Instructions to use zkjzou/SWE-Verifier-Score-Only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zkjzou/SWE-Verifier-Score-Only with Transformers:

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

pipe = pipeline("text-generation", model="zkjzou/SWE-Verifier-Score-Only")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("zkjzou/SWE-Verifier-Score-Only")
model = AutoModelForMultimodalLM.from_pretrained("zkjzou/SWE-Verifier-Score-Only", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zkjzou/SWE-Verifier-Score-Only with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zkjzou/SWE-Verifier-Score-Only"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zkjzou/SWE-Verifier-Score-Only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zkjzou/SWE-Verifier-Score-Only

SGLang

How to use zkjzou/SWE-Verifier-Score-Only 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 "zkjzou/SWE-Verifier-Score-Only" \
    --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": "zkjzou/SWE-Verifier-Score-Only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "zkjzou/SWE-Verifier-Score-Only" \
        --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": "zkjzou/SWE-Verifier-Score-Only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zkjzou/SWE-Verifier-Score-Only with Docker Model Runner:
```
docker model run hf.co/zkjzou/SWE-Verifier-Score-Only
```

SWE-Verifier (Score Only)

The SWE-Verifier (Score Only) model used in the paper, based on Qwen3.5-4B.

Scores a proposed coding-agent action from the task and observed history, producing reasoning and a scalar score.

Model path: zkjzou/SWE-Verifier-Score-Only.

Usage

hf download zkjzou/SWE-Verifier-Score-Only

Use the bundled prompts and tokenizer with the SWE-Verifier runtime.

Training data: score_only in zkjzou/swe-verifier-training.

License

Apache 2.0. Base-model attribution is retained in the repository's license and notice files.

Downloads last month: -

Safetensors

Model size

5B params

Tensor type

F32

BF16

Model tree for zkjzou/SWE-Verifier-Score-Only

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(1168)

this model

Dataset used to train zkjzou/SWE-Verifier-Score-Only

Collection including zkjzou/SWE-Verifier-Score-Only

SWE-Verifier

Collection

5 items • Updated about 14 hours ago

Paper for zkjzou/SWE-Verifier-Score-Only

SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents

Paper • 2610.30284 • Published 9 days ago • 5