vahbuna

magic-wormhole

get things from one computer to another, safely

dadaptation

D-Adaptation for SGD, Adam and AdaGrad

LLM-Training-Puzzles

What would you do with 1000 H100s...

llama_index

LlamaIndex is a data framework for your LLM applications

self-rag

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

synthesizer

A multi-purpose LLM framework for RAG and data creation.

felm

Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models"

giskard

🐢 Open-Source Evaluation & Testing for LLMs and ML models

webnn

🧠 Web Neural Network API

vall-e

An unofficial PyTorch implementation of the audio LM VALL-E

pflowtts_pytorch

Unofficial implementation of NVIDIA P-Flow TTS paper

StyleTTS2

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

EmotiVoice

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

pheme

tortoise-tts

A multi-voice TTS system trained with an emphasis on quality

IMS-Toucan

Multilingual and Controllable Text-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart.

MambaTransformer

Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling

YourTTS

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

cutlass

CUDA Templates for Linear Algebra Subroutines

whos_filtered

openlogprobs

Extract full next-token probabilities via language model APIs

LLaMA-Pro

[ACL 2024] Progressive LLaMA with Block Expansion.

profiling-cuda-in-torch

TinyLlama

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

transformers.js

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

gomin

GOMIN; Gaudio Open Mel-spectrogram Inversion Network

wanda

A simple and effective LLM pruning approach.

mpt-30B-inference

Run inference on MPT-30B using CPU

PoSE

Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)

StableLM

StableLM: Stability AI Language Models