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

Brand new TTS solution

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

Vector (and Scalar) Quantization, in Pytorch

A generative speech model for daily dialogue.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Python下shuffle几百G文件

DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models

Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

[CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

The official Python library for the OpenAI API

DeepSeek Coder: Let the Code Write Itself

Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" (ICLR 2024)

[ACL 2023] Learning Multi-step Reasoning by Solving Arithmetic Tasks. https://arxiv.org/abs/2306.01707

A series of large language models developed by Baichuan Intelligent Technology

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Neural Networks and the Chomsky Hierarchy

Leveraging training data for few-shot prompting

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…

[ACL2023 Area Chair Award] Official repo for the paper "Tell2Design: A Dataset for Language-Guided Floor Plan Generation".

[ACL 2023] Contextual Distortion Reveals Constituency: Mask Language Models are Implicit Parsers.

Official homepage for Tab-CoT: Zero-shot Tabular Chain of Thought (Findings of ACL 2023)

Inference code for Llama models

One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting