Instructions to use sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP with Transformers:

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

pipe = pipeline("text-generation", model="sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP")
model = AutoModelForCausalLM.from_pretrained("sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP

SGLang

How to use sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP 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 "sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP" \
    --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": "sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP",
		"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 "sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP" \
        --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": "sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP with Docker Model Runner:
```
docker model run hf.co/sunblaze-ucb/OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP
```

OLMo-2-7B-SFT-GRPO-MATH-1EPOCH-SYSP

Description:

A GRPO-fine-tuned version of allenai/OLMo-2-1124-7B-SFT trained on the MATH dataset with a system prompt.

This model was developed as part of the research presented in the paper Learning to Reason without External Rewards. It utilizes the Intuitor method, an instantiation of Reinforcement Learning from Internal Feedback (RLIF), which enables models to learn from intrinsic signals like self-certainty without requiring external rewards or labeled gold solutions.

Resources

Paper: Learning to Reason without External Rewards
Repository: sunblaze-ucb/Intuitor

Citation

@article{zhao2025learning,
  title={Learning to Reason without External Rewards},
  author={Zhao, Xuandong and Kang, Zhewei and Feng, Aosong and Levine, Sergey and Song, Dawn},
  journal={arXiv preprint arXiv:2505.19590},
  year={2025}
}