Prakyath Kantharaju's repositories
torchtune
A Native-PyTorch Library for LLM Fine-tuning
torchrl_mcts
This is a proof of concept on how MCTS can be implemented on top of TorchRL
personal_blog
Personal blog and website for learning.
alpha-zero-general
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
tinylora
finetuning using lora and tinygrad. PEFT but better.
rl_benchmark
Bench marking and comparing torch rl and stable-baslines
kickstart.nvim
A launch point for your personal nvim configuration
Quadruped
Repository for the Stanford pupper documentation and train learner.
Fine_tune_Anything
Fine tuning code generation for any repository using a small and lightweight models
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
test_walking_with_palm
quad controler with palm, both RL controller and IK controlller
stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
integration
integration for acc and gyrodata
Hacking-robotics
Series of robotics tutorials for manipulators, locomotion robots, RL and Imitation learning.
manipulation
Course notes for MIT manipulation class
myosuite
MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.
HIL_toolkit
Toolkit for human in the loop optimization
App-Polar-streaming
Using asyncio, data
Resume-assistant
Rating resume, edit suggestion and cover letter generator
lit-llama
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
lang-segment-anything
SAM with text prompt
dotfiles
dotfiles
uitvbo
This repository contains the code for the paper "On Controller-Tuning with Time-Varying Optimization" (Accepted at the 61st IEEE Conference for Decision and Control).
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Lead-the-way
Using drone for navigation of legged and wheeled robotos.