Bunch of notebooks for pre-training custom Saiga-like LLM
☆12Feb 9, 2024Updated 2 years ago
Alternatives and similar repositories for saiga-custom
Users that are interested in saiga-custom are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Paint2code - a lightweight tool designed to transform your hand-drawn sketches into functional HTML code.☆16May 30, 2024Updated 2 years ago
- комплексное руководство по машинному обучению (ML) и обработке естественного языка (NLP). Этот проект предназначен для студентов техничес…☆31Aug 24, 2024Updated last year
- ☆17Oct 9, 2023Updated 2 years ago
- Question-answer bot, using Retrieval-Augmented Generation method.☆17Nov 8, 2023Updated 2 years ago
- This project is concerned with my participating in the RuNNE competition https://github.com/dialogue-evaluation/RuNNE☆13Jun 28, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆47Mar 20, 2025Updated last year
- практические занятия, реальные проекты и техники разработки☆16Mar 23, 2025Updated last year
- Language modeling and instruction tuning for Russian☆466Aug 20, 2024Updated last year
- AI Chatbots in Neovim without needing API keys☆16Sep 13, 2025Updated 10 months ago
- Проект языковой модели для проведения морфемного анализа, сегментации и токенизации слов русского языка.☆18Jan 10, 2025Updated last year
- Простой нормализатор текстов перед синтезом речи☆49May 13, 2024Updated 2 years ago
- ☆22Oct 30, 2024Updated last year
- The educational course dedicated to FOSS culture and toolchain☆20Mar 24, 2026Updated 4 months ago
- Make downloading scientific data much easier☆13Mar 3, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Repo for hosting tutorial code associated with the "AssemblyAI and Python in 5 Minutes" blog by AssemblyAI☆12Jul 29, 2023Updated 3 years ago
- Это прототип решения типа Agentic RAG (Retrieval-Augmented Generation) с данными из Jira, Confluence и Git.☆11Dec 4, 2024Updated last year
- Source code of the paper: RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering [F…☆68May 28, 2024Updated 2 years ago
- Materials that help you to navigate in the world of NLP☆21Sep 10, 2025Updated 11 months ago
- Applying the DQN-Agent from keras-rl to Starcraft 2 Learning Environment and modding it to to use the Rainbow-DQN algorithms.☆11Jul 3, 2019Updated 7 years ago
- Visual Odometry using a Recurrent Convolutional Neural Network in PyTorch☆13Jul 6, 2022Updated 4 years ago
- Smart assistant in Telegram bot format for transcribing online meetings☆15Apr 1, 2024Updated 2 years ago
- ☆25May 27, 2024Updated 2 years ago
- A minimal, strictly structured Python project template☆15Apr 26, 2023Updated 3 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆16Feb 18, 2023Updated 3 years ago
- Multilingual RAG benchmark.☆11Nov 22, 2024Updated last year
- ☆11Sep 5, 2022Updated 3 years ago
- Implementation of transformer for optical character recognition of russian words☆14Nov 25, 2023Updated 2 years ago
- High-performance profanity filter☆16Mar 3, 2026Updated 5 months ago
- Fork of RecurrentGPT with modifications☆10Sep 18, 2024Updated last year
- A lightweight module to generate colorful ascii art from images☆10Feb 22, 2024Updated 2 years ago
- d3-based SU/SEGY picker☆11Jun 8, 2018Updated 8 years ago
- ☆18Oct 8, 2025Updated 10 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Music generator utilizing a Bidirectional LSTM architecture in Keras.☆21Apr 8, 2018Updated 8 years ago
- memo☆13Dec 22, 2022Updated 3 years ago
- Код для файнтюна LM (rugpt, LLaMa, FRED T5) средствами transformers + deepspeed + LoRa☆14May 22, 2023Updated 3 years ago
- FastAPI backend enterprise template☆21Mar 29, 2025Updated last year
- ☆18Nov 2, 2018Updated 7 years ago
- Russian text segmenter and tokenizer☆18Mar 2, 2021Updated 5 years ago
- 📚 A small collection of Russian literature 📚☆15Dec 9, 2022Updated 3 years ago