VIDEO
HIGHLIGHT
Log InSign up
NEW POWERFUL Local ChatGPT 🤯 Mindblowing Unrestricted GPT-4 | Vicuna
SummaryTranscriptChat

NEW POWERFUL Local ChatGPT 🤯 Mindblowing Unrestricted GPT-4 | Vicuna

Introduction to Vicuna AI Text Generation

In this video, the speaker introduces a new text generation AI called Vicuna. The model was trained on questions and answers from GPT4 and is completely offline. The speaker provides a link to the project's homepage where users can find more information about the model.

Features of Vicuna AI

  • Vicuna is a text generation AI that was recently released.
  • It was trained on questions and answers from GPT4 and achieves more than 90% quality compared to other models like OpenAI Chat GPT and Google Bard.
  • Users can choose between different models such as Vicuna, Koala, Alpaca, Llama, or Bygunum.
  • Users can download and run Vicuna on their own PC.

Installation Steps for Uber Booger

  • Uber Booger is another program that allows users to customize their experience with text generation AI.
  • The installation steps are manual but there is a super simple installation script available to simplify the process.
  • Users will need to open up a new folder somewhere on their PC where they'd like to install this.
  • After downloading Uber Booger, users will be prompted whether they have an Nvidia graphics card that they'd like to use or just run in CPU mode.

Setting Up Vikuna Model

  • After all this is set up it'll download an 8 gigabyte model file which is Vicuna.
  • Users will be prompted to copy the text which is the Vicuna model and place it in the models folder.

Setting up Vicuna Model

This section covers the steps to set up the Vicuna model.

Steps

  • Download the Vicuna model from Hugging Face, which is around 8 gigabytes in size.
  • Wait for the download to complete depending on your internet speed and connection.
  • Press any key to continue and start the web UI.
  • To uninstall, delete the Uber booger folder.

Using Chat GPT Bot

This section covers how to use Chat GPT bot.

Steps

  • Open the local URL 127001 7860 or similar in your browser by selecting it and right-clicking or Ctrl+clicking if underlined.
  • Type a prompt or message in the chat box.
  • Hit enter or generate to send a response.
  • Replace last reply as if you were speaking back to yourself using LSA replace last reply command.
  • Change between Kai chat chatter mode here and instruct modes for different ways of speaking with the bot.
  • Clear history at bottom of page when needed.
  • Use character gallery at bottom of page to set up specific characters and speak with them using saved states whenever desired.

Customizing Characters

This section covers customizing characters in Chat GPT bot.

Steps

  • Head up to characters tab where you can edit different characters' names, greetings, context, and pictures.
  • Set context for each character by adding statements that provide background information about them.
  • Clear history on text generation tab after setting context.

Installation and Interface Overview

This section covers the installation process for Uber Booger Run, as well as an overview of its interface.

Installing Uber Booger Run

  • Download the program from the website.
  • Select a model or enter the hugging face path.
  • The training tab allows for customization of extensions.

Interface Mode

  • Customize extensions such as text-to-speech and speech-to-text.
  • Command line flags are available for program customization.

Enabling Speech-to-Text and Text-to-Speech

This section covers how to enable speech-to-text and text-to-speech in Uber Booger Run.

Enabling Speech-to-Text

  • Enable speech-to-text in the interface mode.
  • Download The Whisper model if necessary.
  • Record audio from microphone to generate text output.

Enabling Text-to-Speech

  • Customize voice pitch and speed in the interface mode.
  • Program generates speech output based on typed input.

Running Uber Booger Run on Your PC

This section covers how to run Uber Booger Run on your own PC without internet connection.

Hardware Requirements

  • Can run on any PC that can handle generation side of AI.
  • No need for high-end hardware or graphics card. Can run on CPU only, albeit slower.

Limitations

  • Output may not be 100% accurate or truthful due to small model size.

Conclusion

This section concludes the video by thanking viewers for watching and asking for feedback.

Final Thoughts

  • One-line installation command is available.
  • Feedback is appreciated regarding future content with easy installation scripts.
Video description

Vicuna: A new, powerful model based on LLaMa, and trained with GPT-4. Vicuna boasts "90%* quality of OpenAI ChatGPT and Google Bard". This is unseen quality and performance, all on your computer and offline. UPDATED GUIDE (CPU works! + Installer has changed): https://youtu.be/d4dk_7FptXk View what this script does & see the source code here: https://vicuna.tc.ht Install Oobabooga & Vicuna: iex (irm vicuna.tc.ht) Full manual install text guide: https://hub.tcno.co/ai/text-ai/vicuna/ More info on Vicuna: https://vicuna.lmsys.org/ Oobabooga: https://github.com/oobabooga/text-generation-webui/ Manual model download: https://huggingface.co/anon8231489123/vicuna-13b-GPTQ-4bit-128g/tree/main Based on the original model (from what I understand): https://huggingface.co/lmsys/vicuna-13b-delta-v0 Timestamps: 0:00 - Explanation 0:22 - What is Vicuna? 1:36 - What is Oobabooga? 2:18 - One-click install script 4:59 - Using the WebUI 5:45 - Basic chat & VRAM usage 6:24 - Guide responses in certain ways (POWERFUL) 7:14 - Preset AI characters/Personas 7:49 - Creating a character/AI persona 8:11 - Limitations 9:02 - Parameters 9:48 - Fine-Tuning 10:05 - Speech-To-Text and Text-To-Speech (tts/stt) #AI #ChatGPT #Guide ----------------------------- 💸 Found this useful? Help me make more! Support me by becoming a member: https://youtube.com/channel/UCkih2oVTbXPEpVwE-U7kmHw/join ----------------------------- 💸 Direct donations via Ko-Fi: https://ko-fi.com/TCNOco 💬 Discuss the video & Suggest (Discord): https://s.tcno.co/Discord 👉 Game guides & Simple tips: https://YouTube.com/TroubleChuteBasics 🌐 Website: https://tcno.co 📧 Need voiceovers done? Business query? Contact my business email: TroubleChute (at) tcno.co ----------------------------- 🎨 My Themes & Windows Skins: https://hub.tcno.co/faq/my-windows/ 👨💻 Software I use: https://hub.tcno.co/faq/my-software/ ➡️ My Setup: https://hub.tcno.co/faq/my-hardware/ 🖥️ My Current Hardware (Links here are affiliate links. If you click one, I'll receive a small commission at no extra cost to you): Intel i9-13900k - https://amzn.to/42xQuI1 GIGABYTE Z790 AORUS Master - https://amzn.to/3nHuBHx G.Skill RipJaws 2x(2x32G) [128GB] - https://amzn.to/42cilxN Corsair H150i 360mm AIO - https://amzn.to/42cznvP MSI 3080Ti Gaming X Trio - https://amzn.to/3pdnLdb Corsair 1000W RM1000i - https://amzn.to/42gOTGY Corsair MP600 PRO XT 2TB - https://amzn.to/3NSvwzx 🎙️ My Current Mic/Recording Gear: Shure SM7B - https://amzn.to/3nDGYo1 Audient iD14 - https://amzn.to/3pgf2XK dbx 286s - https://amzn.to/3VNaq7O Triton Audio FetHead - https://amzn.to/3pdjIgZ Everything in this video is my personal opinion and experience and should not be considered professional advice. Always do your own research and ensure what you're doing is safe.