Instructions to use MegaScience/Qwen2.5-3B-MegaScience with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MegaScience/Qwen2.5-3B-MegaScience with Transformers:

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

pipe = pipeline("text-generation", model="MegaScience/Qwen2.5-3B-MegaScience")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MegaScience/Qwen2.5-3B-MegaScience")
model = AutoModelForCausalLM.from_pretrained("MegaScience/Qwen2.5-3B-MegaScience")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MegaScience/Qwen2.5-3B-MegaScience with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MegaScience/Qwen2.5-3B-MegaScience"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MegaScience/Qwen2.5-3B-MegaScience",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MegaScience/Qwen2.5-3B-MegaScience

SGLang

How to use MegaScience/Qwen2.5-3B-MegaScience 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 "MegaScience/Qwen2.5-3B-MegaScience" \
    --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": "MegaScience/Qwen2.5-3B-MegaScience",
		"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 "MegaScience/Qwen2.5-3B-MegaScience" \
        --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": "MegaScience/Qwen2.5-3B-MegaScience",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MegaScience/Qwen2.5-3B-MegaScience with Docker Model Runner:
```
docker model run hf.co/MegaScience/Qwen2.5-3B-MegaScience
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning

This repository contains the Qwen2.5-3B-MegaScience model, one of the models trained as part of the MegaScience project.

For the official code, data processing pipeline, and evaluation system, please refer to the MegaScience GitHub repository.

Qwen2.5-3B-MegaScience

Usage

You can use this model with the Hugging Face transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "MegaScience/Qwen2.5-3B-MegaScience"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example text generation
prompt = "The capital of France is"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt")

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=20)
print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0])

Training Recipe

LR: 5e-6
LR Schedule: Cosine
Batch Size: 512
Max Length: 4,096
Warm Up Ratio: 0.05
Epochs: 3

Evaluation Results

More about MegaScience

Citation

Check out our paper for more details. If you use our dataset or find our work useful, please cite

@article{fan2025megascience,
  title={MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning},
  author={Fan, Run-Ze and Wang, Zengzhi and Liu, Pengfei},
  year={2025},
  journal={arXiv preprint arXiv:2507.16812},
  url={https://arxiv.org/abs/2507.16812}
}