Update README.md

README.md

@@ -18,7 +18,7 @@ widget:
 - text: "Catalunya és una referència en <mask> a nivell europeu."
 ---
 
-# [TODO: MODEL_NAME]
+# DistilBerta-base
 
 ## Table of Contents
 <details>
@@ -42,10 +42,10 @@ widget:
 </details>
 
 ## Overview
-- **Architecture:** [TODO: roberta-base/roberta-large/bart...]
-- **Language:** [TODO: Catalan/Spanish...]
-- **Task:** [TODO: Text Classification / Extractive QA...]
-- **Data:** [TODO: BNE/Tecla/Teca/Pharmaconer...]
+- **Architecture:** DistilRoBERTa
+- **Language:** Catalan
+- **Task:** Fill-Mask
+- **Data:** Crawling
 
 
 ## Model description
@@ -61,8 +61,7 @@ widget:
 ## How to use
 
 ```python
-from transformers import AutoModel, AutoTokenizer, pipeline
-from datasets import load_dataset
+from transformers import pipeline
 [TODO: Add minimal code here]
 ```
 
@@ -105,24 +104,25 @@ The training corpus consists of several corpora gathered from web crawling and p
 
 ### Evaluation results
 
+This model has been fine-tuned on the downstream tasks of the Catalan Language Understanding Evaluation benchmark (CLUB).
+
 | Task        | NER (F1)      | POS (F1)   | STS-ca (Comb)   | TeCla (Acc.) | TEca (Acc.) | VilaQuAD (F1/EM)| ViquiQuAD (F1/EM) | CatalanQA (F1/EM) | XQuAD-ca <sup>1</sup> (F1/EM) | 
 | ------------|:-------------:| -----:|:------|:------|:-------|:------|:----|:----|:----|
-| RoBERTa-large-ca-v2        | **89.82** | **99.02** | **83.41** | **75.46** | **83.61** | **89.34/75.50** | **89.20**/75.77 | **90.72/79.06** | **73.79**/55.34 |
-| RoBERTa-base-ca-v2      | 89.29 | 98.96 | 79.07 | 74.26 | 83.14 | 87.74/72.58 | 88.72/**75.91** | 89.50/76.63 | 73.64/**55.42** |
+| RoBERTa-large-ca-v2        | 89.82 | 99.02 | 83.41 | 75.46 | 83.61 | 89.34/75.50 | 89.20/75.77 | 90.72/79.06 | 73.79/55.34 |
+| RoBERTa-base-ca-v2      | 89.29 | 98.96 | 79.07 | 74.26 | 83.14 | 87.74/72.58 | 88.72/75.91 | 89.50/76.63 | 73.64/55.42 |
 | DistilRoBERTa-base-ca-v2| xx.xx | xx.xx | xx.xx | xx.xx | xx.xx | xx.xx/xx.xx | xx.xx/xx.xx | xx.xx/xx.xx | xx.xx/xx.xx |
 
 <sup>1</sup> : Trained on CatalanQA, tested on XQuAD-ca.
 
-
 ## Additional Information
 
 ### Authors 
 
-Text Mining Unit (TeMU) at the Barcelona Supercomputing Center (bsc-temu@bsc.es).
+The Text Mining Unit (TeMU) from Barcelona Supercomputing Center ([bsc-temu@bsc.es](bsc-temu@bsc.es)).
 
 ### Contact information
 
-For further information, send an email to aina@bsc.es.
+For further information, send an email to [aina@bsc.es](aina@bsc.es).
 
 ## Copyright