Upload model.

README.md

@@ -1,3 +1,97 @@
 ---
-license: apache-2.0
+
+language:
+
+- ca
+
+tags:
+
+- "catalan"
+
+- "text classification"
+
+- "tecla"
+
+- "CaText"
+
+- "Catalan Textual Corpus"
+
+datasets:
+
+- "projecte-aina/tecla"
+
+metrics:
+- accuracy
+
+model-index:
+- name: roberta-base-ca-v2-cased-tc
+  results:
+  - task:
+      type: text-classification
+    dataset:
+      name: TeCla
+      type: projecte-aina/tecla
+    metrics:
+      - name: Accuracy
+        type: accuracy
+        value: 0.7426
+
+widget:
+
+- text: "Els Pets presenten el seu nou treball al Palau Sant Jordi." 
+
+- text: "Els barcelonins incrementen un 23% l’ús del cotxe des de l’inici de la pandèmia."
+
+- text: "Retards a quatre línies de Rodalies per una avaria entre Sants i plaça de Catalunya."
+
+- text: "Majors de 60 anys i sanitaris començaran a rebre la tercera dosi de la vacuna covid els propers dies."
+
+- text: "Els cinemes Verdi estrenen Verdi Classics, un nou canal de televisió."
+
 ---
+
+# Catalan BERTa-v2 (roberta-base-ca-v2) finetuned for Text Classification.
+
+The **roberta-base-ca-v2-cased-tc** is a Text Classification (TC) model for the Catalan language fine-tuned from the [roberta-base-ca-v2](https://huggingface.co/projecte-aina/roberta-base-ca-v2) model, a [RoBERTa](https://arxiv.org/abs/1907.11692) base model pre-trained on a medium-size corpus collected from publicly available corpora and crawlers (check the roberta-base-ca-v2 model card for more details).
+
+## Datasets
+We used the TC dataset in Catalan called [TeCla](https://huggingface.co/datasets/projecte-aina/tecla) for training and evaluation.
+
+## Evaluation and results
+We evaluated the _roberta-base-ca-v2-cased-tc_ on the TeCla test set against standard multilingual and monolingual baselines:
+
+| Model        | TeCla (Accuracy) | 
+| ------------|:-------------|
+| roberta-base-ca-v2-cased-tc | **74.26** |
+| roberta-base-ca-cased-tc | 73.65 |
+| mBERT       |  69.90 | 
+| XLM-RoBERTa | 70.14 | 
+
+For more details, check the fine-tuning and evaluation scripts in the official [GitHub repository](https://github.com/projecte-aina/club).
+
+## Citing 
+If you use any of these resources (datasets or models) in your work, please cite our latest paper:
+```bibtex
+@inproceedings{armengol-estape-etal-2021-multilingual,
+    title = "Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? {A} Comprehensive Assessment for {C}atalan",
+    author = "Armengol-Estap{\'e}, Jordi  and
+      Carrino, Casimiro Pio  and
+      Rodriguez-Penagos, Carlos  and
+      de Gibert Bonet, Ona  and
+      Armentano-Oller, Carme  and
+      Gonzalez-Agirre, Aitor  and
+      Melero, Maite  and
+      Villegas, Marta",
+    booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
+    month = aug,
+    year = "2021",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2021.findings-acl.437",
+    doi = "10.18653/v1/2021.findings-acl.437",
+    pages = "4933--4946",
+}
+```
+
+### Funding
+This work was funded by the [Catalan Government](https://politiquesdigitals.gencat.cat/en/inici/index.html) within the framework of the [AINA project.](https://politiquesdigitals.gencat.cat/ca/economia/catalonia-ai/aina).

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "projecte-aina/roberta-base-ca-v2-cased-tc",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "tecla",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+      "0": "Medi ambient",
+      "1": "Societat",
+      "2": "Policial",
+      "3": "Judicial",
+      "4": "Empresa",
+      "5": "Partits",
+      "6": "Política",
+      "7": "Successos",
+      "8": "Salut",
+      "9": "Infraestructures",
+      "10": "Parlament",
+      "11": "Música",
+      "12": "Govern",
+      "13": "Unió Europea",
+      "14": "Economia",
+      "15": "Mobilitat",
+      "16": "Treball",
+      "17": "Cultura",
+      "18": "Educació"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+        "Medi ambient": 0,
+        "Societat": 1,
+        "Policial": 2,
+        "Judicial": 3,
+        "Empresa": 4,
+        "Partits": 5,
+        "Política": 6,
+        "Successos": 7,
+        "Salut": 8,
+        "Infraestructures": 9,
+        "Parlament": 10,
+        "Música": 11,
+        "Govern": 12,
+        "Unió Europea": 13,
+        "Economia": 14,
+        "Mobilitat": 15,
+        "Treball": 16,
+        "Cultura": 17,
+        "Educació": 18
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5da19d73d770844b657a2e4489d742af5e843a480c8b5fc46cbb61d1a6698e2
+size 498717165

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "/gpfs/projects/bsc88/BERTs/models/roberta_base_ca_jsc/transformed_lr0.0005"}