《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Inference code for Llama models

PyTorch Tutorial for Deep Learning Researchers

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

A resource for learning about Machine learning & Deep Learning

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Traditional Mandarin LLMs for Taiwan

OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA

A minimalist implementation of score-based diffusion model

finetune llama2 with traditional chinese dataset

The purpose of this project is to address the design and implementation of an intelligent traffic light system based on fuzzy logic technology using Python.

Code for Submission titled "Guidance Learning for Multi-Domain DIalogue Management"

Master Thesis

Code for SRMRL

The offical code of "Parameter-Efficient Learning for Text-to-Speech Accent Adaptation"

Official code for Empower NLG: Offline Reinforcement Learning for Informal Summarization in Online Domains

In this project, we design a fuzzy controller to control a simple traffic light. The input is the number of vehicles about to pass on Main Street and the number of vehicles waiting on Side Street. …