Downloads · 30 days
0
ortegaalfredo/carpincho-13b-ggml-q4
carpincho-13b-ggml-q4 is a machine learning model from ortegaalfredo. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
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).
Downloads · 30 days
0
Access
Public
Updated May 18, 2023
Repo size
16.3 GB
Likes
2
Public
Click a slice to open those files.
.bin8.1 GB · 100%
From the Hugging Face model README
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).
The model is provided in ggml format, for use with the llama.cpp CPU-only LLM inference (https://github.com/ggerganov/llama.cpp)
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.
This is a generic LLM chatbot that can be used to interact directly with humans.
This bot is uncensored and may provide shocking answers. Also it contains bias present in the training material.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
Contact the creator at @ortegaalfredo on twitter/github