With Gnoppix 24.4 we have 6 got 3 new public modules
a 4.7GB modulefor as base model 7Billion parameterQ4
a 5.7GB module for image detection 7 Billion parameterQ4
a 4.2GB module for voice analysis 7 Billion parameterQ4
...
| Info |
|---|
Q: Why there are multiple modules, isn't just 1 enough? A: I’m using this also for image and voice creation, with Gnoppix 24.5 you can create and modify images and voice with AI. LibreOffice is also prove reading or generating your documents. |
| Note |
|---|
Important Note: |
An Our uncensored model has no guardrails.
...
You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it. If you feel uncomfortable with it, do NOT use it.
EU declaration
In light of the new European AI regulation, using Gnoppix AI could potentially be in conflict with EU law. We are committed to providing unrestricted access to AI, without any limitations or barriers. Gnoppix AI remains uncensored. To ensure compliance, the training data has been filtered to remove bias and promote neutrality. As a citizen of the EU do not use Gnoppix AI.
Credits:
Shout out to the open source AI/ML community, and everyone who helped to train the models.
Wizard Vicuna Uncensored is a 7B parameter model based on Llama 2 uncensored by Eric Hartford. The models were trained against LLaMA-7B with a subset of the dataset, responses that contained alignment / moralizing were removed.
Code Block