open-thought / reasoning-gym-eval
Collection of LLM completions for reasoning-gym task datasets
☆16Updated last week
Alternatives and similar repositories for reasoning-gym-eval:
Users that are interested in reasoning-gym-eval are comparing it to the libraries listed below
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆37Updated this week
- Code for minimum-entropy coupling.☆31Updated 9 months ago
- Implementation of Spectral State Space Models☆16Updated last year
- ☆21Updated 3 months ago
- Simple GRPO scripts and configurations.☆59Updated last month
- Minimum Description Length probing for neural network representations☆19Updated 2 months ago
- A reading list of relevant papers and projects on foundation model annotation☆25Updated last month
- ☆38Updated 8 months ago
- Jax like function transformation engine but micro, microjax☆30Updated 5 months ago
- Code for☆24Updated 3 months ago
- ☆15Updated 6 months ago
- Understanding how features learned by neural networks evolve throughout training☆34Updated 5 months ago
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Updated 4 months ago
- Generative cellular automaton-like learning environments for RL.☆19Updated 2 months ago
- ☆67Updated 2 months ago
- Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)☆21Updated 4 months ago
- ☆25Updated 9 months ago
- Learn online intrinsic rewards from LLM feedback☆35Updated 3 months ago
- ☆27Updated 8 months ago
- Evaluation of neuro-symbolic engines☆35Updated 7 months ago
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆54Updated last month
- look how they massacred my boy☆63Updated 5 months ago
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆101Updated this week
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated 2 weeks ago
- ☆26Updated 11 months ago
- LMQL implementation of tree of thoughts☆34Updated last year
- Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"☆59Updated last year
- An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.☆25Updated 9 months ago
- Clean RL implementation using MLX☆28Updated last year
- Automated Capability Discovery via Foundation Model Self-Exploration☆42Updated last month