Instructions to use xx18/Composition-RL-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xx18/Composition-RL-8B with Transformers:

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

pipe = pipeline("text-generation", model="xx18/Composition-RL-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xx18/Composition-RL-8B")
model = AutoModelForCausalLM.from_pretrained("xx18/Composition-RL-8B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use xx18/Composition-RL-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xx18/Composition-RL-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xx18/Composition-RL-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xx18/Composition-RL-8B

SGLang

How to use xx18/Composition-RL-8B 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 "xx18/Composition-RL-8B" \
    --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": "xx18/Composition-RL-8B",
		"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 "xx18/Composition-RL-8B" \
        --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": "xx18/Composition-RL-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xx18/Composition-RL-8B with Docker Model Runner:
```
docker model run hf.co/xx18/Composition-RL-8B
```

Composition-RL-8B / README.md

xx18

Add model card and metadata (#1)

93dff5e about 1 month ago

preview code

raw

history blame contribute delete

1.86 kB

	---
	library_name: transformers
	pipeline_tag: text-generation
	---

	# Composition-RL-8B

	Composition-RL is a data-efficient Reinforcement Learning with Verifiable Rewards (RLVR) approach that addresses the scarcity of informative training signals by automatically composing multiple verifiable problems into a single, harder compositional prompt.

	This specific checkpoint is the 8B version, initialized from Qwen3-8B-Base and trained on the `MATH-Composition-199K` dataset.

	## Model Description
	As training progresses in RLVR, models often master "easy" prompts, resulting in a pass rate of 1 and reducing effective learning. Composition-RL mitigates this by creating new, complex, yet verifiable questions from existing data, maintaining a high level of difficulty and informative signals throughout training.

	- Developed by: Xin Xu, Clive Bai, Kai Yang, Tianhao Chen, Yangkun Chen, Weijie Liu, Hao Chen, Yang Wang, Saiyong Yang, and Can Yang.
	- Paper: [Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models](https://huggingface.co/papers/2602.12036)
	- Repository: [GitHub - Composition-RL](https://github.com/XinXU-USTC/Composition-RL)
	- Base Model: Qwen3-8B-Base

	## Usage
	For evaluation and data generation instructions, please refer to the official [GitHub repository](https://github.com/XinXU-USTC/Composition-RL).

	## Citation
	If you find this work helpful for your research, please consider citing:

	```bibtex
	@article{xu2026composition-rl,
	title={Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models},
	author={Xu, Xin and Bai, Clive and Yang, Kai Rural and Chen, Tianhao and Chen, Yangkun and Liu, Weijie and Chen, Hao and Wang, Yang and Yang, Saiyong and Yang, Can},
	journal={arXiv preprint arXiv:2602.12036},
	year={2026}
	}
	```