Pinned Repositories
annotated_deep_learning_paper_implementations
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
attorch
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
automemcpy
Bayesian-Machine-Learning
Code for the Assignment given in CSE515 Bayesian Machine Learning
CSE511_CA_project
RISCV RV32i Simulator and Assembler
Distributed-Database-with-Raft-Consensus-Algorithm
Implemented a database storing string key-value pairs using Raft Consensus Algorithm, ensuring consistent data replication and fault recovery across the distributed network of nodes. Obtained Linearizable Reads without paying high latency penalties for each request by utilizing the leader lease mechanism.
Linear-Optimization-Simplex-Algorithm
From scratch implementation of Dantzig's Simplex Algorithm to find optimal solutions to linear programs in canonical form.
Machine-Learning-Project
Modeling Stock Market Returns using Statistical, Classical Machine Learning and Deep Learning Models trained on CNNPred Dataset
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.
TransformerLens
A library for mechanistic interpretability of GPT-style language models
Vaibtan's Repositories
Vaibtan/attorch
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
Vaibtan/Bayesian-Machine-Learning
Code for the Assignment given in CSE515 Bayesian Machine Learning
Vaibtan/Distributed-Database-with-Raft-Consensus-Algorithm
Implemented a database storing string key-value pairs using Raft Consensus Algorithm, ensuring consistent data replication and fault recovery across the distributed network of nodes. Obtained Linearizable Reads without paying high latency penalties for each request by utilizing the leader lease mechanism.
Vaibtan/Linear-Optimization-Simplex-Algorithm
From scratch implementation of Dantzig's Simplex Algorithm to find optimal solutions to linear programs in canonical form.
Vaibtan/Machine-Learning-Project
Modeling Stock Market Returns using Statistical, Classical Machine Learning and Deep Learning Models trained on CNNPred Dataset
Vaibtan/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.
Vaibtan/TransformerLens
A library for mechanistic interpretability of GPT-style language models
Vaibtan/Vaibtan
Config files for my GitHub profile.
Vaibtan/Black-Scholes-Visualizer
An interactive dashboard to explore how varying market conditions impact option pricing with real-time interactive visualizations
Vaibtan/CSE-530-Distributed-Systems
Vaibtan/CSE-585-Computing-for-Medicine-Assignments
Vaibtan/CUDA-lectures
Material for cuda-mode lectures
Vaibtan/CUDA-Programming
Vaibtan/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Vaibtan/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
Vaibtan/Haskell-MOOC
My solutions to the problems sets of Haskell MOOC offered by the University of Helsinki
Vaibtan/llama.cpp
LLM inference in C/C++
Vaibtan/llama2.c
Inference Llama 2 in one file of pure C
Vaibtan/LLMs-from-scratch
Implementing a ChatGPT-like LLM from scratch, step by step
Vaibtan/LoRA-MNIST-Experiment
Vaibtan/Minimal-Byte-Pair-Encoding-Implementation
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
Vaibtan/Portfolio-Website
3-D portfolio made using ThreeJS and React
Vaibtan/pykan
Kolmogorov Arnold Networks
Vaibtan/pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Vaibtan/randomized-strategy-smart-contract
Vaibtan/Statistical-Inference-assignment
Solution Codes to MTH 372 Statistical Inference assignment
Vaibtan/tquic
A high-performance, lightweight, and cross-platform QUIC library
Vaibtan/triton
Development repository for the Triton language and compiler
Vaibtan/Variable-Length-Integer-Encoding-Schemes
Vaibtan/xgboost
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow