seal-rg / recurrent-pretrainingLinks
Pretraining code for a large-scale depth-recurrent language model
☆801Updated this week
Alternatives and similar repositories for recurrent-pretraining
Users that are interested in recurrent-pretraining are comparing it to the libraries listed below
Sorting:
- Training Large Language Model to Reason in a Continuous Latent Space☆1,185Updated 5 months ago
- Dream 7B, a large diffusion language model☆839Updated 3 weeks ago
- procedural reasoning datasets☆960Updated last week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆341Updated 7 months ago
- Recipes to scale inference-time compute of open models☆1,106Updated last month
- Build your own visual reasoning model☆395Updated last week
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆318Updated 7 months ago
- OLMoE: Open Mixture-of-Experts Language Models☆809Updated 4 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆404Updated this week
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆497Updated last week
- [COLM 2025] LIMO: Less is More for Reasoning☆980Updated last week
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,123Updated 5 months ago
- ☆585Updated 3 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,023Updated 2 weeks ago
- MLGym A New Framework and Benchmark for Advancing AI Research Agents☆529Updated 3 weeks ago
- Muon is Scalable for LLM Training☆1,093Updated 3 months ago
- ☆1,025Updated 7 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆888Updated 2 months ago
- prime-rl is a codebase for decentralized async RL training at scale☆368Updated this week
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆498Updated 2 months ago
- Code for Quiet-STaR☆735Updated 10 months ago
- Muon is an optimizer for hidden layers in neural networks☆1,092Updated this week
- Code for BLT research paper☆1,736Updated last month
- System 2 Reasoning Link Collection☆843Updated 4 months ago
- TTRL: Test-Time Reinforcement Learning☆704Updated 3 weeks ago
- A bibliography and survey of the papers surrounding o1☆1,205Updated 8 months ago
- Tina: Tiny Reasoning Models via LoRA☆266Updated last month
- [ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters☆564Updated 5 months ago
- Automatic evals for LLMs☆467Updated 2 weeks ago
- Atom of Thoughts for Markov LLM Test-Time Scaling☆579Updated last month