oseh mathias's repositories
crypto-utils
A collection of crypto utilities for Collect
escrow-eth
Escrow service on the Eth network, written in React and Solidity
finetune-llama-lora-cypher
Fine-tuning Llama 2 7B and CodeLlama 13B models with synthetic Cypher queries for natural language to database query translation.
langchain-extract
π¦βοΈ Did you say you like data?
langchain-neo4j-knowledge-graph
Example Langchain agent to demonstrate the potential use of Neo4j graph database as memory.
Lexical
Created with CodeSandbox
next-js-context
Efficient persistent global state management without Redux, using Context, Reducers, and LocalStorage
wavesurfer.js
Navigable waveform built on Web Audio and Canvas
architecture-decision-record
Architecture decision record (ADR) examples for software planning, IT leadership, and template documentation
audiolm-superfeel
Superfeel adaptation of implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
flutter-webrtc
WebRTC plugin for Flutter Mobile/Desktop/Web
generate-synthetic-cypher-queries
Generates synthetic training data to fine tune LLMs to create cypher queries from natural language
how-to-make-webcam-pulse-detector-with-python-opencv
A python application that detects and highlights the heart-rate of an
langchainjs
π¦π Build context-aware reasoning applications π¦π
MorphyNet
MorphyNet: a Large Multilingual Database of Derivational and Inflectional Morphology (+morpheme segmentation)
react-big-calendar
gcal/outlook like calendar component
react-dnd-copy
Created with CodeSandbox
record
Audio recorder from microphone to a given file path. No external dependencies, MediaRecorder is used for Android an AVAudioRecorder for iOS.
semchunk
A fast and lightweight pure Python library for splitting text into semantically meaningful chunks.
soundstorm-pytorch
Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
soundstorm-superfeel
Superfeel adaptation of implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
styletts2-large
A fork of styletts2 with BigBird instead of BERT backing to increase sequence length to 4096
webcam-pulse-detector
A python application that detects and highlights the heart-rate of an individual (using only their own webcam) in real-time.