alexanderpanchenko

LLM101n

LLM101n: Let's build a Storyteller

TaxoLLaMA

[ACL 2024] TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Sematic Tasks

gigachain

⚡ Фреймворк для создания комплексных приложений с LLM ⚡

MERA

MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundamental models.

ru-prompts

ctrl

Conditional Transformer Language Model for Controllable Generation

OFA

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

PROTES

Gradient-free optimization method for the multidimensional arrays and discretized multivariate functions based on the tensor train (TT) format.

fpcross

Solver in the low-rank tensor train format with cross approximation approach for the multidimensional Fokker-Planck equation

ttopt

Gradient-free optimization method for multivariable functions based on the low rank tensor train (TT) format and maximal-volume principle.

teneva

A framework based on the tensor train decomposition for working with multivariate functions and multidimensional arrays

GENA_LM

GENA-LM is a transformer masked language model trained on human DNA sequence.

pogema

POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF settings.

OmniFusion

OmniFusion — a multimodal model to communicate using text and images

nntile

A neural network training framework within a task-based parallel programming paradigm

lm-polygraph

PromptKG

PromptKG Family: a Gallery of Prompt Learning & KG-related research works, toolkits, and paper-list.

al_toolbox

Active learning

Awesome-LLM-KG

Awesome papers about unifying LLMs and KGs

RuMedBench

https://arxiv.org/abs/2201.06499

ru-clip

CLIP implementation for Russian language

LightAutoML

Fast and customizable framework for automatic ML model creation (AutoML)

nablaDFT

nablaDFT: Large-Scale Conformational Energy and Hamiltonian Prediction benchmark and dataset

Kandinsky-2

Kandinsky 2 — multilingual text2image latent diffusion model

OpenHGNN

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL.

HAN

Heterogeneous Graph Neural Network

Graph_Transformer_Networks

Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper)

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

chatgpt_telegram_bot

💬 Telegram bot with ChatGPT, Python-based, using OpenAI's API.

paradetox

Data and info for the paper "ParaDetox: Text Detoxification with Parallel Data"