Awesome GitHub RepositoriesEncoder-Decoder Model Integrations

This repository provides a collection of reference implementations and code examples for training and deploying machine learning models using the MLX framework. It serves as a practical guide for executing distributed training, fine-tuning large language models, converting model weights, and implementing multimodal generative workflows. The project distinguishes itself through specialized examples for local hardware execution, featuring weight quantization to reduce memory usage and low-rank adaptation for parameter-efficient fine-tuning. It also includes scripts for transforming external mod

This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of large language models. It provides a guided progression through the theory, architecture, training, and deployment of these models. The curriculum includes specialized guides on transformer architecture, model training tutorials, and frameworks for designing autonomous agents. It also provides dedicated resources for studying model safety and ethics. The material covers a wide range of technical capabilities, including distributed training strategies, parameter-efficient fine-tu

The official PyTorch implementation of Google's Gemma models

This is a collection of educational Jupyter Notebook tutorials that teach sequence-to-sequence modeling using PyTorch and TorchText, focused on neural machine translation. The project provides hands-on guides for building and training encoder-decoder architectures with recurrent neural networks like LSTM and GRU, implementing attention mechanisms that allow the decoder to focus on relevant input tokens during sequence generation. The tutorials cover the full pipeline of machine translation, from tokenizing multilingual text using language-specific tokenizers to training multi-layer encoder-de

Qwen2.5-Omni 是一款全渠道多模态大语言模型，旨在处理和生成跨文本、音频、视觉和视频的内容。它作为实时语音 AI 运行，利用端到端架构来维持低延迟响应的同步语音对话。 该项目通过量化边缘模型强调效率，允许在移动硬件和资源受限的设备上进行本地推理。它采用 4 位权重量化、基于 CPU 的进程卸载和按需权重加载，以降低 GPU 内存需求。 该系统集成了专门的编码器来分析多模态数据流，并具有用于实时语音生成的流式解码器。它还包括语音定制功能，以修改音频输出的音调和性别特征。