Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash attention v2.

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

SALMONN: Speech Audio Language Music Open Neural Network

Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration

🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.

Tools for merging pretrained large language models.

Inference Llama 2 in one file of pure C

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Support Continual pre-training & Instruction Tuning forked from llama-recipes

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

YaRN: Efficient Context Window Extension of Large Language Models

日本語LLMまとめ - Overview of Japanese LLMs

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

DSIR large-scale data selection framework for language model training

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

Learn NLP Tutorials with HuggingFace Transformers

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

SoftVC VITS Singing Voice Conversion

Create RP training data from a VN, using GPT-4

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

Let ChatGPT teach your own chatbot in hours with a single GPU!

We propose the Text-to-CQL task and provide the dataset.

alpacaデータセットを日本語化したものです