[feat] Added first version of model and tokenizer.

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "dpalominop/biobert-giotto",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "do_lower_case": false,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.5.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65623fa74d14b08c3c31e695a40be415b66a7f01ba41be2cc03f0970f2c9e8ae
+size 433453330

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, "max_len": 512, "special_tokens_map_file": "/home/jovyan/.cache/huggingface/transformers/65d582748e4126e85861f641572937b543935995a2ffc620e0ae90a86404bfa9.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "monologg/biobert_v1.0_pubmed_pmc"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9355e4b31d7d3d5d572a4eefe9e2cbfc36d572334cd9698ee52822b6f7cc2ba
+size 2351