Stars
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
A quick guide (especially) for trending instruction finetuning datasets
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
Retrieves parquet files from Hugging Face, identifies and quantifies junky data, duplication, contamination, and biased content in dataset using pandas
✨✨Latest Advances on Multimodal Large Language Models
A Dead Simple and Modularized Multi-Modal Training and Finetune Framework. Compatible to any LLaVA/Flamingo/QwenVL/MiniGemini etc series models.
A playbook for systematically maximizing the performance of deep learning models.
视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.
Secrets of RLHF in Large Language Models Part I: PPO
Code and documentation to train Stanford's Alpaca models, and generate the data.
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
Code for fintune ChatGLM-6b using low-rank adaptation (LoRA)
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Image to prompt with BLIP and CLIP
Revisiting Pre-trained Models for Chinese Natural Language Processing (MacBERT)
网页级exhentai阅读器（含翻译功能），js脚本实现，无需安装软件，解决ios频繁重签问题。
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
Next Generation of Shadowsocks(R) macOS client
TensorFlow code and pre-trained models for BERT
A TensorFlow Implementation of the Transformer: Attention Is All You Need
TensorFlow1.x版本教程（入门教程）
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
The swiss army knife of lossless video/audio editing
Conversion between Traditional and Simplified Chinese