korymath
Research Scientist DeepMind, CS PhD University of Alberta Intern Apple Special Projects Group, Google Brain, Twitter Cortex
DeepMindMontreal, Canada
korymath's Stars
Significant-Gravitas/AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
LAION-AI/Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
reflex-dev/reflex
🕸️ Web apps in pure Python 🐍
Stability-AI/StableLM
StableLM: Stability AI Language Models
cocktailpeanut/dalai
The simplest way to run LLaMA on your local machine
adityatelange/hugo-PaperMod
A fast, clean, responsive Hugo theme.
huggingface/trl
Train transformer language models with reinforcement learning.
lucidrains/PaLM-rlhf-pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
thu-ml/tianshou
An elegant PyTorch deep reinforcement learning library.
OpenAccess-AI-Collective/axolotl
Go ahead and axolotl questions
a16z-infra/companion-app
AI companions with memory: a lightweight stack to create and host your own AI companions
salesforce/CodeGen
CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.
CarperAI/trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
luosiallen/latent-consistency-model
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
eric-mitchell/direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
anthropics/hh-rlhf
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
google-deepmind/android_env
RL research on Android devices.
google-deepmind/dramatron
Dramatron uses large language models to generate coherent scripts and screenplays.
r2d4/react-llm
Easy-to-use headless React Hooks to run LLMs in the browser with WebGPU. Just useLLM().
CarperAI/cheese
Used for adaptive human in the loop evaluation of language and embedding models.
yangkevin2/emnlp22-re3-story-generation
alexc-hollywood/screen-json
Programmable/cross-platform screenplay files as JSON data documents: a screenwriting data model for the web designed to replace Final Draft Pro/Celtx/Fountain/FadeIn/Adobe Story format chaos.
google-deepmind/emergent_communication_at_scale
HumeAI/competitions
Hume AI ML Competitions
geometric-intelligence/pirounet
Conditional dance generator
uoe-agents/Expressivity-of-Emergent-Languages
The official code base of Expressivity of Emergent Languages (ICLR-2022).
korymath/justforlaughs
nfb-onf/sound-of-laughter
mguzdial3/Simplanimo