soldni
Follow
Lists (1)
Stars
Create and run high-performance macOS and Linux VMs on Apple Silicon, with built-in support for AI agents.
PyTorch building blocks for the OLMo ecosystem
OLMost every training recipe you need to perform data interventions with the OLMo family of models.
Curated list of datasets and tools for post-training.
Versatile typeface for code, from code.
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
😸 Soothing pastel theme for the high-spirited!
A curated list of resources and examples of ASCII Art
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
Toolkit for linearizing PDFs for LLM datasets/training
LLM.swift is a simple and readable library that allows you to interact with large language models locally with ease for macOS, iOS, watchOS, tvOS, and visionOS.
Large Language Model (LLM) module for the Spezi Ecosystem
BPE modification that implements removing of the intermediate tokens during tokenizer training.
A curated list of awesome model based RL resources (continually updated)
Dockerized iCloud Client - make a local copy of your iCloud documents and photos, and keep it automatically up-to-date.
Tools for shrinking fastText models (in gensim format)
[ACL 2024] This is the code repo for our ACL’24 paper "Cleaner Pretraining Corpus Curation with Neural Web Scraping".
GitHub Action to build and push Docker images with Buildx
Fast bare-bones BPE for modern tokenizer training
A javascript text differencing implementation.
A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.
Run a TryCloudflare tunnel to your flask app right from code.
A PyTorch native library for large model training
Chat Templates for 🤗 HuggingFace Large Language Models
Go-DomDistiller is a Go port of the DOM Distiller library which implements Reader mode in Chrome for Android and Desktop. It has no dependencies on Chromium and is meant to run as a command line pr…