Instructions to use nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K with Transformers:

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

pipe = pipeline("text-generation", model="nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K

SGLang

How to use nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K 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 "nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K with Docker Model Runner:
```
docker model run hf.co/nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K
```

LLaDA-Instruct-JustGRPO

This model is LLaDA-8B-Instruct fine-tuned with JustGRPO on GSM8K.

It was introduced in the paper The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models.

Method

JustGRPO is a minimalist RL approach for diffusion language models. Instead of complex diffusion-specific RL adaptations, we simply treat dLLMs as autoregressive models during training and apply standard GRPO. See our paper for details.

Project Page: https://nzl-thu.github.io/the-flexibility-trap
Paper: arXiv:2601.15165
Code: https://github.com/LeapLabTHU/JustGRPO

Performance on GSM8K

Sequence Length	128	256	512
Accuracy (%)	83.8	89.1	89.8

Usage

For generation and evaluation, please refer to our GitHub repository.

Citation

@article{ni2026flexibility,
  title={The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models},
  author={Ni, Zanlin and Wang, Shenzhi and Yue, Yang and Yu, Tianyu and Zhao, Weilin and Hua, Yeguo and Chen, Tianyi and Song, Jun and Yu, Cheng and Zheng, Bo and Huang, Gao},
  journal={arXiv preprint arXiv:2601.15165},
  year={2026}
}

Downloads last month: 125

Safetensors

Model size

8B params

Tensor type

F32

Model tree for nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K

Base model

GSAI-ML/LLaDA-8B-Instruct

Finetuned

(32)

this model

Paper for nzl-thu/LLaDA-Instruct-JustGRPO-GSM8K

The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models

Paper • 2601.15165 • Published Jan 21 • 75