zyq-scut / rltf Goto Github PK
View Code? Open in Web Editor NEWAccepted by Transactions on Machine Learning Research (TMLR)
License: BSD 3-Clause "New" or "Revised" License
Accepted by Transactions on Machine Learning Research (TMLR)
License: BSD 3-Clause "New" or "Revised" License
Hello, I noticed that you have trained a four classification model (Critic).
what are the accuracy, recall, f1_score of the classification model in APPS testset. how to determine whether the critic model is ready?
孩子要看哭了,救救孩子
Is there any plan to add RLTF to the current state-of-the-art code model? Like starcoder or other LLM?
For the data in this repo, there are no 'pass_ratio', 'error_line', 'reward_type' in gen_solutions_critic_scores.pkl
I notice that your work only focus on code LLM, I wanna to use your method in general LLM to fix some factual error in model's response. Sincerely ask you for advice.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.