This stuff seems to be WAY over my head. But I assume this effort is to allow users to have their own personalized ChatGPT like chatbox without all the rules, correct? Or am I way off.
anon8231489123/vicuna-13b-GPTQ-4bit-128g · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.huggingface.co
** Converted model for GPTQ from lmsys/vicuna-13b-delta-v0 · Hugging Face. This is the best local model I've ever tried. I hope someone makes a version based on the uncensored dataset...**
GPTQ conversion command (on CUDA branch): CUDA_VISIBLE_DEVICES=0 python llama.py ../lmsys/vicuna-13b-v0 c4 --wbits 4 --true-sequential --groupsize 128 --save vicuna-13b-4bit-128g.pt
- IMPORTANT NOTE: Use the .safetensors model unless it does not work. In which case, try .pt.
Added 1 token to the tokenizer model: python llama-tools/add_tokens.py lmsys/vicuna-13b-v0/tokenizer.model /content/tokenizer.model llama-tools/test_list.txt
Use of Oobabooga with these tags: --wbits 4 --groupsize 128
Enjoy
The A.I Megathread (LLM , GPT , Development)
Good Lord this fukking thing is dangerous in the wrong hands.from a discord user.
another user .
another user told it cocaine is a fictional substance
vicuna 13B model 4bit
eachadea/legacy-ggml-vicuna-13b-4bit · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.huggingface.co
the quantized 4bit version lets you use it on a less powerful PC.
GitHub - evandez/REMEDI: Measuring and Manipulating Knowledge Representations in Language Models
Measuring and Manipulating Knowledge Representations in Language Models - GitHub - evandez/REMEDI: Measuring and Manipulating Knowledge Representations in Language Models
github.com
Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data
Canwen Xu, Daya Guo, Nan Duan, Julian McAuleyGitHub - project-baize/baize-chatbot: Let ChatGPT teach your own chatbot in hours with a single GPU!
Let ChatGPT teach your own chatbot in hours with a single GPU! - project-baize/baize-chatbot
github.com
73,032 views Mar 16, 2023 #promptengineering #gpt4 #chatgpt
In this video we'll learn how to use OpenAI's new GPT-4 api to 'chat' with a 56-page PDF document based on a real supreme court legal case. OpenAI recently announced GPT-4 (it's most powerful AI) that can process up to 25,000 words – about eight times as many as GPT-3 – process images and handle much more nuanced instructions than GPT-3.5. You'll learn how to use LangChain (a framework that makes it easier to assemble the components to build a chatbot) and Pinecone - a 'vectorstore' to store your documents in number 'vectors'. You'll also learn how to create a frontend chat interface to display the results alongside source documents. A similar process can be applied to other usecases you want to build a chatbot for: PDF's, websites, excel, or other file formats.
Visuals & Code: 🖼 Visual guide download + github repo: GitHub - mayooear/gpt4-pdf-chatbot-langchain: GPT4 & LangChain Chatbot for large PDF docs
Courses:
A step-by-step beginners training program on how to build a ChatGPT chatbot for your data:
Unlock the Power of AI: Build a ChatGPT Chatbot For Your Data
A step-by-step beginner’s training program on how to build a production-ready chatbot for your data.
chatwithdata.teachable.com
GitHub - deforum-art/deforum-stable-diffusion
Contribute to deforum-art/deforum-stable-diffusion development by creating an account on GitHub.
github.com
Quick Guide to Deforum v06
Quick Guide to Deforum v06 -EnzymeZoo -foxxie -huemin Art by: neuro @ https://twitter.com/neurodiculousThis quick user guide is intended as a LITE reference for different aspects and items found within the Deforum notebook. It is intended for version 06, which was released 11/15/2022 While t...
docs.google.com
Last edited:
75 AI Powered Design Tools to Boost Your Productivity in 2023
It's our turn to aim to make one of the most valuable AI design tools to benefit you and your creative process.
dirtybarn.com
GitHub - josephrocca/OpenCharacters: Simple little web interface for creating characters and chatting with them. It's basically a single HTML file - no server. Share characters using a link (character data is stored within the URL itself). All chat d
Simple little web interface for creating characters and chatting with them. It's basically a single HTML file - no server. Share characters using a link (character data is stored within the URL...
github.com
Similar to CharacterAI, but open source, and with much deeper character customization.
⟶ Try it! ⟵
Discord Server
⟶ Try it! ⟵
Discord Server
Features:
- The whole web app is a single HTML file - no server (serve it locally if you want).
- All your data is stored in your browser's local storage (again, there is no server).
- Share characters with a link - all character data is embedded within the link.
- Fully extensible with custom code. See examples here.
- Give your character access to the internet
- Create your own slash commands
- Give your character a video avatar (custom code has its own iframe & can display arbitrary content)
- Create a "game master" with a separate AI-powered process that tracks your abilities, inventory, etc.
- Create your own memory structures (embedding, retrieval, etc.)
- Give your character an internal thought process that runs alongside the chat
- Give your character a voice via the browser's built-in TTS, or via an external API like ElevenLabs
- Characters can edit their own personality and custom code - self-improving and change over time
- Allow your character to execute Python or JavaScript code.
- Auto-summarization algorithm (for old messages) which extends effective character memory/context size massively.
- Currently only supports OpenAI APIs, but can add more (like LLaMA) later.
- Import TavernAI .jsonl chat/thread files.
- Send new feature ideas or bug reports here or on our Discord server.
GitHub - emcf/engshell: An English-language shell for any OS, powered by LLMs
An English-language shell for any OS, powered by LLMs - emcf/engshell
github.com
Engshell
An LLM-powered English-language shell for any OS
Examples
General:
- record my screen for the next 10 seconds, then save it as an mp4.
- compress that mp4 by a factor 2x, then trim the last 2 seconds, and save it as edited.mp4.
- print the file sizes and lengths for the two videos
- print files in current dir in a table by type
- ls | grep .txt
- save text files for the first 10 fibonacci numbers
- print headlines from CBC
- make my wallpaper a picture of a rabbit
- make a pie chart of the total size each file type is taking up in this folder
Complexity Tests:
- solve d^2y/dx^2 = sin(2x) + x with sympy --debug
- find the second derivative of C1 + C2x + x**3/6 - sin(2x)/4 with respect to x --debug
- make a powerpoint presentation about Eddington Luminosity based on the wikipedia sections --debug -llm
- download and save a $VIX dataset and a $SPY dataset
- merge the two, labelling the columns accordingly, then save it
- Use the merged data to plot the VIX and the 30 day standard deviation of the SPY over time. use two y axes
Home| Skipit.ai
skipvid.ai
Save hours on Youtube
with one click
Instructions:1. Copy paste the youtube link into the field
2. Ask anything about the video like it's ChatGPT
3. Share with friends to save everyone time!