Skip to content

Instantly share code, notes, and snippets.

View sikang99's full-sized avatar
💭
Happy working

Stoney Kang sikang99

💭
Happy working
View GitHub Profile
@sikang99
sikang99 / webrtc.rst
Created November 9, 2018 23:45 — forked from voluntas/webrtc.rst
WebRTC 資料まとめ
@sikang99
sikang99 / webrtc.rst
Created November 11, 2018 16:04 — forked from voluntas/webrtc.rst
WebRTC の未来

詳解 WebRTC

更新:2017-09-26
作者:@voluntas
作者サイト:http://voluntas.github.io/
バージョン:1.2.1
セッション日時:2017-09-24 14:20 - 15:00
セッション場所:5号館3F
@sikang99
sikang99 / webrtc-data-channels.js
Created November 13, 2018 00:36 — forked from noonat/webrtc-data-channels.js
WebRTC Data Channels
// This is a bare bones example of creating a data channel between two WebRTC
// peers. Let's imagine two peers trying to connect to each other. We'll call
// one the "offer peer", and the other the "answer peer". The offer peer will
// be the one initiating a connection, and the answer peer will be the one
// responding to it.
//
// The two peers must use a separate connection to negotiate their connection.
// A websocket connection to a shared server is often used for this negotiation.
// They will exchange offers and answers using the websocket. Each peer will
// also attempt to discover more details about themselves (ICE), such as their
sudo apt-get update
sudo apt-get install -y python3 python3-dev python3-pip gcc
sudo apt-get install -y python3-opencv
sudo apt-get install -y python3-numpy
sudo apt-get install git
sudo apt-get install wget
sudo apt-get install python3-setuptools
wget https://github.com/rockchip-linux/rknpu2/raw/master/runtime/RK356X/Linux/librknn_api/aarch64/librknnrt.so
sudo mv librknnrt.so /usr/lib/librknnrt.so
git clone https://github.com/rockchip-linux/rknn-toolkit2.git
@sikang99
sikang99 / compact-llm.md
Last active November 13, 2023 20:21
LLaMA, Alpaca, chatGLM, ...

Compact Language Models

Abbrs

  • GPT : Generative Pretrained Transformer
  • LLaMA : Large Language Model Meta AI, Meta
  • GLM : Generic Language Model, Tsinghua University
  • LoRA : Low-Rank Adaptation, MS
  • LiGO : Linear Growth Operator, MIT
  • PEFT : Parameter-Efficient Fine-Tuning, Hugging Face
  • LoRA + DeepSpeed + CPU offloading
@sikang99
sikang99 / learning_methods.md
Last active March 26, 2023 13:37
Learning Methods

Learning Methods

Transfer Learning

Federated Learning

Meta Learning

@sikang99
sikang99 / efficient_deep_learning.md
Last active March 30, 2023 00:21
Efficient Deep Learning
@sikang99
sikang99 / GNNs.md
Last active April 3, 2023 05:01
Graph Neural Networks (GNN)