeekJudge-9B")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ZJUSCL/SeekJudge-9B")
model = AutoModelForMultimodalLM.from_pretrained("ZJUSCL/SeekJudge-9B", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ZJUSCL/SeekJudge-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZJUSCL/SeekJudge-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZJUSCL/SeekJudge-9B",
		"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/ZJUSCL/SeekJudge-9B

SGLang

How to use ZJUSCL/SeekJudge-9B 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 "ZJUSCL/SeekJudge-9B" \
    --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": "ZJUSCL/SeekJudge-9B",
		"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 "ZJUSCL/SeekJudge-9B" \
        --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": "ZJUSCL/SeekJudge-9B",
		"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 ZJUSCL/SeekJudge-9B with Docker Model Runner:
```
docker model run hf.co/ZJUSCL/SeekJudge-9B
```

SeekJudge-9B

SeekJudge-9B is the trained judge model of SeekJudge, a reward framework for reinforcement learning in computer-use agents. Given a task goal and a recorded trajectory (screenshots plus actions), it decides whether the goal was achieved and emits per-step quality labels in the <answer_overall> / <answer_step> format.

The model is a judge, not an agent. It does not produce GUI actions.

Code and resources


Code	github.com/ZJUSCL/SeekJudge
Benchmark	ZJUSCL/CUAStepBench
Leaderboard	github.com/ZJUSCL/CUAStepBench

The repository README covers serving the model, running it as a batch judge over trajectory datasets, and hosting it as an HTTP reward server for online RL training. This checkpoint requires seek.trained: True in the SeekJudge configuration, which selects the parser for the trained output format.

Model size


Total parameters	9.41 B (9,409.81 M)
Trainable during SFT	8.95 B (8,953.80 M, 95.15 %)
Frozen	vision encoder and aligner (456 M)
Precision	bfloat16
Checkpoint on disk	18.8 GB (17.5 GiB), 4 safetensors shards
Context length	262,144 (trained at 32,000)

Architecture follows the Qwen3.5 multimodal stack: 32 language layers mixing linear attention with full attention every 4th layer, hidden size 4096, 16 attention heads with 4 KV heads, plus a 27-layer SigLIP-style vision tower (hidden size 1152, patch size 16) projecting to 4096.

Training cost


Hardware	8 x NVIDIA RTX A6000 (48 GB), single node
Wall-clock time	41.4 h (149,071 s)
GPU-hours	331 A6000-hours
Throughput	52.5 s per optimizer step, 0.61 samples/s
Peak memory	25.4 GiB per GPU

Peak memory stays low because DeepSpeed ZeRO-3 offloads both optimizer states and parameters to CPU, which trades memory for the step time above.

Training configuration

Full-parameter supervised fine-tuning of the language model on top of Qwen/Qwen3.5-9B, with the vision encoder and the aligner frozen. Run with ms-swift 4.1.0.dev0 on transformers 5.3.0.

Parameter	Value
Tuning type	full (`freeze_vit=True`, `freeze_aligner=True`, `freeze_llm=False`)
Epochs	2
Optimizer steps	2,840 (1,420 per epoch)
Global batch size	32 sequences (1 per device x 4 accumulation x 8 GPUs)
Learning rate	1e-5, cosine schedule, warmup ratio 0.05
Optimizer	`adamw_torch_fused`, betas (0.9, 0.95), weight decay 0.01
Gradient clipping	1.0
Max sequence length	32,000
Precision	bfloat16
Attention	FlashAttention
Memory	DeepSpeed ZeRO-3, CPU offload of optimizer and parameters, gradient checkpointing
Packing / padding-free	off
Template	`qwen3_5`, non-thinking prefix enabled
Seed	42

Data volume


Samples	45,416
Tokens per sample	3,335 mean, 2,971 std, 597 min, 31,769 max
Tokens per epoch	approximately 151 M
Tokens seen	approximately 303 M over 2 epochs

The mixture combines trajectory-level judging targets, per-step analysis targets, and tool-query targets, so that one model serves every stage of the SeekJudge pipeline.

Final training metrics

Training loss 0.246 and token accuracy 0.918 at step 2,840; mean loss over the whole run 0.380.

License

Apache-2.0, inherited from the Qwen3.5-9B base model. The SeekJudge codebase is MIT-licensed.

Downloads last month: 15

Safetensors

Model size

1.47M params

Tensor type

BF16

Model tree for ZJUSCL/SeekJudge-9B

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(563)

this model