Update README.md

README.md

@@ -23,7 +23,7 @@ Nace en los montes Universales, en la sierra de Albarracín, sobre la rama occid
 
 This is a basic implementation of the multilingual model ["ixambert-base-cased"](https://huggingface.co/ixa-ehu/ixambert-base-cased), fine-tuned on SQuAD v1.1, that is able to answer basic factual questions in English, Spanish and Basque. This model reaches a F1 score of 89.1 on the SQuAD 1.1 dev set.
 
-# Overview
+## Overview
 
 **Language model:** ixambert-base-cased
 **Languages:** English, Spanish and Basque
@@ -32,7 +32,7 @@ This is a basic implementation of the multilingual model ["ixambert-base-cased"]
 **Eval data:** SQuAD v1.1
 **Infrastructure:** 1x GeForce RTX 2080
 
-### Outputs
+## Outputs
 
 The model outputs the answer to the question, the start and end positions of the answer in the original context, and a score for the probability for that span of text to be the correct answer. For example:
 
@@ -40,7 +40,7 @@ The model outputs the answer to the question, the start and end positions of the
 {'score': 0.9667195081710815, 'start': 101, 'end': 105, 'answer': '1820'}
 ```
 
-### How to use
+## How to use
 
 ```python
 from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
@@ -58,7 +58,7 @@ model = AutoModelForQuestionAnswering.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 ```
 
-### Hyperparameters
+## Hyperparameters
 
 ```
 batch_size = 8