Ziniu Li's Projects
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
中文 LLaMA-2 & Alpaca-2 大模型二期项目 + 本地CPU/GPU训练部署 (Chinese LLaMA-2 & Alpaca-2 LLMs)
Linux 端使用 Clash 作为代理工具
2018 Spring Course, Computer Vision and Pattern Recognition, in XJTU
Experiments with Deep Learning
Face Recognition on NVIDIA TX2
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
Code for Go-Explore: a New Approach for Hard-Exploration Problems
Minimalistic gridworld package for OpenAI Gym
High Dimensional Data Analysis: Lasso, Compressed Sensing, AdaBoost
Code for ICLR 2022 Paper (HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning)
Code for NeurIPS 2023 Paper (Imitation Learning from Imperfection: Theoretical Justifications and Algorithms)
This is my implementation of algorithms in the book, 《Machine Learning》, by Zhihua Zhou
The course of machine learning I take in XJTU, 2018 spring, guided by Prof Deyu Meng
TensorFlow implementation of Model-Uncertainty-in-Neural-Networks
Nonlinear Independent Components Estimation (Dinh et al, 2014) in PyTorch.
Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)
Reproducing results from DeepMind's paper on Population Based Training of Neural Networks.