Model Card for Carpincho-13b

This is Carpincho-13B an Instruction-tuned LLM based on LLama-13B. It is trained to answer in colloquial spanish Argentine language. It's based on LLama-13b (https://huggingface.co/decapoda-research/llama-13b-hf).

Model Details

The model is provided in ggml format, for use with the llama.cpp CPU-only LLM inference (https://github.com/ggerganov/llama.cpp)

Usage

Clone the llama.cpp repository:

git clone https://github.com/ggerganov/llama.cpp

Compile the tool:

make

Download the file carpincho-13b-ggml-model-q4_0.bin into the llama.cpp directory and run this command:

./main -m ./carpincho-13b-ggml-model-q4_0.bin -i -ins -t 4

Change -t 4 to the number of physical CPU cores you have.

This model requires at least 8GB of free RAM. No GPU is needed to run llama.cpp.

Model Description

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

Model Sources [optional]

Repository: https://huggingface.co/decapoda-research/llama-13b-hf
Paper [optional]: https://arxiv.org/abs/2302.13971

Uses

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

Bias, Risks, and Limitations

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

Recommendations

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