Instructions to use OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward with Transformers:

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

pipe = pipeline("text-generation", model="OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward")
model = AutoModelForCausalLM.from_pretrained("OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward")
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 OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward

SGLang

How to use OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward 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 "OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward" \
    --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": "OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward",
		"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 "OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward" \
        --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": "OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward with Docker Model Runner:
```
docker model run hf.co/OpenLearnLM/special-r1-deepseek-qwen3-8b-sped-adaptive-think-noreward
```

Special-R1-Qwen2.5-7B-NoThink

A reasoning-enhanced language model fine-tuned from Qwen2.5-7B-Instruct using GRPO (Group Relative Policy Optimization) for special education applications.

Model Description

This model is trained to provide direct, concise answers without explicit chain-of-thought reasoning steps (NoThink variant). It focuses on generating accurate responses efficiently.

Base Model: Qwen/Qwen2.5-7B-Instruct
Training Method: GRPO (Group Relative Policy Optimization)
Training Steps: 300
Focus: Direct answer generation without verbose reasoning

Training Details

Training Configuration

Framework: veRL (Volcano Engine Reinforcement Learning)
Algorithm: GRPO
Batch Size: Configured for 4x GPU setup
Precision: bfloat16

Training Data

Educational reasoning tasks
Mathematical problem solving
General knowledge Q&A

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "OpenLearnLM/special-r1-qwen2.5-7b-nothink"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

messages = [
    {"role": "user", "content": "What is the capital of France?"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=512)
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)

Model Variants

Model	Description
special-r1-qwen2.5-7b-nothink (this)	Direct answers without explicit reasoning
special-r1-qwen2.5-7b-think	With chain-of-thought reasoning

Limitations

Trained primarily on English and Korean data
May not perform optimally on highly specialized domains outside training distribution
As an early checkpoint (step 300), performance may improve with continued training

Citation

If you use this model, please cite:

@misc{openlearnlm2025special,
  title={Special-R1: Reasoning Models for Education},
  author={OpenLearnLM Team},
  year={2025},
  publisher={HuggingFace},
  url={https://huggingface.co/OpenLearnLM/special-r1-qwen2.5-7b-nothink}
}