%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Aot
Overview :
Atom of Thoughts (AoT) is a novel reasoning framework that transforms the reasoning process into a Markov process by representing solutions as a combination of atomic problems. This framework significantly improves the performance of large language models on reasoning tasks through decomposition and contraction mechanisms, while reducing wasted computing resources. AoT can be used as an independent reasoning method or as a plugin for existing test-time augmentation methods, flexibly combining the advantages of different methods. This framework is open-source and implemented in Python, making it suitable for researchers and developers to experiment with and apply in the fields of natural language processing and large language models.
Target Users :
This product is suitable for scholars, developers, and research teams engaged in natural language processing and large language model research who need to improve model reasoning performance. It provides users with an efficient and flexible reasoning framework that helps them achieve better performance and resource utilization in reasoning tasks.
Use Cases
Using the AoT framework to reason about mathematical problems significantly improves the model's accuracy in solving problems.
Integrating AoT as a plugin into existing reasoning frameworks improves overall performance.
Reducing the computational overhead during model reasoning by contracting datasets improves efficiency.
Features
Supports various reasoning scenarios, including mathematics, multiple-choice questions, and multi-hop question answering
Can be combined with existing test-time augmentation methods as a plugin to enhance performance
Improves computing resource utilization efficiency through atomic state representation
Supports various datasets and models, such as gpt-4o-mini
Provides quick start scripts for users to easily conduct experiments and tests
Supports generating contracted datasets for use with other frameworks
Open-source code for easy secondary development by researchers and developers
How to Use
1. Clone the project locally: `git clone https://github.com/qixucen/atom`
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%230080ff;%20}%20%3c/style%3e%3c/defs%3e%3cpath%20class='st0'%20d='M16.2,11.1c.4.5.4,1.2,0,1.8l-4.7,7.1h-3.8l5.3-8L7.6,4h3.8l4.7,7.1Z'/%3e%3c/svg%3e)
2. Create an `apikey.py` file and configure the API key and URL
3. Install dependencies: `pip install -r requirements.txt`
4. Run the inference script using the command line, for example: `python main.py --dataset math --start 0 --end 10 --model gpt-4o-mini`
5. Generate a contracted dataset in plugin mode: `python main.py --dataset math --mode plugin --start 0 --end 10 --model gpt-4o-mini`
6. See the README.md file for more features and parameter configurations
7. Adjust the code or expand functionality as needed
Featured AI Tools
Tensorpool
TensorPool is a cloud GPU platform dedicated to simplifying machine learning model training. It provides an intuitive command-line interface (CLI) enabling users to easily describe tasks and automate GPU orchestration and execution. Core TensorPool technology includes intelligent Spot instance recovery, instantly resuming jobs interrupted by preemptible instance termination, combining the cost advantages of Spot instances with the reliability of on-demand instances. Furthermore, TensorPool utilizes real-time multi-cloud analysis to select the cheapest GPU options, ensuring users only pay for actual execution time, eliminating costs associated with idle machines. TensorPool aims to accelerate machine learning engineering by eliminating the extensive cloud provider configuration overhead. It offers personal and enterprise plans; personal plans include a $5 weekly credit, while enterprise plans provide enhanced support and features.
Model Training and Deployment
306.6K
Scireviewhub
SciReviewHub is an AI-powered tool designed to accelerate scientific writing and literature reviews. We leverage AI technology to quickly filter relevant papers based on your research goals and synthesize the most pertinent information into easily understandable and readily usable literature reviews. Through our platform, you can enhance your research efficiency, expedite publication timelines, and achieve breakthroughs in your field. Join SciReviewHub and reshape the future of scientific writing!
Research Tools
284.8K