Wei Liu's starred repositories
awesome_lists
Awesome Lists for Tenure-Track Assistant Professors and PhD students. (助理教授/博士生生存指南)
LLMDataHub
A quick guide (especially) for trending instruction finetuning datasets
LLM-Shearing
[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
Mu-scaling
Research without Re-search: Maximal Update Parametrization Yields Accurate Loss Prediction across Scales
adaptive-span
Transformer training code for sequential tasks
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
DeepSpeedExamples
Example models using DeepSpeed
RedPajama-Data
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
PaddleFleetX
飞桨大模型开发套件，提供大语言模型、跨模态大模型、生物计算大模型等领域的全流程开发工具链。
PaddleSlim
PaddleSlim is an open-source library for deep model compression and architecture search.
ChatGPT4MT
🎁[ChatGPT4MT] Towards Making the Most of ChatGPT for Machine Translation
ErrorAnalysis_Prompt
:gift:[ChatGPT4MTevaluation] ErrorAnalysis Prompt for MT Evaluation in ChatGPT
ChatGPT-vs.-BERT
🎁[ChatGPT4NLU] A Comparative Study on ChatGPT and Fine-tuned BERT
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
BlenderProc
A procedural Blender pipeline for photorealistic training image generation
safe-rules
详细的C/C++编程规范指南，由360质量工程部编著，适用于桌面、服务端及嵌入式软件系统。