[CVPR2024 Highlight] VBench - We Evaluate Video Generation
- aigc
- evaluation-kit
- gen-ai
- stable-diffusion
142,273 visible repositories in the index
241–264 of 802 · Most stars
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
Web-based tool converts GitHub repository contents into a single formatted text file
A robust Python tool for text-based AI training and generation using GPT-2.
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
YaRN: Efficient Context Window Extension of Large Language Models
YouTube Full Text Search - Search all of YouTube from the command line
心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models
📄 🤖 AI for medical and scientific papers
Converts PDF, DOC, DOCX, XML, HTML, RTF, etc to plain text
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
A neurosymbolic perspective on LLMs
VSCode extension for code suggestion
An easy way to extract information from documents
Synthetic data curation for post-training and structured data extraction
Advanced html to text converter
Pure C inference of Mistral Voxtral Realtime 4B speech to text model
中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调,给出三元组信息抽取微调示例。
Fetch an entire site and save it as a text file (to be used with AI models).
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Online playground for OpenAPI tokenizers
Template for building your own custom ChatGPT style doc search powered by Next.js, OpenAI, and Supabase.
All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型