Mohan Li's 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, ... 🧠
awesome-document-understanding
A curated list of resources for Document Understanding (DU) topic
bert_score
BERT score for text generation
build-nanogpt
Video+code lecture on building nanoGPT from scratch
Causality4NLP_Papers
A reading list for papers on causality for natural language processing (NLP)
char-rnn
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
chinese_fuzzy_matching
100行解决中文模糊实体识别with字典树和编辑距离 Chinese fuzzy entity matching with prefix tree and distance editing
CS294-112
CS 294-112 @ UCB Deep RL
DeBERTa
The implementation of DeBERTa
DRL
Deep Reinforcement Learning
InstructUIE
Universal information extraction with instruction learning
Live
收集于互联网的一些高清直播源。
LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
micrograd
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
mt-dnn
Multi-Task Deep Neural Networks for Natural Language Understanding
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
nn-zero-to-hero
Neural Networks: Zero to Hero
SearchEngine
搜索引擎原理
SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
snake-ga
AI Agent that learns how to play Snake with Deep Q-Learning
Stock_Analysis_For_Quant
Various Types of Stock Analysis in Excel, Matlab, Power BI, Python, R, and Tableau
The-Art-of-Linear-Algebra
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"
tianshou
An elegant, flexible, and superfast PyTorch deep reinforcement learning platform.
tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
UGEN
Incorporating Instructional Prompts into A Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling - Coling2022(Oral))
wl-coref
This repository contains the code for EMNLP-2021 paper "Word-Level Coreference Resolution"