facebookresearch / coconutLinks
Training Large Language Model to Reason in a Continuous Latent Space
☆1,265Updated last month
Alternatives and similar repositories for coconut
Users that are interested in coconut are comparing it to the libraries listed below
Sorting:
- Pretraining and inference code for a large-scale depth-recurrent language model☆827Updated 2 weeks ago
- procedural reasoning datasets☆1,102Updated this week
- Recipes to scale inference-time compute of open models☆1,110Updated 3 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,085Updated 3 weeks ago
- A bibliography and survey of the papers surrounding o1☆1,206Updated 10 months ago
- [COLM 2025] LIMO: Less is More for Reasoning☆1,018Updated last month
- OLMoE: Open Mixture-of-Experts Language Models☆866Updated 6 months ago
- ☆1,034Updated 9 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,545Updated 4 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆862Updated last week
- ☆1,233Updated last week
- Large Reasoning Models☆805Updated 9 months ago
- Dream 7B, a large diffusion language model☆970Updated 3 weeks ago
- Official Repo for Open-Reasoner-Zero☆2,039Updated 3 months ago
- Code for BLT research paper☆1,983Updated 3 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,293Updated 2 weeks ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆528Updated 2 months ago
- ☆933Updated 2 months ago
- System 2 Reasoning Link Collection☆852Updated 6 months ago
- TTRL: Test-Time Reinforcement Learning☆806Updated last month
- Muon is Scalable for LLM Training☆1,311Updated last month
- Scalable RL solution for advanced reasoning of language models☆1,731Updated 6 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,942Updated this week
- An Open Large Reasoning Model for Real-World Solutions☆1,516Updated 3 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆461Updated this week
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,145Updated 7 months ago
- ☆1,353Updated 10 months ago
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆957Updated this week
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,562Updated 5 months ago
- Code for Quiet-STaR☆741Updated last year