Alexander Abramov's repositories
albert
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
awesome-RLHF
A curated list of reinforcement learning with human feedback resources (continually updated)
facebook-hateful-memes
Facebook hateful memes challenge using multi-modal learning. More info about it here: https://ai.facebook.com/blog/hateful-memes-challenge-and-data-set
FNet-TensorFlow-PyTorch
TensorFlow & PyTorch implementation of the paper "FNet: Mixing Tokens with Fourier Transforms".
FRED-T5-Finetuning
Скрипт для файнтюна FRED-T5
HateXplain
Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.
JAX-in-Action
Notebooks for the "JAX in Action" book
LLaMA2
This repository contains an implementation of the LLaMA 2 (Large Language Model Meta AI) model, a Generative Pretrained Transformer (GPT) variant. The implementation focuses on the model architecture and the inference process. The code is restructured and heavily commented to facilitate easy understanding of the key parts of the architecture.
LM-finetune
Код для файнтюна LM (rugpt, LLaMa, FRED T5) средствами transformers + deepspeed + LoRa
lm-human-preferences--tf
Code for the paper Fine-Tuning Language Models from Human Preferences
Machine-Learning-with-Python
Practice and tutorial-style notebooks covering wide variety of machine learning techniques
MergeLM
Codebase for Merging Language Models
mesh
Mesh TensorFlow: Model Parallelism Made Easier
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
models
Models and examples built with TensorFlow
Prompt-Engineering-Guide
:octopus: Guides, papers, lecture, and resources for prompt engineering
rulm
Language modeling for Russian
ruTS
Библиотека для извлечения статистик из текстов на русском языке.
SafeNLP
Safety Score for Pre-Trained Language Models
tensor-house
A collection of reference machine learning and optimization models for enterprise operations: marketing, pricing, supply chain
TF_JAX_tutorials
All about the fundamental blocks of TF and JAX!
trl
Train transformer language models with reinforcement learning.
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.