MARS5 speech model (TTS) from CAMB.AI

A unified tokenization tool for Images, Chinese and English.

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Video+code lecture on building nanoGPT from scratch

A Native-PyTorch Library for LLM Fine-tuning

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

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

a state-of-the-art-level open visual language model | 多模态预训练模型

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

This reference can be used with any existing OpenAI integrated apps to run with TRT-LLM inference locally on GeForce GPU on Windows instead of cloud.

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

Train transformer language models with reinforcement learning.

Python bindings for llama.cpp

Voice data <= 10 mins can also be used to train a good VC model!

Tools for merging pretrained large language models.

Finetuning VITS Efficiently

A fast inference library for running LLMs locally on modern consumer-class GPUs

Official Implementation of StyleTTS

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

Port of Facebook's LLaMA model in C/C++

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Official Implementation of StyleTTS-VC