Tucano-2b4-Instruct-fp16-ov

<img src="./logotucano.png" alt="An illustration of a Tucano bird showing vibrant colors like yellow, orange, blue, green, and black." height="200">

Maintainer: Alessandro de Oliveira Faria - CABELO

Tucano-2b4-Instruct-fp16-ov

• Model creator: TucanoBR
• Original model: Tucano-2b4-Instruct

Description

Tucano OpenVINO is the version of the Tucano model ported to Intel openVINO inference technology. Tucano is a series of decoder-transformers natively pretrained in Portuguese. All Tucano models were trained on GigaVerbo, a concatenation of deduplicated Portuguese text corpora amounting to 200 billion tokens.

Read our preprint here. Read our preprint here.

Usage

We provide a reference implementation of Tucano OpenVINO, as well as sampling code, in a dedicated github repository.

Compatibility

The provided OpenVINO™ IR model is compatible with:

• OpenVINO version 2024.5.0 and higher
• Optimum Intel 1.21.0 and higher

Running Model Inference with Optimum Intel

1. Install packages required for using Optimum Intel integration with the OpenVINO backend:

pip install optimum[openvino]

1. Run model inference:

from transformers import AutoTokenizer
from optimum.intel.openvino import OVModelForCausalLM

model_id = "cabelo/Tucano-2b4-Instruct-fp16-ov"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(model_id)

inputs = tokenizer("O que é Carnaval?", return_tensors="pt")

outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)

For more examples and possible optimizations, refer to the OpenVINO Large Language Model Inference Guide.

Running Model Inference with OpenVINO GenAI

1. Install packages required for using OpenVINO GenAI.

pip install openvino-genai huggingface_hub

1. Download model from HuggingFace Hub

import huggingface_hub as hf_hub

model_id = "cabelo/Tucano-2b4-Instruct-fp16-ov"
model_path = "Tucano-2b4-Instruct-fp16-ov"

hf_hub.snapshot_download(model_id, local_dir=model_path)

1. Run model inference:

import openvino_genai as ov_genai

device = "CPU"
pipe = ov_genai.LLMPipeline(model_path, device)
print(pipe.generate("O que é OpenVINO?", max_length=200))

More GenAI usage examples can be found in OpenVINO GenAI library docs and samples

Limitations

Check the original model card for original model card for limitations.

Legal information

The original model is distributed under gemma license. More details can be found in original model card.

Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel’s Global Human Rights Principles. Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.