Awesome GitHub RepositoriesInteractive Model Interfaces

ChatGLM-6B is an open-source bilingual large language model designed for natural dialogue and text generation in both English and Chinese. It is structured as a dialogue model capable of tasks such as role-playing and information extraction. The project provides implementations for quantized language models, using low-precision weights to reduce GPU memory requirements for local inference. It also supports parameter-efficient fine-tuning, allowing model behavior to be optimized for specific tasks without requiring full retraining. The model includes capabilities for local execution on GPUs a

Dive into LLMs is a framework designed for fine-tuning large language models and constructing modular machine learning pipelines. It provides a structured environment for adjusting pre-trained models on custom datasets while optimizing computational efficiency and training time. The project distinguishes itself by offering an interactive web interface that allows for the deployment and publication of trained models directly to a browser. This enables users to test and interact with model results through a standardized web-based environment. The platform supports the creation of flexible work

This project is a comprehensive toolkit for adapting large language models to the Chinese language, providing a specialized framework for fine-tuning, inference, and local deployment. It serves as a coordinated suite for language-specific adaptation, including tools for expanding tokenizers and implementing retrieval-augmented generation. The project distinguishes itself through a complete pipeline for model adaptation, featuring multilingual tokenizer expansion and a fine-tuning framework that supports instruction-based supervised training and adapter merging. It also includes a dedicated de

ChatGLM3 is a comprehensive framework for deploying, fine-tuning, and serving large language models. It functions as a high-performance inference engine designed to support conversational AI, enabling developers to build interactive agents capable of multi-turn dialogue, autonomous code execution, and structured tool invocation. The project distinguishes itself through its focus on hardware-agnostic deployment and resource optimization. It supports distributed model parallelism across multiple graphics cards, paged key-value caching for concurrent request processing, and weight quantization t

LitGPT is a training and deployment framework for large language models, providing a suite of tools for pretraining, finetuning, quantizing, evaluating, and serving models within a production environment. It includes a dedicated training pipeline for adapting pretrained models to specific tasks, a quantization tool for reducing weight precision, and an inference server for hosting models via web interfaces. The framework supports high-performance model development through custom architecture implementation and the use of predefined recipes to standardize pretraining and finetuning. It enables

Qwen3-TTS is a large language model text-to-speech engine designed to convert written text into natural-sounding human speech. It functions as an audio tokenizer and a generative system for speech synthesis. The project features a promptable voice designer for creating synthetic vocal personas based on natural language descriptions. It also includes a zero-shot voice cloning tool that mimics a target speaker using a short reference audio clip and a transcript. The system provides a framework for speech model fine-tuning to improve speaker likeness and quality through supervised training. Add

ParlAI is a conversational AI research framework designed for training, evaluating, and sharing dialogue models using a unified interface for datasets and agents. It functions as a PyTorch-based training platform and a dialogue data collection system, providing a centralized model zoo for the distribution of versioned pretrained agents. The project distinguishes itself through a knowledge-grounded retrieval system that combines dense and sparse indexing to ground responses in external information. It also provides a comprehensive infrastructure for gathering human-AI interaction data via inte

This project is a comprehensive Node.js software development kit designed for integrating large language models into applications. It serves as a foundational client for interacting with REST and WebSocket services, enabling developers to implement chat functionality, multimodal content generation, and autonomous agent orchestration. The library provides a structured framework for defining executable tools and enforcing JSON schemas, ensuring that model outputs remain programmatically compatible with downstream systems. The SDK distinguishes itself through its robust request orchestration and

Moshi is a real-time voice foundation model and speech-to-speech framework designed for bidirectional, low-latency conversations. It functions as a full-duplex voice interface that processes audio and text concurrently in a single stream, enabling natural human-machine dialogue without sequential processing delays. The system utilizes a neural audio codec to compress high-fidelity audio into low-bitrate tokens for efficient transmission. To manage complex responses and reasoning, it employs internal monologue modeling, which generates a hidden stream of thought tokens alongside audible speech

This project is a web-based user interface for interacting with large language models via API keys. It functions as an OpenAI API client and a general LLM web chat interface, allowing users to send prompts and receive responses through a private web portal. The application features a security layer with password-based access control to restrict public usage. It supports custom request routing and proxy configurations to bypass network restrictions, and it is available as a progressive web app for native-like installation on mobile devices. The interface includes rich text rendering for Markd

This project provides a Chinese large language model based on the LLaMA architecture. It is an instruction-tuned model optimized for natural language processing and multi-turn conversations in Chinese. The system includes a framework for parameter-efficient fine-tuning using low-rank adaptation and quantization to reduce memory requirements. It also implements retrieval augmented generation for local document question answering and supports long-context processing for sequences up to 64K tokens. The project covers a broad set of capabilities including supervised instruction tuning, reinforce

llm-zoomcamp is a comprehensive educational program and course for building real-life AI systems using large language models. It serves as a structured curriculum and implementation guide for developing AI applications and retrieval techniques. The project provides instructional material on building retrieval augmented generation pipelines to ground model responses in custom knowledge bases. It includes training on vector database implementation, semantic search, and the use of function calling to create autonomous agentic workflows. The curriculum covers a broad range of system development

