BlackSamorez

tensor_parallel

Automatically split your PyTorch models on multiple GPUs for training & inference

mipt_lab

MIPT physics lab reports

ebanko

NLP based telegram bot

BlackSamorez

gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

CV22

My CV

nlp_course

YSDA course in Natural Language Processing

quaified_impalas

NMA 2021 group project

raytracer22

2022 iteration of my annual raytracer project.

toohak-quiz

accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

bitsandbytes

8-bit CUDA functions for PyTorch

blacksamorez.github.io

efficient-dl-systems

Efficient Deep Learning Systems course (HSE, YSDA)

raytracer21

An almost pure c++ raytracer programm

GRAPE

GRAPE approximations for NMR

JamDrummer

langchain

🦜🔗 Build context-aware reasoning applications

marina

Experiments for the paper MARINA accepted into ICML-2021

metaseq

Repo for external large-scale work

MiniFL

P-tuning

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

peft-rosa

A fork of the PEFT library, supporting Robust Adaptation (RoSA)

PFL-DocVQA-Competition

https://benchmarks.elsa-ai.eu/?ch=2&com=introduction

QUIK

Repository for the QUIK project, enabling the use of 4bit kernels for generative inference

quip-sharp

TensorRT-LLM

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 efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

YaLM-100B

Pretrained language model with 100B parameters