Marco O1

🚀 🍓 Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

Marco-o1 is a large language model that not only focuses on disciplines with standard answers but also emphasizes open - ended resolutions. It is powered by advanced techniques like CoT fine - tuning, MCTS, reflection mechanisms, and innovative reasoning strategies, aiming to solve complex real - world problems.

🚀 Quick Start

Load Marco - o1 - CoT model

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AIDC-AI/Marco-o1")
model = AutoModelForCausalLM.from_pretrained("AIDC-AI/Marco-o1")

Inference

Execute the inference script (you can give any customized inputs inside):

./src/talk_with_model.py

# Use vLLM
./src/talk_with_model_vllm.py

✨ Features

Currently, our work is distinguished by the following highlights:

• 🍀 Fine - Tuning with CoT Data: We develop Marco - o1 - CoT by performing full - parameter fine - tuning on the base model using open - source CoT dataset combined with our self - developed synthetic data.
• 🍀 Solution Space Expansion via MCTS: We integrate LLMs with MCTS (Marco - o1 - MCTS), using the model's output confidence to guide the search and expand the solution space.
• 🍀 Reasoning Action Strategy: We implement novel reasoning action strategies and a reflection mechanism (Marco - o1 - MCTS Mini - Step), including exploring different action granularities within the MCTS framework and prompting the model to self - reflect, thereby significantly enhancing the model's ability to solve complex problems.
• 🍀 Application in Translation Tasks: We are the first to apply Large Reasoning Models (LRM) to Machine Translation task, exploring inference time scaling laws in the multilingual and translation domain.

OpenAI recently introduced the groundbreaking o1 model, renowned for its exceptional reasoning capabilities. Inspired by it, Marco - o1 leverages advanced techniques like CoT fine - tuning, MCTS, and Reasoning Action Strategies to enhance its reasoning power. As shown in the figures, Marco - o1 has achieved accuracy improvements on datasets and excels in translating slang expressions.

Figure 2: The overview of Marco - o1.

Figure 3: The main results of Marco - o1.

Figure 4: The demostration of translation task using Marco - o1.

👨🏻‍💻 Acknowledgement

Main Contributors

From MarcoPolo Team, AI Business, Alibaba International Digital Commerce:

• Yu Zhao
• Huifeng Yin
• Hao Wang
• Longyue Wang

Citation

If you find Marco - o1 useful for your research and applications, please cite:

@misc{zhao2024marcoo1openreasoningmodels,
      title={Marco - o1: Towards Open Reasoning Models for Open - Ended Solutions}, 
      author={Yu Zhao and Huifeng Yin and Bo Zeng and Hao Wang and Tianqi Shi and Chenyang Lyu and Longyue Wang and Weihua Luo and Kaifu Zhang},
      year={2024},
      eprint={2411.14405},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2411.14405}, 
}

📄 License

This project is licensed under Apache License Version 2 (SPDX - License - identifier: Apache - 2.0).

⚠️ Important Note

We would like to emphasize that this research work is inspired by OpenAI's o1 (from which the name is also derived). This work aims to explore potential approaches to shed light on the currently unclear technical roadmap for large reasoning models. Besides, our focus is on open - ended questions, and we have observed interesting phenomena in multilingual applications. However, we must acknowledge that the current model primarily exhibits o1 - like reasoning characteristics and its performance still fall short of a fully realized "o1" model. This is not a one - time effort, and we remain committed to continuous optimization and ongoing improvement.

⚠️ Disclaimer

We used compliance checking algorithms during the training process, to ensure the compliance of the trained model and dataset to the best of our ability. Due to complex data and the diversity of language model usage scenarios, we cannot guarantee that the model is completely free of copyright issues or improper content. If you believe anything infringes on your rights or generates improper content, please contact us, and we will promptly address the matter.

For more information, please visit our Github.