Coding & Development

Table Transformer (TATR) is a deep learning model developed by Microsoft for extracting tables from unstructured documents, including PDFs and images. Based on object detection, TATR can be trained to work across various document domains, with pre-trained model weights available for the PubTables-1M dataset. The repository also provides the official code for the PubTables-1M dataset, a large-scale dataset for table detection, structure recognition, and functional analysis, and the GriTS evaluation metric for table structure recognition. Researchers and developers can use TATR to detect and recognize tables, convert them to HTML or CSV, and train custom models for specific needs.

TileRT is an open-source, tile-based runtime engineered for ultra-low-latency Large Language Model (LLM) inference. It aims to push the boundaries of LLM latency without compromising model size or quality, allowing models with hundreds of billions of parameters to achieve millisecond-level time per output token (TPOT). Unlike traditional inference systems optimized for high-throughput batch processing, TileRT prioritizes responsiveness, making it ideal for applications like high-frequency trading, interactive AI, real-time decision-making, and AI-assisted coding. It achieves this by decomposing LLM operators into fine-grained tile-level tasks and dynamically rescheduling computation, I/O, and communication across multiple devices to minimize idle time and improve hardware utilization. TileRT currently supports models like GLM-5 and DeepSeek-V3.2 and offers Multi-Token Prediction (MTP) for efficient longer output generation.

TimeCapsuleLLM is an innovative open-source project focused on creating language models (LLMs) trained exclusively on data from specific historical periods and geographic locations. The primary goal is to mitigate modern biases inherent in contemporary LLMs and accurately emulate the linguistic style, vocabulary, and worldview of a chosen era. The project has developed several versions, including v0, v0.5, v1, and v2, with increasing dataset sizes and model parameters, built on architectures like nanoGPT, Phi 1.5, and llamaforcausallm. It emphasizes Selective Temporal Training (STT) where all training data is curated from a defined historical window, ensuring the model's knowledge and language reflect that period without modern influence. The project provides core training scripts, tokenizer building tools, and detailed documentation for researchers and developers interested in historical language modeling.

tokenizers is an open-source library developed by Hugging Face, offering highly optimized and versatile tokenizers for natural language processing tasks. Implemented primarily in Rust, it boasts exceptional performance, capable of tokenizing a gigabyte of text on a server's CPU in less than 20 seconds. The library supports training new vocabularies and tokenizing text using popular models like Byte-Pair Encoding, WordPiece, and Unigram. It includes features such as alignment tracking during normalization, ensuring that the original sentence segments corresponding to tokens can always be retrieved. Additionally, it handles pre-processing steps like truncation, padding, and adding special tokens required by various models, making it suitable for both research and production environments.

I-Stem provides an AI-powered solution to make websites accessible in minutes. Its platform allows for a streamlined approach to ensure fast, hassle-free execution, converting any webpage into a fully accessible chat-and-voice UI. The tool preserves 100% of existing design and functionality and can be deployed without requiring engineering resources. I-Stem leverages advanced voice AI for hands-free navigation and natural input, delivering inclusive experiences for all users. It also helps businesses tap into the $13 trillion global market of customers with disabilities and ensures compliance with ADA, EAA, and RPWD regulations effortlessly.

Image to Prompt AI is an advanced AI tool designed to transform images into detailed text prompts. Leveraging state-of-the-art AI technology, it accurately analyzes and understands image content, generating comprehensive descriptions that capture objects, composition, mood, and artistic elements. This tool is ideal for content creators, marketers, and SEO specialists looking to enhance image accessibility and optimization. It offers rapid processing, delivering instant text descriptions, and provides 20 free image-to-prompt conversions every 24 hours. Users can easily export generated text in multiple formats, making it versatile for various creative and professional applications.

Trajectory Transformer is an open-source code release that implements offline reinforcement learning as a sequence modeling problem. Based on the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem," this tool provides a framework for training models to predict trajectories. It includes scripts for training transformers on various datasets and for planning with these models. The project also offers pretrained models for multiple datasets, allowing users to quickly experiment and reproduce results. It supports installation via conda or Docker, and provides utilities for running jobs on Azure, making it suitable for researchers and engineers in reinforcement learning and robotics.

TASO, the Tensor Algebra SuperOptimizer for Deep Learning, significantly enhances the performance of deep neural network models. It achieves this by automatically generating and verifying graph transformations to build a vast search space of computation graphs equivalent to the original DNN model. Employing a cost-based search algorithm, TASO discovers highly optimized computation graphs, leading to up to a 3x performance improvement over graph optimizers in current deep learning frameworks. It supports optimizing pre-trained models in ONNX, TensorFlow, and PyTorch formats, and offers a Python interface for arbitrary DNN architectures. Optimized graphs can be exported to ONNX for use in existing deep learning frameworks, maintaining original model accuracy.

