hitorilabs / navi
compute, storage, and networking infra at home
☆65Updated last year
Alternatives and similar repositories for navi:
Users that are interested in navi are comparing it to the libraries listed below
- Simple Transformer in Jax☆136Updated 10 months ago
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated last year
- Simple embedding -> text model trained on a small subset of Wikipedia sentences.☆153Updated last year
- Simplex Random Feature attention, in PyTorch☆74Updated last year
- ☆38Updated 9 months ago
- A really tiny autograd engine☆92Updated last year
- a highly efficient compression algorithm for the n1 implant (neuralink's compression challenge)☆46Updated 11 months ago
- Ultra low overhead NVIDIA GPU telemetry plugin for telegraf with memory temperature readings.☆62Updated 9 months ago
- This repo is my attempt at a rough implementation of nanoGPT trained on a dataset of 30,000 unique Twitter usernames☆24Updated last year
- Stream of my favorite papers and links☆41Updated last month
- ☆61Updated last year
- Cerule - A Tiny Mighty Vision Model☆67Updated 8 months ago
- ☆22Updated last year
- ☆55Updated 2 months ago
- ☆20Updated last year
- Sparse autoencoders for Contra text embedding models☆25Updated last year
- look how they massacred my boy☆63Updated 6 months ago
- papers.day☆93Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆63Updated last week
- A visual interface for understanding and interpreting Transformers☆77Updated last year
- Tools to help me easily add scripts to make my unix workflow faster☆39Updated 2 weeks ago
- A repository of prompts and Python scripts for intelligent transformation of raw text into diverse formats.☆30Updated last year
- A simple API converting a user's proposed tweet into a veritable banger.☆101Updated last year
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆59Updated 11 months ago
- My name is Ozymandias, King of Kings; Look on my Works, ye Mighty, and despair!☆40Updated last year
- could we make an ml stack in 100,000 lines of code?☆42Updated 9 months ago
- ☆23Updated 9 months ago
- ☆99Updated last year
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆50Updated 5 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year