19 مستودعات
Web-based interfaces specifically designed for testing and interacting with machine learning model outputs.
Distinct from Web Interfaces: Distinct from general web interfaces: focuses on model-specific interaction and testing environments.
Explore 19 awesome GitHub repositories matching web development · Interactive Model Interfaces. Refine with filters or upvote what's useful.
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
Provides web-based interfaces specifically designed for testing and interacting with model outputs in real-time.
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
Provides a browser-based platform for deploying and testing trained machine learning models.
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
Provides a graphical interactive interface for testing and engaging with machine learning model outputs.
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
Provides web-based graphical user interfaces for real-time model interaction and demonstration of capabilities.
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
Ships a chat interface for manually verifying model responses and extracting embeddings for analysis.
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
Provides a web-based interface for interacting with and testing speech model outputs.
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
Provides a live web-based interface to send messages to trained models and inspect generated responses and metadata.
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
Provides an interface for interacting with AI models, including chat and multimodal content generation.
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
Includes a local web interface for interacting with the voice foundation model via a browser.
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
Implements a private web interface specifically for interacting with OpenAI models using a personal API key.
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
Provides a web-based graphical user interface for conducting multi-turn conversations with the model.
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
Guides the deployment of interactive interfaces that allow users to interact with the developed language model systems.
هذا المشروع عبارة عن سلسلة دروس للتعلم العميق ومنهج تعليمي مصمم لتدريس أساسيات PyTorch. يعمل كدليل تدريب مهيكل لإتقان بنية الشبكة العصبية، والتمايز التلقائي، واستخدام الموترات ورسوم الحساب الديناميكية. يركز المنهج على التطبيقات العملية، وتحديداً توجيه تطوير أنظمة التوصية، ونماذج الإعلانات، وشبكات الاهتمام للتنبؤ بتفضيلات المستخدم. كما يوفر محتوى تعليمياً للتنبؤ بالسلاسل الزمنية ومعالجة البيانات المتسلسلة. تغطي المادة مجموعة واسعة من قدرات التعلم العميق، بما في ذلك بناء نماذج لتصنيف الصور والنصوص بالإضافة إلى البيانات المهيكلة. تدمج سير عمل لتسريع GPU، وتصور مقاييس التدريب، وإنشاء واجهات قائمة على الويب لاختبار تنبؤات النموذج. يتم تقديم المشروع كمجموعة من دفاتر Jupyter.
Includes a guide for creating interactive web interfaces to test model inputs and view predictions.
هذا المشروع عبارة عن منهج تعليمي للتعلم الآلي ومنصة تعليمية يتم تقديمها من خلال دفاتر Jupyter التفاعلية. يعمل كدليل شامل لإتقان مجموعة أدوات علوم البيانات في Python، ويوفر دروساً منظمة للحوسبة العددية، ومعالجة البيانات الجدولية، والتصور الإحصائي. يتضمن المنهج أدلة تنفيذ محددة لـ Scikit-Learn ودورة عملية حول TensorFlow لبناء وتدريب ونشر الشبكات العصبية ونماذج رؤية الحاسب. ويغطي العملية الشاملة لبناء النماذج التنبؤية، من صياغة المشكلة الأولية وتصنيف المهام إلى نشر النماذج عبر واجهات الويب التفاعلية. يغطي المشروع سطح إمكانات واسع بما في ذلك الحوسبة العددية مع المصفوفات متعددة الأبعاد، وتحليل البيانات الاستكشافي، وروتينات معالجة البيانات مسبقاً. ويوفر سير عمل مفصلاً للتعلم الخاضع للإشراف وغير الخاضع للإشراف، وخطوط أنابيب التعلم الآلي المؤتمتة، وتحسين المعلمات الفائقة، وتقييم النموذج باستخدام مقاييس التصنيف والتحقق المتبادل. يتم تنظيم المحتوى التعليمي كسلسلة من الدفاتر التي تتداخل فيها أكواد Python مع التفسيرات السردية لتوثيق سير عمل علوم البيانات.
Integrates trained models into web-based interfaces for real-time classification and user interaction.
freegpt-webui هي واجهة ويب ذاتية الاستضافة للتفاعل مع نماذج لغوية كبيرة. توفر واجهة أمامية تعتمد على الدردشة مصممة للتواصل مع نماذج GPT 3.5 وGPT 4. يتيح التطبيق الدردشة بدون مفتاح واجهة برمجة تطبيقات، مما يسمح للمستخدمين بالوصول إلى الذكاء الاصطناعي التحادثي لتوليد النصوص واسترجاع المعلومات دون تقديم أو إدارة مفاتيح مصادقة شخصية. يتعامل النظام مع دمج النموذج من خلال بوابة وكيل عكسي ويدعم معالجة التدفق غير المتزامنة لتوليد النصوص في الوقت الفعلي. يتم الاحتفاظ بتفضيلات المستخدم وسجل المحادثة عبر تخزين جلسة جانب العميل.
Offers an interactive web-based interface specifically designed for interacting with machine learning model outputs.
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
Provides an interactive web interface for uploading media and generating talking videos without command-line usage.
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
Ollama launches an interactive chat interface using a specified model and runtime for real-time communication.
هذا المشروع عبارة عن واجهة ويب ذاتية الاستضافة وتطبيق سطح مكتب مصمم للتفاعل مع نماذج اللغة. يوفر منصة خاصة لإدارة جلسات المحادثة، مما يسمح للمستخدمين بالاتصال بخدمات الذكاء الاصطناعي الخارجية مع الحفاظ على التحكم في سجل تفاعلاتهم وإعدادات التهيئة. يتميز التطبيق بتقديم واجهة موحدة تدعم المدخلات والمخرجات متعددة الوسائط، بما في ذلك معالجة التفاعل الصوتي وإنشاء الصور التوليدية. ويؤمن بيانات الاعتماد الحساسة عن طريق توجيه الطلبات عبر وكيل خلفي (backend proxy) ويضمن خصوصية البيانات عن طريق تخزين سجلات المحادثة وسجل الجلسة محلياً على جهاز المستخدم. بعيداً عن وظائف الدردشة الأساسية، تتضمن المنصة أدوات للبث المباشر للاستجابات، وإدارة سجل المحادثة، والقدرة على تصدير السجلات للأرشفة. يتم حزم البرنامج كملف تنفيذي مستقل لسطح المكتب، مما يمكن المستخدمين من الوصول إلى خدمات الذكاء الاصطناعي هذه بشكل مستقل عن متصفح الويب.
Provides an interactive web interface for communicating with language models using custom prompts and streaming responses.
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
Provides a web-based development environment using structured modeling languages to simplify interface creation.