Machine learning projectSun May 28 2023
Links to articles I’ve found useful as I figure this LLM stuff out.
Introductions to Machine Learning
This document will explain what neural networks are and how they work, which will help you understand how AI and machine learning work. In the scenario below you’ll play the part of the neural network.
A high-level overview of machine learning for people with little or no knowledge of computer science and statistics. You’ll be introduced to some essential concepts, explore data, and interactively go through the machine learning life-cycle - using Python to train, save, and use a machine learning model like we would in the real world.
In this blog, we will discuss the workflow of a Machine learning project this includes all the steps required to build the proper machine learning project from scratch.
- karpathy/nanoGPT: The simplest, fastest repository for training/finetuning medium-sized GPTs.
- alpaca lora
- lxe/ggml at wasm-demo
ChatGPT-like chatbot in the browser using ggml and emscripten. No API keys required. No server required. No data is sent to any server.
- MusicalInformatics/intro_to_ml: Introduction to Machine Learning
- Supervised learning - Wikipedia
- Iris flower data set - Wikipedia
- Perceptron - Wikipedia
- Artificial neural network - Wikipedia
- Labeled data - Wikipedia
Looking to research #ChatGPT services that allow you to create chatbots that can answer questions about specific information (e.g. #documentation ). I’ve found: heybot.thesamur.ai github.com/arc53/DocsGPT docsgpt.ai/ Anything else you know about? Is there a good example of an open source GPT chat application A: Yes, there are several examples of open source GPT chat applications. Here are a few:
- ChatterBot - ChatterBot is a Python library that can be used to build conversational agents powered by GPT-2 or other natural language processing algorithms. It supports various conversational formats and can be used to create chatbots for different platforms such as Telegram, Facebook, Slack and more.
- Botpress - Botpress is an open source conversational AI platform that can be used to build chatbots for various platforms such as websites, Facebook, Slack, and more. It is powered by GPT-2 and other natural language processing algorithms and features a visual interface to create conversational workflows.
- Rasa - Rasa is an open source framework for building conversational AI applications for text and voice interfaces. It includes tools for building, training, and evaluating models powered by GPT and other machine learning algorithms. It also supports integration with different chat platforms such as Slack, Facebook Messenger, and more.
- DeepPavlov - DeepPavlov is an open source conversational AI framework that supports various NLP tasks such as intent recognition, entity extraction, and dialogue management. It is powered by GPT and other machine learning algorithms and features pre-trained models for various conversational scenarios such as customer support, chitchat, and more. These are just a few examples of open source GPT chat applications. There are many others available on GitHub and other open source platforms. Can you provide URLs? A: Certainly! Here are the URLs for the open source GPT chat applications mentioned in my previous response:
- ChatterBot: https://github.com/gunthercox/ChatterBot
- Botpress: https://github.com/botpress/botpress
- Rasa: https://github.com/RasaHQ/rasa
- DeepPavlov: https://github.com/deepmipt/DeepPavlov
imartinez/privateGPT: Interact privately with your documents using the power of GPT, 100% privately, no data leaks 800+ ChatGPT and GPT-3 Examples, Demos, Apps, Showcase, and Generative AI Use-cases | Discover AI use cases
Getting Started with Hugging Face Transformers for NLP (see also /Users/philip/pyprojects/huggingfacetoy)
Phrases Jargon Words
- Gradient descent
- loss function
- learning rate
- sigmoid neuron
from random screenshot
Tips & Tricks • use automatic1111 or Easy Diffusion (https:// github.com/AUTOMATIC1111/stable- diffusion-webui | https://github.com/ cmdr2/stable-diffusion-ui) • Here are some instructions for installation and use: https://stable-diffusion-art.com/ • use models from civitai.com • negativ prompts are important • Modifier Studies: https:// proximacentaurib.notion.site/ 2b07d3195d5948c6a7e5836f9d535592?v • Artist Style Studies: https:// proximacentaurib.notion.site/ e28a4f8d97724f14a784a53868589e7d?v • Hires. fix! • for advanced, search for ControlNet • be creative and have fun robertlacok/datasciencenotebooks
wevi Word Embedding Visual Inspector