Instructions to use xx18/Composition-RL-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xx18/Composition-RL-4B with Transformers:

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

pipe = pipeline("text-generation", model="xx18/Composition-RL-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xx18/Composition-RL-4B")
model = AutoModelForCausalLM.from_pretrained("xx18/Composition-RL-4B")
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-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xx18/Composition-RL-4B"
# 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-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xx18/Composition-RL-4B

SGLang

How to use xx18/Composition-RL-4B 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-4B" \
    --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-4B",
		"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-4B" \
        --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-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xx18/Composition-RL-4B with Docker Model Runner:
```
docker model run hf.co/xx18/Composition-RL-4B
```

nielsr HF Staff commited on Apr 23

Commit

839759d

verified ·

1 Parent(s): 1be21c8

Add model card

Browse files

Hi! I'm Niels from the Hugging Face community science team. I noticed this model repository is missing a model card and metadata. I've opened this PR to add a description of the model based on the paper "Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models", include links to the official code and paper, and add appropriate metadata to improve the model's discoverability on the Hub.

Files changed (1) hide show

README.md +41 -0

README.md ADDED Viewed

	@@ -0,0 +1,41 @@

+---
+library_name: transformers
+pipeline_tag: text-generation
+---
+# Composition-RL-8B
+This repository contains the **Composition-RL-8B** model checkpoint, a version of Qwen3-8B-Base fine-tuned using the **Composition-RL** framework.
+Composition-RL is a data-efficient Reinforcement Learning with Verifiable Rewards (RLVR) approach introduced in the paper: [Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models](https://huggingface.co/papers/2602.12036).
+## Overview
+Composition-RL addresses the challenge of "too-easy" prompts (where the pass rate becomes 1 during training) by automatically composing multiple verifiable problems into a single, more complex, yet still verifiable prompt. This ensures that the model continues to receive informative training signals throughout the RL process, leading to improved reasoning capabilities across mathematical and scientific domains.
+## Model Details
+- **Base Model:** Qwen3-8b-Base
+- **Training Set:** [MATH-Composition-199K](https://huggingface.co/datasets/xx18/MATH-Composition-199K)
+- **Framework:** Reinforcement Learning with Verifiable Rewards (RLVR)
+## Resources
+- **Paper:** [Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models](https://huggingface.co/papers/2602.12036)
+- **GitHub Repository:** [XinXU-USTC/Composition-RL](https://github.com/XinXU-USTC/Composition-RL)
+- **Collection:** [Composition-RL Models and Datasets](https://huggingface.co/collections/xx18/composition-rl)
+## Usage
+For implementation details, including data generation and evaluation scripts, 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 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}
+}
+```