Search Results for "tiny-core-plus"

KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable that builds off llama.cpp and adds many additional powerful features.

Transcrib — десктопное Electron-приложение для перевода аудио и видео в текстовый формат. Программа работает на базе мощной модели Whisper от OpenAI и Node.js. «Из коробки» в дистрибутив уже вшиты две легкие модели — `tiny` и `base`. Остальные (`small`, `medium`, `large`) можно скачать и обновлять прямо внутри приложения по мере необходимости. Логика простая: чем сложнее модель, тем выше качество текста, но тем дольше идет обработка.

LegacyInsight is an AI-powered reverse engineering platform that transforms legacy software systems into comprehensible business logic. Using cutting-edge GenAI, it analyzes legacy and extracts core operations, business rules, and data transformations—all translated into natural language. LegacyInsight supports enterprise-grade systems built on Java, COBOL, NET and other legacy stacks, helping organizations reclaim understanding of business-critical code.

Implementation of Text Generation models. textgen implements a variety of text generation models, including UDA, GPT2, Seq2Seq, BART, T5, SongNet and other models, out of the box. UDA, non-core word replacement. EDA, simple data augmentation technique: similar words, synonym replacement, random word insertion, deletion, replacement. This project refers to Google's UDA (non-core word replacement) algorithm and EDA algorithm, based on TF-IDF to replace some unimportant words in sentences with synonyms, random word insertion, deletion, replacement, etc. method, generating new text and implementing text augmentation This project realizes the back translation function based on Baidu translation API, first translate Chinese sentences into English, and then translate English into new Chinese. ...

Hebrew text generation models based on EleutherAI's gpt-neo. Each was trained on a TPUv3-8 which was made available to me via the TPU Research Cloud Program. The Open Super-large Crawled ALMAnaCH coRpus is a huge multilingual corpus obtained by language classification and filtering of the Common Crawl corpus using the goclassy architecture.