Cemberk's repositories
alpa
Training and serving large-scale neural networks
Ambient
The multiplayer game engine
annotated_deep_learning_paper_implementations
🧑🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
ControlNet
Let us control diffusion models!
Fantasia3D
official repository for "Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation"
FinNLP
Alternative data (NLP) in finance.
gerev
🧠 AI-powered search engine for your organization 🔎
GPT-4-coding-assistant
GPT-4 Coding Assistant is a web application that leverages the power of OpenAI's GPT-4 to help developers with their coding tasks.
llm-security
New ways of breaking app-integrated LLMs
local-attention
An implementation of local windowed attention for language modeling
magic-copy
Magic Copy is a Chrome extension that uses Meta's Segment Anything Model to extract a foreground object from an image and copy it to the clipboard.
Make-It-3D
Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
only_train_once
[ICLR 2023] OTOv2: Automatic, Generic, User-Friendly; [NeurIPS 2021] Only Train Once: A One-Shot Neural Network Training And Pruning Framework
Promptify
Prompt Engineering | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research
pytorch-cpp
C++ Implementation of PyTorch Tutorials for Everyone
quivr
Dump all your files and thoughts into your GenerativeAI Second Brain and chat with it
reflexion
Reflexion: an autonomous agent with dynamic memory and self-reflection
rosenpass
Rosenpass is a formally verified, post-quantum secure VPN that uses WireGuard to transport the actual data.
runhouse
Programmable 🐍 remote compute 🔋 and data 📂 across environments 💻 and users 👩💻
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.
st-chat
Streamlit Component, for a Chatbot UI
Stock-Market-App
Simple Stock Market App build with Streamlit and Python
toolformer-pytorch
Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI
tree-of-thoughts
Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities