Instructions to use Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 with Transformers:

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

pipe = pipeline("text-generation", model="Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326")
model = AutoModelForCausalLM.from_pretrained("Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326", device_map="auto")
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 Settings

vLLM

How to use Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326

SGLang

How to use Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 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 "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326" \
    --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": "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326",
		"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 "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326" \
        --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": "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 with Docker Model Runner:
```
docker model run hf.co/Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326
```

📝 Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning

Checkpoints of Trust Region Preference Approximation (TRPA) on DeepScaleR based on DeepSeek-R1-Distill-Qwen-7B using the 0326 version of verl0326

[TRPA Paper | TRPA Github]

📚 Citation

@article{su2025trust,
  title={Trust region preference approximation: A simple and stable reinforcement learning algorithm for llm reasoning},
  author={Su, Xuerui and Xie, Shufang and Liu, Guoqing and Xia, Yingce and Luo, Renqian and Jin, Peiran and Ma, Zhiming and Wang, Yue and Wang, Zun and Liu, Yuting},
  journal={arXiv preprint arXiv:2504.04524},
  year={2025}
}

Downloads last month: 17

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Finetuned

(304)

this model

Dataset used to train Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326

Paper for Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326

Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning

Paper • 2504.04524 • Published Apr 6, 2025 • 1