tensorpro's repositories
Autonomous-Braking
Work towards a self-driving car's braking system with video demo.
DAO-lib
A library for making DAOs in solidity.
adversarial-experiments
Playing around with adversarial examlpes
CodeRL
This is a fork of code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22) specific to running on TPUs
darknet_scripts
An example of how to hack around with my darknet fork
Doom-Mapping
old research project using 2d maps to augment a Doom RL agent's state space
exppy
A library to help keep track of results and models from machine learning experiments.
large-code-models
TRC sponsored research investigating RL agents that model programming constructs (IE ASTs) more directly.
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
pytorch-a3c
PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".
pytorch-yolo2
Convert https://pjreddie.com/darknet/yolo/ into pytorch
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.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
ViZDoom
Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information. :godmode:
Voyager
An Open-Ended Embodied Agent with Large Language Models
vue-s3-dropzone
:droplet: Vue.js component works with AWS S3 serverlessly
XPretrain
Multi-modality pre-training