Instructions to use SJTU-DENG-Lab/LightningRL-8B-b32-MBPP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SJTU-DENG-Lab/LightningRL-8B-b32-MBPP with Transformers:

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

pipe = pipeline("text-generation", model="SJTU-DENG-Lab/LightningRL-8B-b32-MBPP", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("SJTU-DENG-Lab/LightningRL-8B-b32-MBPP", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SJTU-DENG-Lab/LightningRL-8B-b32-MBPP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SJTU-DENG-Lab/LightningRL-8B-b32-MBPP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SJTU-DENG-Lab/LightningRL-8B-b32-MBPP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SJTU-DENG-Lab/LightningRL-8B-b32-MBPP

SGLang

How to use SJTU-DENG-Lab/LightningRL-8B-b32-MBPP 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 "SJTU-DENG-Lab/LightningRL-8B-b32-MBPP" \
    --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": "SJTU-DENG-Lab/LightningRL-8B-b32-MBPP",
		"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 "SJTU-DENG-Lab/LightningRL-8B-b32-MBPP" \
        --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": "SJTU-DENG-Lab/LightningRL-8B-b32-MBPP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SJTU-DENG-Lab/LightningRL-8B-b32-MBPP with Docker Model Runner:
```
docker model run hf.co/SJTU-DENG-Lab/LightningRL-8B-b32-MBPP
```

LightningRL

Diffusion Large Language Models with a SOTA Accuracy–Parallelism Trade-off

We introduce LightningRL, a reinforcement learning post-training framework for block-wise diffusion Large Language Models (dLLMs) that breaks the accuracy–parallelism trade-off. Applied to SDAR-8B, LightningRL achieves 7.32 average TPF and 497.9 AUP — simultaneously improving both generation quality and inference speed.

LightningRL-8B-32b-MATH500, LightningRL-8B-32b-GSM8K, LightningRL-8B-32b-MBPP, and LightningRL-8B-32b-HumanEval are task-specific variants fine-tuned with different reward weight configurations for targeted deployment.

Citation

@misc{hu2026lightningrlbreakingaccuracyparallelismtradeoff,
      title={LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning}, 
      author={Yanzhe Hu and Yijie Jin and Pengfei Liu and Kai Yu and Zhijie Deng},
      year={2026},
      eprint={2603.13319},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2603.13319}, 
}

Downloads last month: 12

Safetensors

Model size

8B params

Tensor type

F16

Collection including SJTU-DENG-Lab/LightningRL-8B-b32-MBPP

LightingRL

Collection

Diffusion Large Language Models with a SOTA Accuracy–Parallelism Trade-off • 7 items • Updated Apr 16 • 2

Paper for SJTU-DENG-Lab/LightningRL-8B-b32-MBPP

LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning

Paper • 2603.13319 • Published Mar 4 • 1