ML-flash / M-E-GALinks
MEGA is a novel general purpose Genetic Algorithm frame work. That brings new Ideas and Features into the ML sphere such as transfer learning ,life long learning, and potentially open evolution. At the moment the code is still under development and investigation but I look forward to eventually validating the above claims.
☆35Updated last week
Alternatives and similar repositories for M-E-GA
Users that are interested in M-E-GA are comparing it to the libraries listed below
Sorting:
- The history files when recording human interaction while solving ARC tasks☆118Updated last week
- Exploration into the proposed architecture from Sapient Intelligence of Singapore 🇸🇬☆73Updated 5 months ago
- Plotting (entropy, varentropy) for small LMs☆99Updated 7 months ago
- My submission to the ARC-AGI-3 Developer Preview Agent Compitition.☆31Updated 4 months ago
- Automated Capability Discovery via Foundation Model Self-Exploration☆66Updated 11 months ago
- ☆67Updated 6 months ago
- SoTA Approach for ARC-AGI 2☆157Updated 4 months ago
- look how they massacred my boy☆63Updated last year
- ☆148Updated this week
- Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrast…☆138Updated this week
- Automating the Search for Artificial Life with Foundation Models!☆449Updated 2 months ago
- ☆34Updated 10 months ago
- Stupid test to check whether MDL principles improve ARC performance☆76Updated this week
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆85Updated 4 months ago
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆285Updated last year
- My writings about ARC (Abstraction and Reasoning Corpus)☆87Updated last month
- ☆603Updated 7 months ago
- Testing baseline LLMs performance across various models☆335Updated this week
- Implementation of SOAR☆48Updated 4 months ago
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆77Updated 11 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆107Updated last month
- Cellular Automata Accelerated in JAX (Oral at ICLR 2025)☆239Updated last month
- ☆27Updated 5 months ago
- ☆133Updated last year
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆61Updated last year
- A reinforcement learning framework based on MLX.☆249Updated last month
- smol models are fun too☆93Updated last year
- 🤖 Complete reproduction of 'AlphaGo Moment for Model Architecture Discovery' using MLX-LM instead of GPT-4. Autonomous neural architectu…☆27Updated 5 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆109Updated 10 months ago
- train entropix like a champ!☆20Updated last year