Instructions to use eth-nlped/TutorRL-7B-think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eth-nlped/TutorRL-7B-think with Transformers:

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

pipe = pipeline("text-generation", model="eth-nlped/TutorRL-7B-think")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eth-nlped/TutorRL-7B-think")
model = AutoModelForCausalLM.from_pretrained("eth-nlped/TutorRL-7B-think", 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 eth-nlped/TutorRL-7B-think with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/eth-nlped/TutorRL-7B-think

SGLang

How to use eth-nlped/TutorRL-7B-think 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 "eth-nlped/TutorRL-7B-think" \
    --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": "eth-nlped/TutorRL-7B-think",
		"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 "eth-nlped/TutorRL-7B-think" \
        --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": "eth-nlped/TutorRL-7B-think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use eth-nlped/TutorRL-7B-think with Docker Model Runner:
```
docker model run hf.co/eth-nlped/TutorRL-7B-think
```

TutorRL-7B-think / README.md

dmacjam

Update README.md

a53badf verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

2.64 kB

	---
	library_name: transformers
	license: apache-2.0
	license_link: https://github.com/eth-lre/PedagogicalRL/blob/main/LICENSE
	pipeline_tag: text-generation
	base_model:
	- Qwen/Qwen2.5-7B-Instruct
	tags:
	- math-tutor
	- grpo
	datasets:
	- SynthLabsAI/Big-Math-RL-Verified
	---

	# TutorRL-7B-think

	## Overview

	TutorRL-7B-think is a fine-tuned variant of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct), trained to act as a math tutor rather than a solver. It is aligned to pedagogical principles using reinforcement learning (GRPO) in a synthetic multi-turn classroom setting, without requiring any human-labeled data.

	This model was developed as part of the research project [From Problem-Solving to Teaching Problem-Solving](https://arxiv.org/abs/2505.15607), which proposes a scalable, annotation-free approach to training LLMs as educational tutors. Instead of directly answering questions, the model is optimized to scaffold reasoning, guide through Socratic questioning, and withhold final solutions when beneficial for learning.

	Repository: [https://github.com/eth-lre/PedagogicalRL](https://github.com/eth-lre/PedagogicalRL)

	## Intended Use

	This model is intended for use in:

	* Interactive math tutoring
	* Socratic dialogue generation
	* Research on educational alignment of LLMs
	* Safe and indirect teaching in problem-solving contexts

	## Thinking
	This model variant allows for hidden thinking.
	The thinking content is enclosed in tags: `<think> ... </think>`.

	## Example Usage

	```python
	from transformers import AutoTokenizer, AutoModelForCausalLM

	model_id = "eth-nlped/TutorRL-7B-think"

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

	messages = [
	{"role": "user", "content": "Can you help me solve 3x + 5 = 20?"}
	]

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

	outputs = model.generate(**inputs, max_new_tokens=512)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	## Citation

	If you use this model or build upon the training framework, please cite:

	```
	@misc{dinucujianu2025problemsolvingteachingproblemsolvingaligning,
	title={From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning},
	author={David Dinucu-Jianu and Jakub Macina and Nico Daheim and Ido Hakimi and Iryna Gurevych and Mrinmaya Sachan},
	year={2025},
	eprint={2505.15607},
	archivePrefix={arXiv},
	primaryClass={cs.CL},
	url={https://arxiv.org/abs/2505.15607}
	}
	```