Tim Newsom's repositories
AI_Girlfriend
Creating a waifu
api-interfaces
Interface definitions for API interactions between components
AudioGPT
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
bark
🔊 Text-Prompted Generative Audio Model
dalle-mini
DALL·E Mini - Generate images from a text prompt
device_rabbit_r1
GSI tree for the Rabbit R1
gaussian-splatting
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
grok-1
Grok open release
LocalAI
:robot: Self-hosted, community-driven, local OpenAI-compatible API. Drop-in replacement for OpenAI running LLMs on consumer-grade hardware. No GPU required. LocalAI is a RESTful API to run ggml compatible models: llama.cpp, alpaca.cpp, gpt4all.cpp, rwkv.cpp, whisper.cpp, vicuna, koala, gpt4all-j, cerebras and many others!
My-TTGO-Watch
A GUI named hedge for smartwatch like devices based on ESP32. Currently support for T-Watch2020 (V1,V2,V3), T-Watch2021, M5Paper, M5Core2 and native Linux support for testing.
nanoFramework.M5Stack
:package: Board support package for M5Stack, M5StickC and M5StickCPlus for .NET nanoFramework
node-llmatic
Use self-hosted LLMs with an OpenAI compatible API
privateGPT
Interact privately with your documents using the power of GPT, 100% privately, no data leaks
rag_llama_demo
Retrieval Augmented Generation (RAG) for Llama models using e5 vector embedding model for private LLM usage
SadTalker
[CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
shap-e
Generate 3D objects conditioned on text or images
stability-sdk
SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)
StableStudio
Community interface for generative AI
tortoise-tts
A multi-voice TTS system trained with an emphasis on quality
truss
Serve any model without boilerplate code
weaviate
Weaviate is an open source vector database that stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance and scalability of a cloud-native database, all accessible through GraphQL, REST, and various language clients.
whisper.cpp
Port of OpenAI's Whisper model in C/C++
wire-pod
Free, fully-featured server software for the Anki Vector robot.