A tool for extracting plain text from Wikipedia dumps

Python package for WikiMedia dump processing (Wiktionary, Wikipedia etc). Wikitext parsing, template expansion, Lua module execution. For data extraction, bulk syntax checking, error detection, and…

Wiktionary dump file parser and multilingual data extractor

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Instruct-tune LLaMA on consumer hardware

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源多模态对话模型

Your image is almost there!

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

Robust recipes to align language models with human and AI preferences

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

OpenMMLab Text Detection, Recognition and Understanding Toolbox

useful text recognition algorithms, CRNN and SVTR text recognition

RepVGG: Making VGG-style ConvNets Great Again

This repository contains datasets and baselines for benchmarking Chinese text recognition.

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

🔥🔥🔥AI-driven data management platform Over 1 million developers are using Chat2DB

Train transformer language models with reinforcement learning.

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

Universal and Transferable Attacks on Aligned Language Models

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Transformer related optimization, including BERT, GPT

Development repository for the Triton language and compiler

Fast and memory-efficient exact attention

Question and Answer based on Anything.

Log analyser / visualiser for Java HotSpot JIT compiler. Inspect inlining decisions, hot methods, bytecode, and assembly. View results in the JavaFX user interface.

Ongoing research training transformer models at scale