Instructions to use AQuarterMile/WritingBench-Critic-Model-Qwen-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AQuarterMile/WritingBench-Critic-Model-Qwen-7B with Transformers:

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

pipe = pipeline("text-generation", model="AQuarterMile/WritingBench-Critic-Model-Qwen-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("AQuarterMile/WritingBench-Critic-Model-Qwen-7B")
model = AutoModelForMultimodalLM.from_pretrained("AQuarterMile/WritingBench-Critic-Model-Qwen-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AQuarterMile/WritingBench-Critic-Model-Qwen-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AQuarterMile/WritingBench-Critic-Model-Qwen-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AQuarterMile/WritingBench-Critic-Model-Qwen-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AQuarterMile/WritingBench-Critic-Model-Qwen-7B

SGLang

How to use AQuarterMile/WritingBench-Critic-Model-Qwen-7B 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 "AQuarterMile/WritingBench-Critic-Model-Qwen-7B" \
    --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": "AQuarterMile/WritingBench-Critic-Model-Qwen-7B",
		"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 "AQuarterMile/WritingBench-Critic-Model-Qwen-7B" \
        --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": "AQuarterMile/WritingBench-Critic-Model-Qwen-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AQuarterMile/WritingBench-Critic-Model-Qwen-7B with Docker Model Runner:
```
docker model run hf.co/AQuarterMile/WritingBench-Critic-Model-Qwen-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

WritingBench-Critic-Model-Qwen-7B

📃 [Paper] • 🚀 [Github Repo] • 📏 [Critic Model] • ✍️ [Writer-7B] [Writer-32B]

This model is fine-tuned from Qwen/Qwen2.5-7B-Instruct on a 50K SFT dataset for writing evaluation tasks.

For each criterion, the evaluator independently assigns a score on a 10-point scale to a response, providing both a score and a justification.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 7e-06
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Framework versions

Transformers 4.46.1
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

📝 Citation

@misc{wu2025writingbench,
      title={WritingBench: A Comprehensive Benchmark for Generative Writing}, 
      author={Yuning Wu and Jiahao Mei and Ming Yan and Chenliang Li and Shaopeng Lai and Yuran Ren and Zijia Wang and Ji Zhang and Mengyue Wu and Qin Jin and Fei Huang},
      year={2025},
      url={https://arxiv.org/abs/2503.05244}, 
}