Jeff's repositories
AlwaysReddy
AlwaysReddy is a LLM voice assistant that is always just a hotkey away.
ApertureScience-Personality-Core-System
This repository is about implementing The Personality Cores Conversation System originally developed by Aperture Science, Inc. in the Portal game serise by Valve using llama3.
autotrain-advanced
🤗 AutoTrain Advanced
awesome-code-ai
A list of AI coding tools (assistants, completions, refactoring, etc.)
DAMO-YOLO
DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.
etichetta
A YOLO annotator, for human beings
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.
FastAPI-SaaS-Template
FastAPI based feature rich backend for SaaS products and creating user dashboards.
fish-speech
Brand new TTS solution
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
granite-code-models
Granite Code Models: A Family of Open Foundation Models for Code Intelligence
ifsc
:bank: IFSC Codes Repository
llm.c
LLM training in simple, raw C/CUDA
llmware
Unified framework for building enterprise RAG pipelines with small, specialized models
Machine-Learning-Specialization-Coursera
Contains Solutions and Notes for the Machine Learning Specialization By Stanford University and Deeplearning.ai - Coursera (2022) by Prof. Andrew NG
marker
Convert PDF to markdown quickly with high accuracy
OpenDevin
🐚 OpenDevin: Code Less, Make More
page-assist
Use your locally running AI models to assist you in your web browsing
rbac-wizard
RBAC Wizard is an intuitive UI tool for visualizing Kubernetes RBAC resources.
RealtimeSTT
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
Scrapegraph-ai
Python scraper based on AI
unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
Yi-1.5
Yi-1.5 is an upgraded version of Yi, delivering stronger performance in coding, math, reasoning, and instruction-following capability.