Search Results for "tiny-workflow" - Page 23

KeplerWeka adds the functionality of the open-source machine learning and data mining workbench WEKA to the free and open-source, scientific workflow application, Kepler.

Socr3 is a plugin-oriented, open source platform upon which I'm building an OCR suite. The name Socr3 stands for "Open Source Optical Character Recognition, Reading, Rendering, and Exporting", and is subject to change in the future.

WebAPSEE is an open source project which aims to provide automated support for software process management. The users list is: http://groups.google.com/group/webapsee-usuarios

Trinity is mobile agent framework for creation of wide range of mobile agent types. Main goal of project is to provide a tool for rapid development of non-complex agents. Trinity is implemented in .NET v3.5 with usage of Windows Workflow Foundation and W

A framework for building, deploying and managing well-described REST-ful Web services, including REST-ful Web Services realizations for RSS, XML Topic Maps, Structured Arguments, and Workflow.

SCORE is a tool to facilitate manual coding of video sequences. SCORE is an easy-to-modify OS X tool. SCORE is designed to make the coding easier and enables an all-digital one-program coding workflow.

OpenFlow is a web based, publishing workflow management system aimed at magazine production, controlling editorial planning thru imposition. It uses web standards (XHTML, CSS, javascript, XML, XSL, RDF) making it easy to configure and customize.

Ling-3.0-tiny is inclusionAI’s lightweight hybrid reasoning Mixture-of-Experts model, designed to provide capable reasoning and agentic performance at low inference cost. It contains 7.9B total parameters while activating only 1.3B per token, using a hybrid architecture that alternates Kimi Delta Attention and Multi-Head Latent Attention with a sparse 128-expert MoE.

granite-timeseries-ttm-r2 is part of IBM’s TinyTimeMixers (TTM) series—compact, pre-trained models for multivariate time series forecasting. Unlike massive foundation models, TTM models are designed to be lightweight yet powerful, with only ~805K parameters, enabling high performance even on CPU or single-GPU machines. The r2 version is pre-trained on ~700M samples (r2.1 expands to ~1B), delivering up to 15% better accuracy than the r1 version. TTM supports both zero-shot and fine-tuned...

Ministral 3 3B Base 2512 is the smallest model in the Ministral 3 family, offering a compact yet capable multimodal architecture suited for lightweight AI applications. It combines a 3.4B-parameter language model with a 0.4B vision encoder, enabling both text and image understanding in a tiny footprint. As the base pretrained model, it is not fine-tuned for instructions or reasoning, making it the ideal foundation for custom post-training, domain adaptation, or specialized downstream tasks. The model is fully optimized for edge deployment and can run locally on a single GPU, fitting in 16GB VRAM in BF16 or less than 8GB when quantized. ...

...In normal conversations, it behaves like a reasoning-focused assistant that generates explicit <think> chains before answering. When configured as an agent, it can emit structured tool-use XML for file editing, shell commands, codebase navigation, and workflow automation. Qwable-v1 is designed specifically for software engineering, code editing, debugging, and autonomous coding workflows.