martin-wey / CodeUltraFeedbackLinks
CodeUltraFeedback: aligning large language models to coding preferences
☆71Updated last year
Alternatives and similar repositories for CodeUltraFeedback
Users that are interested in CodeUltraFeedback are comparing it to the libraries listed below
Sorting:
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆59Updated last year
- ☆65Updated last year
- Exploration of automated dataset selection approaches at large scales.☆47Updated 5 months ago
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆81Updated last year
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆82Updated 3 months ago
- Astraios: Parameter-Efficient Instruction Tuning Code Language Models☆60Updated last year
- The repository contains code for Adaptive Data Optimization☆25Updated 8 months ago
- Scalable Meta-Evaluation of LLMs as Evaluators☆42Updated last year
- StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback☆68Updated 11 months ago
- ☆100Updated last year
- [ACL'24] Code and data of paper "When is Tree Search Useful for LLM Planning? It Depends on the Discriminator"☆54Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆75Updated last year
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆104Updated 3 weeks ago
- ☆100Updated last year
- ☆78Updated 5 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆111Updated 7 months ago
- official implementation of paper "Process Reward Model with Q-value Rankings"☆60Updated 6 months ago
- Codebase for Instruction Following without Instruction Tuning☆35Updated 11 months ago
- ReasonFlux-Coder: Open-Source LLM Coders with Co-Evolving Reinforcement Learning☆108Updated last month
- ☆68Updated last week
- A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.☆86Updated last year
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆141Updated 11 months ago
- Self-Alignment with Principle-Following Reward Models☆163Updated 3 months ago
- ☆119Updated last year
- Replicating O1 inference-time scaling laws☆89Updated 8 months ago
- NeurIPS 2024 tutorial on LLM Inference☆45Updated 8 months ago
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆60Updated 5 months ago
- ☆71Updated 5 months ago
- ☆28Updated 7 months ago