Dan Lee's repositories
text-corpus-utils
Handy python data preprocessing utils
naubull2
profile overview
minhash-lsh
LSH using Minhash
llm-primers
Multiple out-sources and scripts for harnessing LLMs quickly
vim-setting
Common personal vimrc backup & share
LongLoRA
Efficient long-context fine-tuning, supervised fine-tuning, LongQA dataset.
codingtests
Just having small fun after work
lm-web-tests
Simple web demo to test various language model decoding methods/parameters.
cli-pipe
Unix like command pipeliner in python
rust-del-dups
Rust duplicate removal API
FastJsonAPI
A wrapper for FastAPI where customizing error outputs is made simple.
python-sandbox
Simple codes on the go, but kept for history
vpunct
An English auto punctuator for voice recognized texts
keras-aux
Keras model/layers for fast model prototyping, starting with Transformer
transformer-aan
souce code for "Accelerating Neural Transformer via an Average Attention Network"
Delving-deep-into-GANs
A curated, quasi-exhaustive list of state-of-the-art publications and resources about Generative Adversarial Networks (GANs) and their applications.
pyahocorasick
Python module (C extension and plain python) implementing Aho-Corasick algorithm
Theano
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.
MemN2N-babi-python
End-To-End Memory Networks for bAbI question-answering tasks
pywit
Python library for Wit.ai
gollum
A simple, Git-powered wiki with a sweet API and local frontend.
keras
Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow.
AlphaGo
A replication of DeepMind's 2016 Nature publication, "Mastering the game of Go with deep neural networks and tree search," details of which can be found on their website.