dylan-sharp

Dylan Sharp's starred repositories

segment-anything-2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Language:Jupyter NotebookApache-2.0862100

audapolis

an editor for spoken-word audio with automatic transcription

Language:TypeScriptAGPL-3.0154300

daily-habit-tracker

Minimalistic app to help track and build daily habits

Language:TypeScript5500

fabric

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

Language:PythonMIT2009700

evolutionary-architecture-by-example

Navigate the complex landscape of .NET software architecture with our step-by-step, story-like guide. Unpack the interplay between modular monoliths, microservices, domain-driven design, and various architectural patterns. Go beyond the one-size-fits-all solutions and understand how to blend these approaches based on your unique needs.

Language:C#MIT149100

core-domain-charts

A tool for collaboratively finding your core domains - strategic business differentiators

CC-BY-SA-4.051800

llama-agents

Language:PythonMIT147100

Loop

Window management made elegant.

Language:SwiftGPL-3.0606200

spreadsheet-is-all-you-need

A nanoGPT pipeline packed in a spreadsheet

MIT201700

modded-nanogpt

GPT-2 (124M) quality in 5B tokens

Language:Python22000

surya

OCR, layout analysis, reading order, line detection in 90+ languages

Language:PythonGPL-3.0941800

univer

Univer is an open-source alternative to Google Sheets, Slides, and Docs

Language:TypeScriptApache-2.0613000

or-tools

Google's Operations Research tools:

Language:C++Apache-2.01087600

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Language:Jupyter NotebookMIT565500

scikit-learn

scikit-learn: machine learning in Python

Language:PythonBSD-3-Clause5911500

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Language:Jupyter Notebook1117700

InstantMesh

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Language:PythonApache-2.0286200

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Language:PythonApache-2.01386300

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

Language:TypeScriptNOASSERTION4053100