Instructions to use THU-KEG/LongWriter-Zero-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use THU-KEG/LongWriter-Zero-32B with Transformers:

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

pipe = pipeline("text-generation", model="THU-KEG/LongWriter-Zero-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("THU-KEG/LongWriter-Zero-32B")
model = AutoModelForCausalLM.from_pretrained("THU-KEG/LongWriter-Zero-32B")
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 THU-KEG/LongWriter-Zero-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "THU-KEG/LongWriter-Zero-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "THU-KEG/LongWriter-Zero-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/THU-KEG/LongWriter-Zero-32B

SGLang

How to use THU-KEG/LongWriter-Zero-32B 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 "THU-KEG/LongWriter-Zero-32B" \
    --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": "THU-KEG/LongWriter-Zero-32B",
		"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 "THU-KEG/LongWriter-Zero-32B" \
        --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": "THU-KEG/LongWriter-Zero-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use THU-KEG/LongWriter-Zero-32B with Docker Model Runner:
```
docker model run hf.co/THU-KEG/LongWriter-Zero-32B
```

Add link to Github repository

by nielsr HF Staff - opened Jun 29, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+11

-10

Files changed (1) hide show

README.md +11 -10

README.md CHANGED Viewed

@@ -1,24 +1,24 @@
 ---
-license: apache-2.0
-datasets:
-- THU-KEG/LongWriter-Zero-RLData
 base_model:
 - Qwen/Qwen2.5-32B
-tags:
-- reinforcement-learning
-- writing
-- Long Context
 language:
 - en
 - zh
-pipeline_tag: text-generation
 library_name: transformers
 ---
 # LongWriter-Zero ✍️ — Mastering Ultra-Long Text Generation via Reinforcement Learning
 <p align="center">
-  🤗 <a href="https://huggingface.co/datasets/THU-KEG/LongWriter-Zero-RLData" target="_blank">HF Dataset</a> • 📃 <a href="https://arxiv.org/abs/2506.18841" target="_blank">Paper</a>
 </p>
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63369da91ba5d5ece24118a4/TLTwlGYvPZ1-99MgiveAA.png)
@@ -178,4 +178,5 @@ for chunk in response.iter_lines():
       archivePrefix={arXiv},
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2506.18841},
-}

 ---
 base_model:
 - Qwen/Qwen2.5-32B
+datasets:
+- THU-KEG/LongWriter-Zero-RLData
 language:
 - en
 - zh
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- reinforcement-learning
+- writing
+- Long Context
 ---
 # LongWriter-Zero ✍️ — Mastering Ultra-Long Text Generation via Reinforcement Learning
 <p align="center">
+  🤗 <a href="https://huggingface.co/datasets/THU-KEG/LongWriter-Zero-RLData" target="_blank">HF Dataset</a> • 📃 <a href="https://arxiv.org/abs/2506.18841" target="_blank">Paper</a> • 💻 <a href="https://github.com/THU-KEG/LongWriter-Zero" target="_blank">Code</a>
 </p>
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63369da91ba5d5ece24118a4/TLTwlGYvPZ1-99MgiveAA.png)
       archivePrefix={arXiv},
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2506.18841},
+}
+```