First comit

README.md

@@ -1,3 +1,32 @@
 ---
+language: pt
 license: apache-2.0
+
+widget:
+- text: "O futuro de DI caiu 20 bps nesta manhã"
+  example_title: "Example 1"
+- text: "O Nubank decidiu cortar a faixa de preço da oferta pública inicial (IPO) após revés no humor dos mercados internacionais com as fintechs."
+  example_title: "Example 2"
+- text: "O Ibovespa acompanha correção do mercado e fecha com alta moderada"
+  example_title: "Example 3"
 ---
+
+# FinBertPTBR : Financial Bert PT BR
+
+FinBertPTBR is a pre-trained NLP model to analyze sentiment of Brazilian Portuguese financial texts. It is built by further training the BERTimbau language model in the finance domain, using a large financial corpus and thereby fine-tuning it for financial sentiment classification.
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModel
+  
+tokenizer = AutoTokenizer.from_pretrained("turing-usp/FinBertPTBR")
+model = AutoModel.from_pretrained("turing-usp/FinBertPTBR")
+```
+
+## Authors
+
+  - [Vinicius Carmo](https://www.linkedin.com/in/vinicius-cleves/)
+  - [Julia Pocciotti](https://www.linkedin.com/in/juliapocciotti/)
+  - [Luísa Heise](https://www.linkedin.com/in/lu%C3%ADsa-mendes-heise/)
+  - [Lucas Leme](https://www.linkedin.com/in/lucas-leme-santos/)
+  

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "/content/drive/Shareddrives/Pesquisa AI + Financ\u0327as/Modelos/language_model/FinBERT PT BR",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123352c03b252152acc9d71e6678aad015d9cd5200e4c4abc5f5cc20a48c6866
+size 435772781

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/leme/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "neuralmind/bert-base-portuguese-cased", "tokenizer_class": "BertTokenizer"}