Instructions to use zml5418/OPSD-Qwen3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zml5418/OPSD-Qwen3-8B with Transformers:

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

pipe = pipeline("text-generation", model="zml5418/OPSD-Qwen3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zml5418/OPSD-Qwen3-8B")
model = AutoModelForCausalLM.from_pretrained("zml5418/OPSD-Qwen3-8B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zml5418/OPSD-Qwen3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zml5418/OPSD-Qwen3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zml5418/OPSD-Qwen3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zml5418/OPSD-Qwen3-8B

SGLang

How to use zml5418/OPSD-Qwen3-8B 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 "zml5418/OPSD-Qwen3-8B" \
    --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": "zml5418/OPSD-Qwen3-8B",
		"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 "zml5418/OPSD-Qwen3-8B" \
        --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": "zml5418/OPSD-Qwen3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zml5418/OPSD-Qwen3-8B with Docker Model Runner:
```
docker model run hf.co/zml5418/OPSD-Qwen3-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OPSD-Qwen3-8B

Checkpoints of Qwen/Qwen3-8B post-trained with OPSD in NoThink mode (enable_thinking=False) on DAPO-Math, released with the paper

Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models Zehao Liu, Vasant G. Honavar. arXiv:2609.28682

These are research artifacts for studying how NoThink post-training moves the model along the Think/NoThink axis of the residual stream ("thinking leakage"). They are not intended as improved general-purpose models.

Checkpoints

Each saved training step is a separate branch:

revision	training step
`step-25`	25
`step-50`	50
`step-75`	75
`step-100`	100

The main branch holds this card and the final checkpoint (step-100). Weights dtype: bfloat16.

from transformers import AutoModelForCausalLM, AutoTokenizer

repo, rev = "zml5418/OPSD-Qwen3-8B", "step-100"
model = AutoModelForCausalLM.from_pretrained(repo, revision=rev, torch_dtype="bfloat16")
tok = AutoTokenizer.from_pretrained(repo, revision=rev)

Training

Training and evaluation details are given in the paper.

Citation

@misc{liu2026thinkingleakagecausalaudit,
      title={Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models},
      author={Zehao Liu and Vasant G. Honavar},
      year={2026},
      eprint={2609.28682},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2609.28682},
}