Texar is a comprehensive toolkit designed to support a broad range of machine learning tasks, with a particular focus on natural language processing and text generation. Built on TensorFlow, it offers a rich library of modular and easy-to-use ML components and functionalities, enabling both researchers and practitioners to rapidly prototype and experiment with models. Key features include support for pre-trained models like BERT, GPT2, and XLNet, and full customizability at multiple abstraction levels. Texar is versatile, supporting various tasks, models, algorithms, data processing, and evaluation methods, from encoder-decoder architectures to reinforcement learning and adversarial learning. It emphasizes modularity for maximum re-use and clean APIs, based on a principled decomposition of learning, inference, and model architecture. The toolkit also supports distributed model training with multiple GPUs and provides extensive documentation and examples.

torch-template-for-deep-learning is an open-source project providing PyTorch implementations of a wide array of classical backbone Convolutional Neural Networks (CNNs), alongside essential tools for deep learning development. It includes various data enhancement techniques like Cutout and Mixup, a collection of torch loss functions such as Focal Loss and Dice Loss, and numerous attention mechanisms including SE Attention and Self Attention. The template also features deployment modes for PyTorch models, conversion utilities from TensorFlow to PyTorch, and Class Activation Mapping (CAM) methods. This comprehensive resource aims to simplify and accelerate the development of deep learning applications by offering readily available and well-structured components.

Vim, or Vision Mamba, is an open-source AI tool developed by hustvl for efficient visual representation learning. It leverages a bidirectional state space model (Mamba) to process visual data, offering a novel approach to computer vision tasks. The tool addresses challenges in visual data representation for SSMs, particularly the position-sensitivity of visual data and the need for global context. Vim has demonstrated superior performance on tasks like ImageNet classification, COCO object detection, and ADE20k semantic segmentation, outperforming established vision transformers like DeiT. Notably, it achieves significant improvements in computation and memory efficiency, being 2.8x faster than DeiT and saving 86.8% GPU memory for high-resolution image feature extraction. This makes Vim a promising candidate for next-generation backbones in vision foundation models.

VideoLLaMA2 is an open-source project designed to significantly advance spatial-temporal modeling and audio understanding within video-Large Language Models (LLMs). It offers a comprehensive framework for researchers and developers to explore and build upon state-of-the-art video analysis capabilities. The tool provides various pre-trained models, including vision-only and audio-visual checkpoints, supporting tasks such as multi-choice video QA, video captioning, open-ended video QA, and audio-visual QA. It includes detailed instructions for installation, running online and offline demos, and quick-start guides for training and evaluating custom VideoLLaMA2 models using datasets like VideoLLaVA. The project emphasizes its top performance on leaderboards like MLVU and VideoMME for ~7B-sized VideoLLMs.

VideoLLM-online is the official implementation of an Online Video Large Language Model for Streaming Video, presented at CVPR 2024. Unlike traditional models that process full videos offline, VideoLLM-online enables real-time interaction within a video stream, allowing it to proactively update responses based on activity changes or assist with next steps. It features a cheap and scalable method for synthesizing streaming data by transforming offline annotations into dialogue data using open-source LLMs. The inference method is parallelized, combining video encoding, LLM forwarding, and response generation asynchronously, achieving high speeds of 10-15 FPS on an A100 GPU for long-form videos up to 10 minutes. The tool is designed for researchers and developers working with streaming video analysis and real-time multimodal AI.

X-MAS FLUX LORA is an AI-powered image generator hosted on Hugging Face, specifically designed to create festive Christmas-themed images. Users can input text descriptions, and the tool will generate high-quality visuals. A notable feature is its ability to translate Korean prompts into English, making it accessible to a broader audience. The application also provides adjustable settings, allowing users to control aspects like image size and level of detail, ensuring more customized outputs. While the tool was previously available, the live website indicates it is currently paused, requiring users to request its restart from the author.

VideoMamba is an innovative open-source state space model designed for efficient video understanding, specifically addressing the dual challenges of local redundancy and global dependencies in video data. It adapts the Mamba architecture to the video domain, overcoming limitations found in existing 3D convolution neural networks and video transformers. Its linear-complexity operator enables efficient long-term modeling, which is crucial for processing high-resolution and extended video content. The tool demonstrates scalability in the visual domain without requiring extensive dataset pretraining, thanks to a novel self-distillation technique. It also exhibits sensitivity for recognizing fine-grained short-term actions, superiority in long-term video understanding, and compatibility with multi-modal contexts, setting a new benchmark for comprehensive video analysis.

