Add colab link

README.md

@@ -13,13 +13,17 @@ inference: false
 
 ## 🦙🇧🇷 Alpaca-LoRA-PTBR: Low-Rank LLaMA Instruct-Tuning
 
+<a target="_blank" href="https://colab.research.google.com/github/DominguesM/alpaca-lora-ptbr-7b/blob/main/notebooks/03%20-%20Evaluate.ipynb">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+</a>
+
 </br>
 
 <img align="left" style="margin-right: 20px;" height="120" src="https://huggingface.co/dominguesm/alpaca-lora-ptbr-7b/resolve/main/assets/alpaca_br_juliet_2.jpg">
 
 **This model was trained and made available solely and exclusively for research purposes.**
 
-Try the pretrained model out on Colab here! (**WIP**)
+Try the pretrained model out on Colab [here](https://colab.research.google.com/github/DominguesM/alpaca-lora-ptbr-7b/blob/main/notebooks/03%20-%20Evaluate.ipynb)!
 
 This repository contains a [low-ranked adapter (LoRa)](https://arxiv.org/pdf/2106.09685.pdf) for LLaMA-7b fit on the [**Stanford Alpaca dataset**](https://github.com/tatsu-lab/stanford_alpaca) translated into **Brazilian Portuguese** using the [**Helsinki-NLP/opus-mt-tc-big-en-pt**](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-pt) model.