AlexKay28

yandex-tank

Load and performance benchmark tool

freshqa

Data and code for FreshLLMs (https://arxiv.org/abs/2310.03214)

large-qa-datasets

A collection of large question answering datasets

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

HaluEval

This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.

DePYsible

An implementation of Defeasible Logic in Python

barfi

Python Flow Based Programming environment that provides a graphical programming environment.

trl

Train transformer language models with reinforcement learning.

open_llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

yadisk

Библиотека-клиент REST API Яндекс.Диска для Python / Yandex.Disk REST API client library for Python

awesome-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

efficient-dl-systems

Efficient Deep Learning Systems course materials (HSE, YSDA)

extension-cpp

C++ extensions in PyTorch

quality

ChatRWKV

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

CTCDecoder

Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

SpikeGPT

Implementation of "SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks"

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

llama

Inference code for Llama models

python-telegram-bot

We have made you a wrapper you can't refuse

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Visual-Attention-Model

gpustat

📊 A simple command-line utility for querying and monitoring GPU status

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

mgpt

Multilingual Generative Pretrained Model

ml-fastapi-docker-heroku

Deploy ML models with FastAPI, Docker, and Heroku

deep_learning_curriculum

Language model alignment-focused deep learning curriculum

quaterion

Blazing fast framework for fine-tuning similarity learning models