First version of biobertpt-all model and tokenizer.

README.md

@@ -1 +1,24 @@
-"hello" 
+<img src="https://raw.githubusercontent.com/HAILab-PUCPR/BioBERTpt/master/logo-biobertpr1.png" alt="Logo BioBERTpt">
+
+# BioBERTpt - Portuguese Clinical and Biomedical BERT
+
+The [BioBERTpt - A Portuguese Neural Language Model for Clinical Named Entity Recognition](https://www.aclweb.org/anthology/2020.clinicalnlp-1.7/) paper contains clinical and biomedical BERT-based models for Portuguese Language, initialized with BERT-Multilingual-Cased & trained on clinical notes and biomedical literature. 
+
+This model card describes the BioBERTpt(all) model, a full version with clinical narratives and biomedical literature in Portuguese language. 
+
+## How to use the model
+
+Load the model via the transformers library:
+```
+from transformers import AutoTokenizer, AutoModel
+tokenizer = AutoTokenizer.from_pretrained("pucpr/biobertpt-all")
+model = AutoModel.from_pretrained("pucpr/biobertpt-all")
+```
+
+## More Information
+
+Refer to the original paper, [BioBERTpt - A Portuguese Neural Language Model for Clinical Named Entity Recognition](https://www.aclweb.org/anthology/2020.clinicalnlp-1.7/) for additional details and performance on Portuguese NER tasks.
+
+## Questions?
+
+Post a Github issue on the [BioBERTpt repo](https://github.com/HAILab-PUCPR/BioBERTpt).

config.json

@@ -0,0 +1,57 @@
+{
+  "_num_labels": 2,
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "directionality": "bidi",
+  "do_sample": false,
+  "early_stopping": false,
+  "eos_token_ids": null,
+  "finetuning_task": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 512,
+  "min_length": 0,
+  "model_type": "bert",
+  "no_repeat_ngram_size": 0,
+  "num_attention_heads": 12,
+  "num_beams": 1,
+  "num_hidden_layers": 12,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_past": true,
+  "pad_token_id": null,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "pruned_heads": {},
+  "repetition_penalty": 1.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "type_vocab_size": 2,
+  "use_bfloat16": false,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6351c9e5220971b536c32884ee3711bcf1f1da5bb186312a6b44f1fc2c26817
+size 714311810

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049ae81a141d362f6fcf829395db9c7b1f44ffebd5c30e8636376e1a57f59489
+size 711690400

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "max_len": 512}