Comments (5)
Native >>>> Lora, it's just the way it is.
We should make a native model of gpt4all with the "unrestricted" dataset, and we'll get something great that's for sure!
Btw: The "unfiltered" model still refuses to answer some questions, the database must be investigated and cleaned further from the woke bullshit that's in it.
from gpt4all.
Yeah it seems to also refuse anything that could be interpreted as negativity towards anyone.
Prompt: Write a tkinter GUI that displays the text "OpenAi sucks".
Output: I'm sorry, but...
It feels like it's even more restrictive than gpt3.5 for some things.
from gpt4all.
Also gpt4all-lora-quantized.bin
from gpt4all.
If it’s trained on ChatGPT outputs then that’s expected and maybe wanted, isn’t it?
from gpt4all.
This is using gpt4all-lora-quantized.bin
:
from gpt4all.
Related Issues (20)
- Unable to instantiate model: Model format not supported (no matching implementation found)
- GPT4ALL crashes when switching model HOT 2
- [Feature] Integrate with a numeric computing package such as Mathematica, and render LaTeX
- ImportError: cannot import name 'GPT4ALL' from 'gpt4all' HOT 1
- Strange echoing of the prompt template HOT 3
- Support for FreeBSD HOT 2
- [Feature] Ability for Command Backspace to delete the currently edited line HOT 2
- [Feature] Add support for Gemma LLMs HOT 4
- ErrorInitializationFailed Vulkan HOT 2
- [Feature] Add support for Mistral API
- Online v2.7.1 release doesn't open, offline v2.7.0 release does HOT 7
- Chats save too slowly, and as of v2.7.1 load too slowly
- ChatML prompt template problems post 2.7.1 HOT 2
- Application crash caused by ChatGPT-3.5 Turbo and ChatGPT-4 HOT 14
- [Feature] Move default model storage to AppData/Local on Windows HOT 1
- Cloning model settings puts value from context length into GPU layers. HOT 1
- [Feature] Add option to load local doc database automatically on start up
- Visin + LLM fused models in GPT4All? HOT 1
- python: Unable to retrieve list of all GPU devices (but Chat UI works) - miniconda3 HOT 4
- [Feature] Add option to load model on start up in server mode
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gpt4all.