wangxuguang's repositories
pong_actor-critic
Trains an agent with (stochastic) Policy Gradients(actor-critic) on Pong. Uses OpenAI Gym.
AlphaZero
Simplest AlphaZero Implementation
Language:PythonMIT000
DiffusionModel
Implement Diffusion Model only by Pytorch and MLP
Language:PythonMIT000
000
llama2.c
Inference Llama 2 in one file of pure C
Language:CMIT000
models
Models and examples built with TensorFlow
Language:PythonApache-2.0000
mosesdecoder
Moses, the machine translation system
Language:GroffLGPL-2.1000
Paddle
PArallel Distributed Deep LEarning
Language:C++Apache-2.0000
PPO-simplest
PPO in one file
Language:Python000
pytorch-pretrained-BERT
The Big-&-Extending-Repository-of-Transformers: PyTorch pretrained models for Google's BERT, OpenAI GPT & GPT-2, Google/CMU Transformer-XL.
Language:Jupyter NotebookApache-2.0000