MichaelDays's Stars
ggerganov/llama.cpp
LLM inference in C/C++
ggerganov/whisper.cpp
Port of OpenAI's Whisper model in C/C++
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
mlc-ai/mlc-llm
Universal LLM Deployment Engine with ML Compilation
karpathy/llama2.c
Inference Llama 2 in one file of pure C
joonspk-research/generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
smol-ai/developer
the first library to let you embed a developer agent in your own app!
rhasspy/piper
A fast, local neural text to speech system
smol-ai/GodMode
AI Chat Browser: Fast, Full webapp access to ChatGPT / Claude / Bard / Bing / Llama2! I use this 20 times a day.
KoboldAI/KoboldAI-Client
InternLM/lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
freedmand/semantra
Multi-tool for semantic search
AI-Engineer-Foundation/agent-protocol
Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.
nickm980/smallville
Generative Agents for video games. Based on Generative Agents: Interactive Simulacra of Human Behavior
XiongjieDai/GPU-Benchmarks-on-LLM-Inference
Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?
akashmjn/tinydiarize
Minimal extension of OpenAI's Whisper adding speaker diarization with special tokens
philipturner/metal-flash-attention
Faster alternative to Metal Performance Shaders
arcee-ai/DALM
Domain Adapted Language Modeling Toolkit - E2E RAG
neonbjb/ocotillo
Performant and accurate speech recognition built on Pytorch
neph1/LlamaTale
Giving the power of LLM's to a MUD lib.
fkodom/dilated-attention-pytorch
(Unofficial) Implementation of dilated attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens" (https://arxiv.org/abs/2307.02486)
Maximilian-Winter/AIRoleplay
Little AI roleplay program
alexisrozhkov/dilated-self-attention
Implementation of the dilated self attention as described in "LongNet: Scaling Transformers to 1,000,000,000 Tokens"