Solvice is revolutionizing resource management with its suite of AI-powered optimization tools. We specialize in applying artificial intelligence, machine learning, and heuristic algorithms to solve complex scheduling and planning challenges. Our key products, OnRoute, OnShift, and OnPick, offer solutions for route optimization, workforce scheduling, and warehouse picking. These tools are designed to help businesses improve operational efficiency, reduce costs, and enhance productivity. Solvice’s APIs provide seamless integration and customization options, ensuring they meet the specific needs of each client. Our commitment to innovation keeps us at the cutting edge of resource optimization technology. Partner with Solvice to leverage the power of AI and transform your business operations.

Capte is an innovative AI-powered platform that automates transcription, subtitling, and translation for video content. Add stylish captions, emojis, and animations to your videos to captivate your audience. Capte offers HD and 4K export options for professional-grade videos. Designed for creators, educators, and agencies, Capte simplifies the video editing process, allowing you to focus on creativity. Its user-friendly interface makes complex tasks easy and efficient. Optimize your social media presence with Capte’s automated post recommendations, helping you engage a wider audience.

Install this version. Find when in tumbleweed

Program in english

A resume parser extracts, analyzes, and organizes data from resumes to identify suitable candidates. This tool streamlines the recruitment process, minimizes errors, and saves time, thus enhancing recruiters' efficiency.

Document about LM Studio

Optimum is an extension of Transformers that provides a set of performance optimization tools to train and run models on targeted hardware with maximum efficiency. It is also the repository of small, mini, tiny models.

BERT model home on github

Excellent document about BERT transformers / models and their parameters: - L=number of layers. - H=size of the hidden layer = number of vectors for each word in the sentence. - A = Number of self-attention heads - Total parameters.

Repository of all Bert models, including small. Start using this model for testing.

LM Studio can be installed on Linux with APU or GPU (looks like it needs the AI CPU though??) and run LLM. Install on Laptop and test if it works.

My account on SageMaker studio. The give out 4 hours of GPU a day!

8000G is the APU series for AI

Doing what a transformer is doing, by hand

Kaggle is like huggingface. They can run notebooks, and give GPU power to notebooks

Mini course of statistical foundations of ML

My account on Stability AI - it is just a link to huggingface

Comparison of efficiency of all LLM models on hugging face

Various methods to run LLM models locally hugging face is only one of them.

AMD seems to sell these accelerators, which are like video cards.

Train LLM on AMD APU. In this scenario, we’ll use an APU because most laptops with a Ryzen CPU include an iGPU; specifically, this post should work with iGPUs based on the “GCN 5.0” architecture, or “Vega” for friends. We’ll use an AMD Ryzen 2200G in this post, an entry-level processor equipped with 4C/4T and an integrated GPU.