Pinned Repositories
BlackSamorez
CV22
My CV
ebanko
NLP based telegram bot
executorch
On-device AI across mobile, embedded and edge for PyTorch
gptq
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
mipt_lab
MIPT physics lab reports
raytracer21
An almost pure c++ raytracer programm
raytracer22
2022 iteration of my annual raytracer project.
tensor_parallel
Automatically split your PyTorch models on multiple GPUs for training & inference
AQLM
Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852
BlackSamorez's Repositories
BlackSamorez/tensor_parallel
Automatically split your PyTorch models on multiple GPUs for training & inference
BlackSamorez/mipt_lab
MIPT physics lab reports
BlackSamorez/ebanko
NLP based telegram bot
BlackSamorez/BlackSamorez
BlackSamorez/gptq
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
BlackSamorez/CV22
My CV
BlackSamorez/executorch
On-device AI across mobile, embedded and edge for PyTorch
BlackSamorez/nlp_course
YSDA course in Natural Language Processing
BlackSamorez/raytracer22
2022 iteration of my annual raytracer project.
BlackSamorez/toohak-quiz
BlackSamorez/accelerate
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
BlackSamorez/bitsandbytes
8-bit CUDA functions for PyTorch
BlackSamorez/blacksamorez.github.io
BlackSamorez/efficient-dl-systems
Efficient Deep Learning Systems course (HSE, YSDA)
BlackSamorez/flute
Fast Matrix Multiplications for Lookup Table-Quantized LLMs
BlackSamorez/GRAPE
GRAPE approximations for NMR
BlackSamorez/JamDrummer
BlackSamorez/langchain
🦜🔗 Build context-aware reasoning applications
BlackSamorez/metaseq
Repo for external large-scale work
BlackSamorez/MiniFL
BlackSamorez/mipt_thesis_code
BlackSamorez/P-tuning
A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.
BlackSamorez/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
BlackSamorez/peft-rosa
A fork of the PEFT library, supporting Robust Adaptation (RoSA)
BlackSamorez/PFL-DocVQA-Competition
https://benchmarks.elsa-ai.eu/?ch=2&com=introduction
BlackSamorez/QUIK
Repository for the QUIK project, enabling the use of 4bit kernels for generative inference
BlackSamorez/quip-sharp
BlackSamorez/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.
BlackSamorez/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
BlackSamorez/YaLM-100B
Pretrained language model with 100B parameters