Beast code in Giters

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Language:PythonApache-2.03600 23 473

presidio

Context aware, pluggable and customizable data protection and de-identification SDK for text and images

Language:PythonMIT3560 67 404

trafilatura

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

Language:PythonApache-2.03356 30 355

Qwen-Agent

Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

Language:PythonNOASSERTION2946 30 296

BMTools

Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

Language:PythonApache-2.02868 35 37

modelscope-agent

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

Language:PythonApache-2.02547 36 197

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

Language:PythonApache-2.02091 29 137

DeepSeek-LLM

DeepSeek LLM: Let there be answers

Language:MakefileMIT1372 24 32

AgentTuning

AgentTuning: Enabling Generalized Agent Abilities for LLMs

Language:Python1316 16 51

cc_net

Tools to download and cleanup Common Crawl data

Language:PythonMIT950 24 44

llm-hallucination-survey

Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

880 13 3

ToolLearningPapers

Apache-2.0846 21 3

chatgpt-corpus

ChatGPT 中文语料库对话语料小说语料客服语料用于训练大模型

GPL-3.0823 7 4

z-bench

Z-Bench 1.0 by 真格基金：一个麻瓜的大语言模型中文测试集。Z-Bench is a LLM prompt dataset for non-technical users, developed by an enthusiastic AI-focused team in Zhenfund.

CC-BY-4.0474 9 8