UnfilteredAI_-_UNfilteredAI-1B-exl2

Quantization made by Richard Erkhov.

Github

Discord

Request more models

UNfilteredAI-1B - EXL2

• Model creator: https://huggingface.co/UnfilteredAI/
• Original model: https://huggingface.co/UnfilteredAI/UNfilteredAI-1B/

Available sizes

| Branch | Bits | Description | | ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ | | 8_0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | | 6_5 | 6.5 | Very similar to 8.0, good tradeoff of size vs performance, recommended. | | 5_0 | 5.0 | Slightly lower quality vs 6.5, but usable on 8GB cards. | | 4_25 | 4.25 | GPTQ equivalent bits per weight, slightly higher quality. | | 3_5 | 3.5 | Lower quality, only use if you have to. |

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/UnfilteredAI_-_UNfilteredAI-1B-exl2 UNfilteredAI-1B-6_5

With huggingface hub:

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch: Linux:

huggingface-cli download UnfilteredAI_-_UNfilteredAI-1B-exl2 --revision 6_5 --local-dir UNfilteredAI-1B-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download UnfilteredAI_-_UNfilteredAI-1B-exl2 --revision 6_5 --local-dir UNfilteredAI-1B-6.5 --local-dir-use-symlinks False

Original model description:

license: other language:

• en tags:
• UnfilteredAI

---

UNfilteredAI-1B

Model Name: UNfilteredAI-1B Model Type: Text Generation

About the Model

The UNfilteredAI-1B model is a large-scale text generation model developed by UnfilteredAI. This model is designed to push the boundaries of creativity and innovation in AI-generated content, without the constraints of traditional content moderation or filtering.

Key Features

• Uncensored and Unrestricted: The UNfilteredAI-1B model is specifically engineered to generate text without any content restrictions or limitations. This allows for the exploration of a wide range of topics and styles, including potentially controversial or sensitive subject matter.
• Extensive Training: The model has been trained on a vast corpus of diverse textual data, enabling it to generate highly coherent and contextually relevant content across a broad range of domains.
• Versatile Applications: The UNfilteredAI-1B model can be utilized for a variety of text-based tasks, such as creative writing, conversational AI, and even educational or research-oriented applications.

Intended Use

The UNfilteredAI-1B model is intended for use by experienced and responsible AI researchers, developers, and enthusiasts who are interested in pushing the boundaries of language generation and exploring the potential of uncensored AI technologies.

Limitations and Ethical Considerations

• Potential for Misuse: The uncensored nature of the UNfilteredAI-1B model means that it could be used to generate harmful, unethical, or illegal content. Users should exercise caution and responsibility when utilizing this model.
• Bias and Inconsistency: As with many large language models, the UNfilteredAI-1B model may exhibit biases and inconsistencies in its outputs, which could lead to the generation of inaccurate, inappropriate, or even offensive content.
• Sensitive Content: The model is capable of generating explicit, adult-oriented, or otherwise sensitive content. Users should be aware of the potential risks and ensure that the model is used in an appropriate and ethical manner.

UnfilteredAI acknowledges the significant ethical considerations and potential risks associated with the development and deployment of uncensored AI models. We encourage users to engage with this model responsibly and to be mindful of the potential impact of their actions.