Instructions to use CMU-AIRe/MRT-offline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CMU-AIRe/MRT-offline with Transformers:

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

pipe = pipeline("text-generation", model="CMU-AIRe/MRT-offline")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CMU-AIRe/MRT-offline")
model = AutoModelForCausalLM.from_pretrained("CMU-AIRe/MRT-offline")
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 CMU-AIRe/MRT-offline with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CMU-AIRe/MRT-offline

SGLang

How to use CMU-AIRe/MRT-offline 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 "CMU-AIRe/MRT-offline" \
    --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": "CMU-AIRe/MRT-offline",
		"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 "CMU-AIRe/MRT-offline" \
        --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": "CMU-AIRe/MRT-offline",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CMU-AIRe/MRT-offline with Docker Model Runner:
```
docker model run hf.co/CMU-AIRe/MRT-offline
```

MRT-offline / README.md

CohenQu

MRT v0.1 checkpoint (R1-Distill-Qwen-1.5B)

986736c verified 22 days ago

preview code

Raw

History Blame Contribute Delete

3.2 kB

	---
	license: mit
	base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
	base_model_relation: finetune
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- reinforcement-learning
	- reasoning
	- math
	- test-time-compute
	- mrt
	- grpo
	---

	# MRT-offline (R1-Distill-Qwen-1.5B)

	DeepSeek-R1-Distill-Qwen-1.5B fine-tuned with Meta Reinforcement Fine-Tuning (MRT) in
	the open-ended setting — the paper-faithful "offline" variant: a dense progress reward
	(the change in the likelihood of eventual success contributed by each reasoning episode),
	estimated from a forced-termination meta-prover over an off-policy prefix and applied as a
	single end-of-trace bonus on top of outcome-reward GRPO.

	- 📄 Paper: [Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning](https://arxiv.org/abs/2503.07572)
	- 💻 Code / recipe: [CMU-AIRe/MRT](https://github.com/CMU-AIRe/MRT) → `train/rl/` (`REPRODUCTION.md`)
	- 🔀 On-policy variant: [CMU-AIRe/MRT-online](https://huggingface.co/CMU-AIRe/MRT-online)

	> v0.1 reproduction. This checkpoint was produced by the open-source v0.1 training
	> code (built on [miles](https://github.com/radixark/miles), since the original Open-R1
	> setup is no longer actively maintained), not the exact run from the paper. It
	> reproduces the paper's relative claim — MRT's gain over the base is ~2–3× the gain
	> from outcome-reward GRPO — at a slightly smaller absolute magnitude (see below).

	## Evaluation

	pass@1 (mean of 64 samples/problem) at a 16K token budget, averaged over AIME 2024 /
	AIME 2025 / AMC 2023 / MinervaMATH / MATH500 (single grader used for training and eval):

	\| model \| AIME24 \| AIME25 \| AMC23 \| Minerva \| MATH500 \| Avg \| gain over base \|
	\|---\|---:\|---:\|---:\|---:\|---:\|---:\|---:\|
	\| base (R1-Distill-Qwen-1.5B) \| 27.34 \| 22.86 \| 67.89 \| 24.94 \| 81.71 \| 44.95 \| — \|
	\| GRPO (outcome-reward) \| 28.12 \| 22.97 \| 67.77 \| 26.45 \| 81.85 \| 45.43 \| +0.48 \|
	\| MRT-offline (this model) \| 28.75 \| 23.59 \| 70.86 \| 24.96 \| 82.61 \| 46.16 \| +1.20 \|

	MRT's gain over base (+1.20) is 2.5× the GRPO gain (+0.48) — within the paper's
	reported 2–3× range. (Paper Table 1 reports +1.1 / +2.2 for GRPO / MRT; our reproduction
	reaches a smaller absolute magnitude — see `REPRODUCTION.md` for the training-length and
	grader notes.)

	## Training

	- Base: `deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B`; data: 4,000 NuminaMath problems.
	- GRPO + α-weighted progress bonus (α=1.0), 248 optimizer steps, 16K budget, temp 0.9.
	- Framework: [miles](https://github.com/radixark/miles) (Megatron-LM + SGLang). Full
	recipe, hyperparameters, and assumptions:
	[CMU-AIRe/MRT `train/rl/REPRODUCTION.md`](https://github.com/CMU-AIRe/MRT/tree/main/train/rl).

	## Citation

	```bibtex
	@misc{qu2025optimizingtesttimecomputemeta,
	title={Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning},
	author={Yuxiao Qu and Matthew Y. R. Yang and Amrith Setlur and Lewis Tunstall and Edward Emanuel Beeching and Ruslan Salakhutdinov and Aviral Kumar},
	year={2025}, eprint={2503.07572}, archivePrefix={arXiv}, primaryClass={cs.LG},
	url={https://arxiv.org/abs/2503.07572},
	}
	```