xLLM Version 2.0: GitHub Repository with Innovative AI Agents

⋅

I am putting all the new code and documentation about xLLM v 2.0 on GitHub, starting with various AI agents. At least, what is open-source and public (there is a lot more behind the public material). All home-made from scratch with radically different technology. You can check the new repository, here. Start with the README file at the top of the repository, here. No Blackbox, no external API calls, and minimum reliance on Python libraries such as TensorFlow, PyTorch or Keras to give you full control over all the components and avoid drawbacks attached to these libraries. Perfect if you need secure, auditable, fast, high-performance AI on premises. The material related to xLLM 1.0 is still on GitHub, here.

Screenshot showing some of the files recently uploaded

Below is some of the material already uploaded:

  • Anomaly detection agent used in cybersecurity, with animated US map with colored zip codes, where color (red, orange, green) represents the risk at a given time (represented by a video frame), and the size represents the intensity or volume (for instance, number of transactions in the time period). The video based on a real use case is also on YouTube, here.
  • Medical agent to process ECG data (electrocardiogram) with high compression rate. The goal is to automate the job of technicians paid to find patterns and help detect signals that indicate an imminent risk of heart attack.
  • Data synthesis agent for tabular enterprise data, useful to generate fraud data or in medical settings. Based on our proprietary NoGAN technology.
  • New deep neural network technology and alternatives, with 96% correct prediction for the next token, on public NVIDIA corporate corpus. Also includes deep neural network smart distillation, and distillation-resistant watermarking to protect your model against unauthorized uses. For now, we use it to suggest alternate prompts to xLLM users, but we plan on using it on a much bigger scale. See the E-XLLM-V4 PowerPoint document for a summary. This doc is also on Google Drive, here.

To no miss future articles, subscribe to my AI newsletter, here.

Liked Liked