First version of the bert model for clinical tempeval. Produces time expressions with time classes and events with DocTimeRels

added_tokens.json

@@ -0,0 +1 @@
+{"</e>": 50266, "<a2>": 50269, "<e>": 50265, "<a1>": 50267, "</a1>": 50268, "<neg>": 50272, "<cr>": 50271, "</a2>": 50270}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "CnlpRobertaForClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": [
+    "timex",
+    "event"
+  ],
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.3.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50273
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127bdecf14a82f80d2fdfc2f3b182bd09fcbdd6d67b2e7a6c56b9e231f8060e0
+size 501094041

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"], "model_max_length": 512, "name_or_path": "roberta-base"}