open-thought / system-2-research
System 2 Reasoning Link Collection
☆832Updated last month
Alternatives and similar repositories for system-2-research
Users that are interested in system-2-research are comparing it to the libraries listed below
Sorting:
- ☆1,019Updated 4 months ago
- A bibliography and survey of the papers surrounding o1☆1,192Updated 5 months ago
- Verifiers for LLM Reinforcement Learning☆924Updated last month
- procedural reasoning datasets☆578Updated last week
- Recipes to scale inference-time compute of open models☆1,068Updated last week
- Training Large Language Model to Reason in a Continuous Latent Space☆1,104Updated 3 months ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆445Updated last month
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆791Updated 2 weeks ago
- Code for Quiet-STaR☆731Updated 8 months ago
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆307Updated 5 months ago
- Pretraining code for a large-scale depth-recurrent language model☆756Updated last month
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆869Updated 2 weeks ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆439Updated 7 months ago
- Build your own visual reasoning model☆359Updated this week
- MLGym A New Framework and Benchmark for Advancing AI Research Agents☆489Updated this week
- Minimalistic large language model 3D-parallelism training☆1,850Updated this week
- ☆515Updated 5 months ago
- A reading list on LLM based Synthetic Data Generation 🔥☆1,265Updated 2 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,516Updated last week
- A benchmark to evaluate language models on questions I've previously asked them to solve.☆1,010Updated 2 weeks ago
- An Open Source Toolkit For LLM Distillation☆596Updated 2 weeks ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆323Updated 5 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆840Updated last week
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆696Updated last week
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆455Updated last week
- Large Reasoning Models☆805Updated 5 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆723Updated 7 months ago
- Sparsify transformers with SAEs and transcoders☆526Updated this week
- ☆111Updated 4 months ago
- A compact LLM pretrained in 9 days by using high quality data☆313Updated last month