OpenPipe / rl-experimentsLinks
OpenPipe Reinforcement Learning Experiments
☆30Updated 5 months ago
Alternatives and similar repositories for rl-experiments
Users that are interested in rl-experiments are comparing it to the libraries listed below
Sorting:
- A Python library to orchestrate LLMs in a neural network-inspired structure☆51Updated 10 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 6 months ago
- ☆58Updated last month
- Very minimal (and stateless) agent framework☆45Updated 7 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆92Updated 7 months ago
- Lego for GRPO☆28Updated 2 months ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 8 months ago
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆52Updated 6 months ago
- never forget anything again! combine AI and intelligent tooling for a local knowledge base to track catalogue, annotate, and plan for you…☆37Updated last year
- ☆116Updated 8 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 6 months ago
- Simple GRPO scripts and configurations.☆59Updated 6 months ago
- Collection of LLM completions for reasoning-gym task datasets☆28Updated last month
- ☆66Updated last year
- GPT-4 Level Conversational QA Trained In a Few Hours☆63Updated last year
- Clue inspired puzzles for testing LLM deduction abilities☆40Updated 5 months ago
- ☆34Updated 3 weeks ago
- ☆54Updated 9 months ago
- ☆21Updated last year
- Train your own SOTA deductive reasoning model☆104Updated 5 months ago
- ☆13Updated 3 months ago
- Simple Graph Memory for AI applications☆89Updated 3 months ago
- LLM reads a paper and produce a working prototype☆57Updated 4 months ago
- BH hackathon☆14Updated last year
- entropix style sampling + GUI☆27Updated 9 months ago
- 🚀 Scale your RAG pipeline using Ragswift: A scalable centralized embeddings management platform☆38Updated last year
- ☆26Updated last year
- ☆49Updated last year
- Modified Beam Search with periodical restart☆12Updated 11 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆83Updated 3 months ago