Raynor's starred repositories
generative-ai-for-beginners
18 Lessons, Get Started Building with Generative AI ๐ https://microsoft.github.io/generative-ai-for-beginners/
openai-cookbook
Examples and guides for using the OpenAI API
annotated_deep_learning_paper_implementations
๐งโ๐ซ 60+ Implementations/tutorials of deep learning papers with side-by-side notes ๐; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), ๐ฎ reinforcement learning (ppo, dqn), capsnet, distillation, ... ๐ง
whisper.cpp
Port of OpenAI's Whisper model in C/C++
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
system-design-resources
These are the best resources for System Design on the Internet
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.
Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
ml-engineering
Machine Learning Engineering Open Book
AnimatedDrawings
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
open_llama
OpenLLaMA, a permissively licensed open source reproduction of Meta AIโs LLaMA 7B trained on the RedPajama dataset
deepsparse
Sparsity-aware deep learning inference runtime for CPUs
annotated_research_papers
This repo contains annotated research papers that I found really good and useful
alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
extended-exercise-windows
A list of startups that have employee-friendly terms for exercising your options past 90 days.
LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
image-matching-webui
๐ค image matching toolbox webui