Junity's Projects
Help you understand how we finetune a LLM with a simplest and annotated example.
็จๆๆฌ็ผ่พๅจๅช่ง้ข
Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan)
This repo can create an character in one url.
LLM based TTS model, providing inference/training/deployment full-stack ability.
This repo provides you a SOP to Create/Finetune character with an URL and simple configuration.
๐ A Vue.js 3 UI Library made by Element team
ๅ็ฅ็ๅ็ๆๆ่ฎก็ฎๅจ
quantization of comparing increament of Critical and ATK.
Personal resume site with a blog, built with Astro and Tailwind.
Code for Kaggle Competition
This is a platform that can help you to develop your own llm data annotating platform.
Junity's personal website
This Jupyter Notebook condenses the Plotly API into one easy to use document with examples
Voice data <= 10 mins can also be used to train a good VC model!
ๅบไบvitsไธsoftvc็ๆญๅฃฐ้ณ่ฒ่ฝฌๆขๆจกๅ
SoftVC VITS Singing Voice Conversion
In this repository, you will learn how code works in VITS(Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech) in Jupyter Notebooks, including normalizing data, training process, inference process, and model's details.
Vector (and Scalar) Quantization, in Pytorch
Listing all Shrines of Zelda on a map, each shrine can be clicked and view how to clear it.