Nulooper's repositories
Awesome-Chinese-LLM
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
augmentoolkit
Convert Compute And Books Into Instruct-Tuning Datasets
AutoGPT
An experimental open-source attempt to make GPT-4 fully autonomous.
awesome-english-ebooks
经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新
Awesome-LLM-Eval
Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, learderboard, papers, docs and models, mainly for Evaluation on LLMs.
consistencydecoder
Consistency Distilled Diff VAE
discord.py
An API wrapper for Discord written in Python.
facechain
FaceChain is a deep-learning toolchain for generating your Digital-Twin.
faster-whisper
Faster Whisper transcription with CTranslate2
FireAct
FireAct: Toward Language Agent Fine-tuning
Fooocus
Focus on prompting and generating
FreeU
FreeU: Free Lunch in Diffusion U-Net
latent-consistency-model
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
LLaMA-Efficient-Tuning
Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan)
llm-books
利用LLM构建应用实践笔记
manga-image-translator
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/
mergekit
Tools for merging pretrained large language models.
Meta-CoT
Meta-CoT: Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models
mistral-src
Reference implementation of Mistral AI 7B v0.1 model.
Monogatari
Monogatari is a simple web visual novel engine, created to bring Visual Novels to the web.
promptflow
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
seamless_communication
Foundational Models for State-of-the-Art Speech and Text Translation
slidev
Presentation Slides for Developers
spleeter
Deezer source separation library including pretrained models.
trainable-agents
Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
whisperX
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)