Watch the video:
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)
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): Go to post or View on YouTube
Install Oobabooga & Vicuna: UPDATED LINK COMING SOON
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