binary-husky

binary-husky's starred repositories

dify

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 you quickly go from prototype to production.

Language:TypeScriptNOASSERTION46724 349 3957

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

Language:PythonApache-2.031577 199 4897

GPTs

leaked prompts of GPTs

28385 300 26

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Language:PythonApache-2.027545 225 4623

one-api

OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistribution system, using a single API for all LLMs, and features an English UI.

Language:JavaScriptMIT18174 99 1422

navidrome

🎧☁️ Modern Music Server and Streamer compatible with Subsonic/Airsonic

Language:GoGPL-3.011476 76 1237

proxychains-ng

proxychains ng (new generation) - a preloader which hooks calls to sockets in dynamically linked programs and redirects it through one or more socks/http proxies. continuation of the unmaintained proxychains project. the sf.net page is currently not updated, use releases from github release page instead.

Language:CGPL-2.09736 233 493

markmap

Build mindmaps with plain text

Language:TypeScriptMIT8687 60 200

reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Language:TypeScriptApache-2.06506 37 101

pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。

Language:PythonApache-2.05511 83 470

viztracer

VizTracer is a low-overhead logging/debugging/profiling tool that can trace and visualize your python code execution.

Language:PythonApache-2.04924 48 196

VITS-fast-fine-tuning

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

Language:PythonApache-2.04702 40 565

MNBVC

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

MIT3409 64 53