Emrul's repositories
trading-vue-js
💹 Hackable charting lib for traders. You can draw literally ANYTHING on top of candlestick charts.
awesome-decentralized-llm
Collection of LLM resources that can be used to build products you can "own" or to perform reproducible research.
coach
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
conformal_classification
Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).
D-Adaptation-Adan
Adan with D-Adaptation automatic step-sizes
d3rlpy
An offline deep reinforcement learning library
decision-transformer
Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.
deep_rl_zoo
A collection of Deep RL algorithms implemented with PyTorch to solve Atari games and classic control tasks like CartPole, LunarLander, and MountainCar.
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
dreamerv3
Mastering Diverse Domains through World Models
dumbproxy
Dumbest HTTP proxy ever
Epiphany
A note-taking App with a static blog generator focusing on technical writing
Explorer
Explorer is a PyTorch reinforcement learning framework for exploring new ideas.
machine-learning-articles
🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.
machine-learning-for-trading
Code for Machine Learning for Algorithmic Trading, 2nd edition.
manim
A community-maintained Python framework for creating mathematical animations.
mutsuki
Socks5/HTTP proxy server
natter
[EXPERIMENTAL] A peer-to-peer TCP port forwarding library using NAT traversal with QUIC
onnx
Open standard for machine learning interoperability
qp2p
peer-to-peer communications library for Rust based on QUIC protocol
rational_activations
Rational Activation Functions - Replacing Padé Activation Units
RevIN
RevIN: Reversible Instance Normalization For Accurate Time-series Forecasting Against Distribution Shift
rl-exploration-baselines
RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven exploration (RIDE).
rl_algorithms
Structural implementation of RL key algorithms
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.
Text2Video-Zero
Text-to-Image Diffusion Models are Zero-Shot Video Generators
Transformers-RL
An easy PyTorch implementation of "Stabilizing Transformers for Reinforcement Learning"