SakanaAI / DiscoPOPLinks
Code for Discovering Preference Optimization Algorithms with and for Large Language Models
☆191Updated last year
Alternatives and similar repositories for DiscoPOP
Users that are interested in DiscoPOP are comparing it to the libraries listed below
Sorting:
- smolLM with Entropix sampler on pytorch☆150Updated 11 months ago
- Code for Discovering Preference Optimization Algorithms with and for Large Language Models☆63Updated last year
- The official repository of ALE-Bench☆116Updated this week
- Plotting (entropy, varentropy) for small LMs☆98Updated 4 months ago
- ☆100Updated 3 months ago
- GRadient-INformed MoE☆264Updated last year
- Swarming algorithms like PSO, Ant Colony, Sakana, and more in PyTorch 😊☆131Updated this week
- ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution☆519Updated 2 weeks ago
- Automating the Search for Artificial Life with Foundation Models!☆431Updated 9 months ago
- look how they massacred my boy☆63Updated 11 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆159Updated last month
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆324Updated 11 months ago
- Implementation of SOAR☆42Updated 3 weeks ago
- An automated tool for discovering insights from research papaer corpora☆139Updated last year
- Code for ExploreTom☆86Updated 3 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 7 months ago
- RLP: Reinforcement as a Pretraining Objective☆155Updated last week
- Collection of LLM completions for reasoning-gym task datasets☆29Updated 3 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆34Updated last year
- ☆67Updated last year
- Alice in Wonderland code base for experiments and raw experiments data☆131Updated 3 weeks ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- σ-GPT: A New Approach to Autoregressive Models☆68Updated last year
- ☆17Updated 8 months ago
- ☆84Updated 3 months ago
- Train your own SOTA deductive reasoning model☆107Updated 7 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆24Updated 3 weeks ago
- Train, tune, and infer Bamba model☆133Updated 4 months ago
- General multi-task deep RL Agent☆185Updated last year
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆343Updated 3 months ago