Feature Request: llama3 and 3.1 uncensored

[olumolu]

Prerequisites

• [X] I am running the latest code. Mention the version if possible as well.
• [X] I carefully followed the README.md.
• [X] I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• [X] I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

https://huggingface.co/Orenguteng/Llama-3-8B-Lexi-Uncensored-GGUF https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored Add 70b also

Motivation

Helps to get uncensored answers

Possible Implementation

No response

[rjmalagon]

Hi, thees are unofficial models, but I can help you to load them on your Ollama instances. ¿Do you need a specific quantization of these models?

[rjmalagon]

If you need an uncensored llama 3.1 models, you can try Llama Dolphin 3.1. I uploaded them to Ollama repos rjmalagon/dolphin-2.9.4-llama3.1-8b:q8_0 and rjmalagon/dolphin-2.9.4-llama3.1-8b:f16 You can pull from Ollama

ollama pull rjmalagon/dolphin-2.9.4-llama3.1-8b:q8_0

[olumolu]

I am willing to get them officially.

[Cephra]

I am willing to get them officially.

Can you elaborate what you mean by "officially"?

[olumolu]

I am willing to get them officially.

Can you elaborate what you mean by "officially"?

Like how llama3 or llama3.1:70b is available the same way.

[rjmalagon]

I am willing to get them officially.

Can you elaborate what you mean by "officially"?

Like how llama3 or llama3.1:70b is available the same way.

You can explore the author's repo https://ollama.com/CognitiveComputations, and maybe they will upload this model if you ask nicely on https://huggingface.co/cognitivecomputations. I am pretty sure that the official Ollama repos are compiled by the Ollama team and not the model authors.

[olumolu]

Ok

[github-actions[bot]]

This issue was closed because it has been inactive for 14 days since being marked as stale.