This repository contains the code for generating the ToxiGen dataset for hate speech detection.
生成模型 tokenizer训练，模型初始化，模型预训练，指令微调。llama，creek
SecGPT is an open-source AI model designed for enhancing cybersecurity efficiency and effectiveness.
Spark-TTS is an advanced text-to-speech system using large language models for natural-sounding voice synthesis.
LettuceDetect is a hallucination detection framework for RAG applications.
A curated list of Model Context Protocol servers for AI model interactions with local and remote resources.
An open source deep research clone that utilizes AI to reason through vast amounts of web data extracted with Firecrawl.
Official Repo for TheoremExplainAgent, generating explanations for theorems using LLMs and AI video generation.
Toolkit for linearizing PDFs for LLM datasets/training.
MAP-NEO is a fully open-sourced Large Language Model with state-of-the-art performance for diverse research applications.
A GitHub repository for practicing large language models (LLMs) with various resources and projects.
一个包含213个中文大模型的评测平台，提供评分排行榜和模型输出结果。
