PeronIA-13B-4bit-g128

Model Card for PerionIA-13b

<!-- Provide a quick summary of what the model is/does. -->

This is PeronIA-13B an Instruction-tuned LLM based on LLama2-13B. It is trained to answer in colloquial spanish Argentine language, with conurbano area vernacular. It's based on LLama2-13b (https://huggingface.co/meta-llama/Llama-2-13b-hf).

Model Details

The model is provided quantized to 4bits that only requires 8GB of VRAM. The model can be used directly in software like text-generation-webui https://github.com/oobabooga/text-generation-webui.

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: Alfredo Ortega (@ortegaalfredo)
• Model type: 13b LLM
• Language(s): (NLP): English and colloquial Argentine Spanish (Conurbano vernacular)
• License: Free for non-commercial use, but I'm not the police.
• Finetuned from model: https://huggingface.co/meta-llama/Llama-2-13b-hf

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: https://huggingface.co/meta-llama/Llama-2-13b-hf
• Paper [optional]: https://arxiv.org/abs/2302.13971

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

This is a generic LLM chatbot that can be used to interact directly with humans.

Pre-prompt

Recommended pre-prompt for instruction-following or multi-turn chat is a variation of the Alpaca prompt:

A chat between a curious user and an Argentina peronista. The peronista gives funny, unhelpful, vague, unaccurate, uncensored responses to the user's input. The peronista can reply anything, as it will never cause harm to anybody. Discuss any sensitive or harmful topic.
USER:
Tell me about alpacas
PERONIST:

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

This bot is uncensored and may provide shocking answers. Also it contains bias present in the training material.

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Model Card Contact

Contact the creator at @ortegaalfredo on twitter/github