finetuning-scheduler is a PyTorch Lightning extension for foundation model experimentation with flexible fine-tuning schedules. It supports explicit or regex-based parameter selection and implicit schedules for initial model exploration, plus automatic restoration of best per-phase checkpoints using early-stopping criteria for each phase. An experimental API, FTSController, brings the same schedules to a plain PyTorch training loop.
HandyAI is a collection of free browser-based tools for AI and Claude developers, including token counters, prompt analyzers, JSON to tool-use converters and cost calculators. It requires no sign-up and lists the LLM Token Counter and AI Cost Calculator as live tools, with others announced for later release.
OCaml-GPR is an OCaml library for Gaussian process regression that includes a command line application and an example application. It implements approximation algorithms for scalable regression with arbitrary covariance functions.
GNU Octave is a programming language for scientific computing with mathematics-oriented syntax and built-in 2D/3D plotting and visualization tools. It is free software licensed under the GNU General Public License and runs on GNU/Linux, macOS, BSD, and Microsoft Windows. Its syntax is largely compatible with Matlab, and it can be extended by packages.
Taplio is described as an all-in-one AI tool for LinkedIn growth, offering idea finding, writing assistance, scheduling at suggested times, and converting an audience into leads. Pricing information lists Starter, Growth, and Pro plans, with AI content, scheduling, and analytics included in all plans, and a 7-day free trial.
A free downloadable guide from Kolena Inc. on testing large language models. It identifies principles for creating reliable testing protocols and details approaches for measuring model effectiveness in NLP tasks such as text summarization and prompt engineering, and discusses tracking performance differences over time.
Fiber is a Python-based distributed computing library for modern computer clusters. It provides the same API as Python's standard multiprocessing library, uses Nanomsg for communication, and allows dynamic allocation of CPU, memory, and GPU resources. Installation uses pip install fiber.
Community notes
Be the first to share how this project worked for you.
Sign in with a verified account to leave a review or join the discussion.
Sign in to reviewKeep exploring
HandyAI is a collection of free browser-based tools for AI and Claude developers, including token counters, prompt analyzers, JSON to tool-use converters and cost calculators. It requires no sign-up and lists the LLM Token Counter and AI Cost Calculator as live tools, with others announced for later release.
OCaml-GPR is an OCaml library for Gaussian process regression that includes a command line application and an example application. It implements approximation algorithms for scalable regression with arbitrary covariance functions.
GNU Octave is a programming language for scientific computing with mathematics-oriented syntax and built-in 2D/3D plotting and visualization tools. It is free software licensed under the GNU General Public License and runs on GNU/Linux, macOS, BSD, and Microsoft Windows. Its syntax is largely compatible with Matlab, and it can be extended by packages.
Taplio is described as an all-in-one AI tool for LinkedIn growth, offering idea finding, writing assistance, scheduling at suggested times, and converting an audience into leads. Pricing information lists Starter, Growth, and Pro plans, with AI content, scheduling, and analytics included in all plans, and a 7-day free trial.
A free downloadable guide from Kolena Inc. on testing large language models. It identifies principles for creating reliable testing protocols and details approaches for measuring model effectiveness in NLP tasks such as text summarization and prompt engineering, and discusses tracking performance differences over time.
Fiber is a Python-based distributed computing library for modern computer clusters. It provides the same API as Python's standard multiprocessing library, uses Nanomsg for communication, and allows dynamic allocation of CPU, memory, and GPU resources. Installation uses pip install fiber.
