Instructions to use TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH with Transformers:

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

pipe = pipeline("text-generation", model="TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH")
model = AutoModelForCausalLM.from_pretrained("TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH")
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 TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH

SGLang

How to use TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH 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 "TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH" \
    --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": "TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH",
		"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 "TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH" \
        --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": "TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH with Docker Model Runner:
```
docker model run hf.co/TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

TMLR-Group-HF/Self-Certainty-Qwen2.5-7B

This is the Qwen2.5-7B model trained by the Self-Certainty method using the MATH training set. It is part of the work presented in the paper Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.

For more details on the Co-rewarding framework and its implementation, you can find the code and further information on the official GitHub repository: https://github.com/tmlr-group/Co-rewarding.

Citation

@article{zhang2025coreward,
      title={Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models},
      author={Zhang, Zizhuo and Zhu, Jianing and Ge, Xinmu and Zhao, Zihua and Zhou, Zhanke and Li, Xuan and Feng, Xiao and Yao, Jiangchao and Han, Bo},
      journal={arXiv preprint arXiv:2508.00410},
      year={2025}
}

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH

Quantizations

4 models

Collection including TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH

Co-rewarding

Collection

Co-rewarding is a novel self-supervised RL framework that improves training stability by seeking complementary supervision from another views. • 75 items • Updated Dec 21, 2025 • 1

Paper for TMLR-Group-HF/Self-Certainty-Qwen2.5-7B-MATH

Co-Reward: Self-supervised Reinforcement Learning for Large Language Model Reasoning via Contrastive Agreement

Paper • 2508.00410 • Published Aug 1, 2025 • 1