蓝蓝的小火苗's repositories
MinerU
A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。
edgetunnel
在原版的基础上修改了显示 VLESS 配置信息转换为订阅内容。使用该脚本，你可以方便地将 VLESS 配置信息使用在线配置转换到 Clash 或 Singbox 等工具中。
fish-speech
Brand new TTS solution
siyuan-unlock
思源笔记免登录版本；可以不登录使用同步功能
lmstfy
A task queue with REST API
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
WARP-Clash-API
该项目可以让你通过订阅的方式使用Cloudflare WARP+，自动获取流量。This project enables you to use Cloudflare WARP+ through subscription, automatically acquiring traffic.
cognee
Deterministic LLMs Outputs for AI Applications and AI Agents
llama3
The official Meta Llama 3 GitHub site
llama3-chinese
Llama3-Chinese是以Meta-Llama-3-8B为底座，使用 DORA + LORA+ 的训练方法，在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。
Cloudreve
🌩支持多家云存储的云盘系统 (Self-hosted file management and sharing system, supports multiple storage providers)
storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
OpenDevin
🐚 OpenDevin: Code Less, Make More
grok-1
Grok open release
wechat-bc
类似开发公众号一样，开发个人微信号
MeloTTS
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
LLaMA-Factory
Unify Efficient Fine-tuning of 100+ LLMs
LanguageAgentTreeSearch
Official repository for paper "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"
ADU-Planner_rag-a-thon2024
2024 LlamaIndex RAG Hackathon "1st Place Award" Project
search_with_lepton
Building a quick conversation-based search demo with Lepton AI.
Chinese-Mixtral-8x7B
中文Mixtral-8x7B（Chinese-Mixtral-8x7B）
AGI-Samantha
AGI has been achieved externally
LLMLingua
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Bert-VITS2-ext
基于Bert-VITS2做的表情、动画测试
sparrow
Data extraction from documents with ML
WikiChat
WikiChat stops the hallucination of large language models by retrieving data from Wikipedia.
worktool
【企业微信】企业微信机器人 聊天机器人、自动加好友、自动拉群、自动群发机器人 免Root零封号 集成ChatGPT
faster-whisper
Faster Whisper transcription with CTranslate2