JirkaKlimes / jit-implementation
π JIT Implementation: Code That Writes Itself
β107Updated 7 months ago
Alternatives and similar repositories for jit-implementation:
Users that are interested in jit-implementation are comparing it to the libraries listed below
- Pytorch script hot swap: Change code without unloading your LLM from VRAMβ124Updated 2 weeks ago
- β129Updated 8 months ago
- Torch-activation, a collection of activation functions for PyTorch libraryβ24Updated last week
- Guaranteed Structured Output from any Language Model via Hierarchical State Machinesβ128Updated last week
- Tokun to can tokensβ17Updated this week
- A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private coβ¦β263Updated this week
- Train an adapter for any embedding model in under a minuteβ102Updated last month
- β106Updated last week
- Formatron empowers everyone to control the format of language models' output with minimal overhead.β197Updated 4 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokensβ139Updated 2 months ago
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.β412Updated last week
- A tool to analyze and debug neural networks in pytorch. Use a GUI to traverse the computation graph and view the data from many differentβ¦β287Updated 5 months ago
- AnyModal is a Flexible Multimodal Language Model Framework for PyTorchβ94Updated 4 months ago
- β288Updated last month
- A little(lil) Language Model (LM)β48Updated 2 weeks ago
- A simple tool that let's you explore different possible paths that an LLM might sample.β166Updated this week
- An implementation of PSGD Kron second-order optimizer for PyTorchβ89Updated last month
- DeMo: Decoupled Momentum Optimizationβ185Updated 5 months ago
- Teaching transformers to play chessβ122Updated 3 months ago
- Generate python documentation using LLMsβ66Updated 10 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"β99Updated 4 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)β64Updated 6 months ago
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fullβ¦β608Updated last month
- AI management toolβ114Updated 6 months ago
- Train your own SOTA deductive reasoning modelβ92Updated 2 months ago
- A pure NumPy implementation of Mamba.β222Updated 10 months ago
- β54Updated this week
- Inference of Mamba models in pure Cβ188Updated last year
- Easily view and modify JSON datasets for large language modelsβ75Updated 2 months ago
- β39Updated this week