Stars
Arch is an intelligent prompt gateway. Engineered with (fast) LLMs for the secure handling, robust observability, and seamless integration of prompts with APIs - all outside business logic. Built b…
Simple text to phones converter for multiple languages
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
A comprehensive guide to LLM evaluation methods designed to assist in identifying the most suitable evaluation techniques for various use cases, promote the adoption of best practices in LLM assess…
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
OpenChat: Advancing Open-source Language Models with Imperfect Data
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
The PyTorch-based audio source separation toolkit for researchers
A very simple framework for state-of-the-art Natural Language Processing (NLP)
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Whisper finetuned on VinBigdata-VLSP2020-100h + KenLM
Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.
Instruct-tune LLaMA on consumer hardware
Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch
Score-based Generative Models (Diffusion Models) for Speech Enhancement and Dereverberation
Awesome-LLM: a curated list of Large Language Model
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
QLoRA: Efficient Finetuning of Quantized LLMs
Ongoing research training transformer language models at scale, including: BERT & GPT-2
PyTorch Implementation of FastDiff (IJCAI'22)
Home for cuQuantum Python & NVIDIA cuQuantum SDK C++ samples
tvanh512 / humanrf
Forked from synthesiaresearch/humanrfOfficial code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"
A collection of resources and papers on Diffusion Models
The Natural Language Decathlon: A Multitask Challenge for NLP
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Universal LLM Deployment Engine with ML Compilation