Acest proiect este o serie de tutoriale de deep learning și un curriculum educațional conceput pentru a preda fundamentele PyTorch. Servește ca ghid de antrenament structurat pentru stăpânirea arhitecturii rețelelor neuronale, diferențierea automată și utilizarea tensorilor și a grafurilor de calcul dinamice. Curriculum-ul se concentrează pe implementări practice, ghidând în mod specific dezvoltarea sistemelor de recomandare, a modelelor de publicitate și a rețelelor de interese pentru a prezice preferințele utilizatorilor. Oferă, de asemenea, conținut instrucțional pentru prognoza seriilor temporale și procesarea datelor secvențiale. Materialul acoperă o gamă largă de capabilități de deep learning, inclusiv construcția modelelor pentru clasificarea imaginilor și a textului, precum și a datelor structurate. Încorporează fluxuri de lucru pentru accelerarea GPU, vizualizarea metricilor de antrenament și crearea de interfețe bazate pe web pentru a testa predicțiile modelului. Proiectul este livrat sub formă de colecție de Jupyter Notebooks.

Acest proiect este un curriculum educațional de machine learning și o platformă de învățare livrată prin Jupyter Notebooks interactive. Servește drept ghid cuprinzător pentru stăpânirea toolkit-ului de data science Python, oferind tutoriale structurate pentru calcul numeric, manipularea datelor tabelare și vizualizarea statistică. Curriculum-ul include ghiduri specifice de implementare pentru Scikit-Learn și un curs practic despre TensorFlow pentru construirea, antrenarea și deployment-ul rețelelor neuronale și a modelelor de computer vision. Acoperă procesul end-to-end de construire a modelelor predictive, de la formularea inițială a problemei și categorizarea sarcinilor până la deployment-ul modelelor prin interfețe web interactive. Proiectul acoperă o suprafață largă de capabilități, inclusiv calcul numeric cu array-uri multidimensionale, analiză exploratorie a datelor și rutine de preprocesare a datelor. Oferă fluxuri de lucru detaliate pentru învățarea supervizată și nesupervizată, pipeline-uri de machine learning automatizat, optimizarea hiperparametrilor și evaluarea modelelor folosind metrici de clasificare și cross-validation. Conținutul educațional este organizat ca o serie de notebook-uri care intercalează codul Python cu explicații narative pentru a documenta fluxurile de lucru în data science.

freegpt-webui este o interfață web self-hosted pentru interacțiunea cu modele de limbaj mari. Oferă un frontend bazat pe chat, conceput pentru comunicarea cu modelele GPT 3.5 și GPT 4. Aplicația permite chat-ul fără cheie API, permițând utilizatorilor să acceseze AI-ul conversațional pentru generarea de text și recuperarea informațiilor fără a furniza sau gestiona chei de autentificare personale. Sistemul gestionează integrarea modelului printr-un gateway de tip reverse-proxy și suportă procesarea asincronă a fluxurilor pentru generarea de text în timp real. Preferințele utilizatorului și istoricul conversațiilor sunt persistate prin stocarea de sesiune client-side.

InfiniteTalk is an open-source system for generating talking head videos driven by audio input. It synthesizes realistic lip movements, head poses, and facial expressions synchronized to a spoken audio track, using either a single still image or a small set of reference video frames as the visual source. The system can produce videos of arbitrary length while maintaining temporal coherence, and it supports animating multiple subjects in a single scene. A key differentiator is the ability to coordinate multiple talking subjects through a structured JSON description, giving each independent lip

Ramalama is a containerized runtime and management tool for large language models. It functions as an OCI AI model manager and registry client, allowing users to package, distribute, and execute AI models as standardized container images. The project differentiates itself by using OCI-compliant distribution for models and retrieval augmented generation assets, enabling the packaging of vector databases into immutable container images. It features hardware-aware image selection that automatically detects GPU or CPU capabilities to pull the most optimized image for the host environment. The sy

Acest proiect este o interfață web self-hosted și o aplicație desktop concepută pentru interacțiunea cu modelele de limbaj. Oferă o platformă privată pentru gestionarea sesiunilor de conversație, permițând utilizatorilor să se conecteze la servicii AI externe, menținând în același timp controlul asupra istoricului interacțiunilor și a setărilor de configurare. Aplicația se distinge prin oferirea unei interfețe unificate care suportă input-uri și output-uri multimodale, inclusiv procesarea interacțiunii vocale și crearea de imagini generative. Securizează credențialele sensibile prin rutarea cererilor printr-un proxy backend și asigură confidențialitatea datelor prin stocarea jurnalelor de conversație și a istoricului sesiunilor local pe dispozitivul utilizatorului. Dincolo de funcționalitatea de chat de bază, platforma include instrumente pentru streaming-ul în timp real al răspunsurilor, gestionarea istoricului conversațiilor și capacitatea de a exporta jurnale pentru arhivare. Software-ul este împachetat ca un executabil desktop standalone, permițând utilizatorilor să acceseze aceste servicii AI independent de un browser web.

This project provides a web-based integrated development environment for defining, documenting, and simulating software interface specifications. It serves as a browser-based modeling tool that enables teams to create structured API contracts using the RAML modeling language. The environment distinguishes itself through its modular design, which allows the modeling interface to be embedded directly into existing web applications and developer portals. It supports a plugin architecture that enables the integration of custom persistence layers and metadata handlers, allowing teams to attach pro