Awesome GitHub RepositoriesLanguage Modeling Data Loading

nlp.js is a JavaScript natural language processing library and development framework used to build natural language understanding engines. It provides a toolkit for creating local machine learning models for intent classification and acts as a multilingual text processor that detects languages and normalizes text across various dialects. The framework distinguishes itself by supporting local execution on both servers and mobile devices, enabling chatbot functionality without an internet connection. It features a specialized system for conversational slot filling to collect mandatory informati

pycorrector is an open-source toolkit for detecting and correcting spelling and grammar errors in Chinese text. It combines multiple correction approaches, including rule-based methods using Kenlm n-gram language models and confusion sets, as well as deep learning correctors built on BERT, GPT, and T5 models. The toolkit also provides a command-line interface for batch processing Chinese text files with configurable detection and output options. The project distinguishes itself by offering a range of correction strategies that can be mixed and matched. Rule-based correction uses character-lev

This project is a neural machine translation system used to build models that automatically translate text from one language to another. It utilizes sequence-to-sequence modeling to transform variable-length input sequences into corresponding output sequences. The system implements bidirectional recurrent neural network encoding and attention mechanisms to capture contextual information and focus on specific parts of the source text during translation. To manage training and inference, it employs separate computational graphs and supports distributing model layers across multiple GPU devices.

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip

Acest proiect este un program educațional cuprinzător și un framework de deep learning conceput pentru a preda deep learning practic folosind PyTorch prin notebook-uri și exemple de cod. Servește drept bibliotecă de nivel înalt pentru construirea, antrenarea și implementarea rețelelor neuronale, acționând ca un orchestrator de antrenare a modelelor care coordonează modelele PyTorch, optimizatoarele și funcțiile de loss. Proiectul oferă toolkit-uri specializate pentru computer vision, procesarea limbajului natural și preprocesarea datelor tabelare. Se distinge prin controale avansate de antrenare, cum ar fi rate de învățare discriminative, un sistem de callback bidirecțional pentru personalizarea logicii de antrenare și o abstractizare de nivel înalt a learner-ului care automatizează plasarea pe dispozitiv și buclele de antrenare. Framework-ul acoperă o suprafață largă de capabilități, inclusiv construcția automată a pipeline-urilor de date, analiza arhitecturii modelelor și evaluarea performanței în sarcini de clasificare, regresie și segmentare. Include, de asemenea, utilitare pentru antrenarea distribuită pe mai multe GPU-uri, antrenarea cu precizie mixtă pentru optimizarea memoriei și suport specializat pentru date de imagistică medicală. Proiectul este livrat sub formă de serie de Jupyter Notebooks.

This is a structured deep learning curriculum for programmers, delivered as a collection of Jupyter notebooks. It teaches the fundamentals of training neural networks for computer vision, natural language processing, tabular data analysis, and collaborative filtering using PyTorch and the fastai library. The course is designed to be hands-on, guiding learners from building a training loop from scratch to fine-tuning pretrained models for a variety of practical tasks. The curriculum distinguishes itself by covering the full lifecycle of a deep learning project, from data preparation and augmen