Thai Sentence Embedding Benchmark is a specialized AI tool designed to evaluate and rank Thai sentence embedding models. It features a comprehensive leaderboard that showcases the performance of different models across a variety of datasets and tasks relevant to the Thai language. Users can access detailed scores for each model, enabling them to compare and select the most suitable embeddings for their specific natural language processing (NLP) applications. This tool is particularly valuable for AI researchers and NLP engineers who require robust benchmarks for developing and optimizing Thai language models.

tts Text To Speech is a powerful text-to-speech (TTS) tool built on Next-gen Kaldi, available as a Hugging Face Space. It allows users to easily convert written text into spoken audio. The application provides options to select from various languages and TTS models, offering flexibility in voice output. Additionally, users can specify a speaker ID and adjust the speaking speed to customize the generated audio. The tool outputs the spoken text as a WAV audio file and also indicates the duration of the generated audio, making it suitable for a range of applications from content creation to research and development.

Best Upscaling Models is a web-based tool that provides a selection of non-diffusion upscaling models to enhance image resolution and quality. Users can upload an image and choose from various models to achieve a higher resolution output. The platform is designed to be straightforward, presenting both the original and the upscaled images for comparison. This tool is particularly useful for individuals and professionals who need to improve the clarity and size of their images without relying on diffusion-based methods, making it a valuable resource for various visual content needs.

ZCF, or Zero-Config Code Flow, is an open-source command-line interface (CLI) tool designed to streamline the coding experience for developers using Claude Code and Codex. It boasts a zero-configuration, one-click setup, making it easy to get started. The tool integrates an intelligent agent system and a personalized AI assistant to enhance coding workflows. ZCF supports bilingual interfaces (English, Chinese, Japanese) and is sponsored by various AI service providers like Z.ai, 302.AI, PackyCode, AICodeMirror, and Crazyrouter, which offer discounted access to AI models and API relay services. It provides quick start commands for full initialization, workflow updates, and language switching, with comprehensive documentation available.

VIBE Image Edit DEMO serves as a demonstration tool for the VIBE-Image-Edit model, hosted on Hugging Face Spaces. This application empowers users to interact with AI-driven image editing by either uploading an existing picture and describing desired modifications or by generating entirely new images from a text prompt. It provides a hands-on experience with the capabilities of the VIBE-Image-Edit model, allowing for creative exploration and practical application of AI in visual content creation. The tool is designed for ease of use, enabling individuals to experiment with advanced image manipulation techniques without requiring deep technical expertise.

VoiceStreamAI is a Python 3-based server and JavaScript client solution designed for near-realtime audio streaming and transcription. It leverages WebSocket for real-time communication and integrates Huggingface's Voice Activity Detection (VAD) with OpenAI's Whisper model (or faster-whisper by default) for accurate speech recognition. Key features include a modular design for easy integration of different VAD and ASR technologies, support for multilingual transcription, and customizable audio chunk processing strategies. The system optimizes processing by detecting speech segments, reducing computational load and improving accuracy. It also supports client-specific configurations for language, chunk length, and processing strategy, making it a flexible solution for developers building real-time transcription capabilities.

Z-IMAGE GEN/LORA is a Hugging Face Space that serves as a demo for a collection of impressive LoRAs for Z-Image-Turbo. This tool enables users to generate high-quality images by simply providing a text prompt and choosing from various LoRA styles, or even adding their own. The application offers adjustable settings such as image size, generation steps, and seed, giving users control over the output. While the Space is currently paused, it showcases the potential for creative content generation and image customization through the exploration of different LoRA models.

LitGPT is a comprehensive open-source toolkit designed for developers and AI researchers working with large language models. It offers over 20 high-performance LLMs, each implemented from scratch without abstractions, ensuring full control and optimized performance. The platform provides ready-to-use recipes for pretraining, finetuning, and deploying these models at scale, supporting features like Flash Attention, FSDP, LoRA, QLoRA, and Adapter finetuning. LitGPT is built to reduce GPU memory usage through various precision settings (FP16, BF16) and quantization techniques (4-bit, 8-bit). It supports deployment as inference APIs and offers command-line interfaces for advanced workflows, making it suitable for enterprise-level applications and academic research.

SnapPoint, offered by Alex Cloudstar, is a full-stack development service focused on delivering robust and timely software solutions. Alex brings experience from companies like E.ON, ING, and Warner Bros., specializing in technologies such as TypeScript, React, Node.js, Next.js, PostgreSQL, and AWS. He is available for freelance projects and long-term collaborations, emphasizing clear communication, honest timelines, and durable code. The service is ideal for clients seeking custom software development with a focus on quality and efficiency, particularly for projects involving modern web stacks and AI agent architectures.