First version of the medslabs model and tokenizer.

README.md

@@ -0,0 +1 @@
+Med Labs Cariai

config.json

@@ -0,0 +1,103 @@
+{
+  "_name_or_path": "spanberta-ner",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "eos_token_ids": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-AMOU",
+    "1": "B-CED",
+    "2": "B-CONC",
+    "3": "B-DATE",
+    "4": "B-DOSE",
+    "5": "B-FORM",
+    "6": "B-FREQ",
+    "7": "B-IDTY",
+    "8": "B-LAB",
+    "9": "B-LOC",
+    "10": "B-MED",
+    "11": "B-MISC",
+    "12": "B-ORG",
+    "13": "B-PER",
+    "14": "B-PERI",
+    "15": "B-POS",
+    "16": "B-PROC",
+    "17": "B-ROA",
+    "18": "I-AMOU",
+    "19": "I-CED",
+    "20": "I-CONC",
+    "21": "I-DATE",
+    "22": "I-DOSE",
+    "23": "I-FORM",
+    "24": "I-FREQ",
+    "25": "I-IDTY",
+    "26": "I-LAB",
+    "27": "I-LOC",
+    "28": "I-MED",
+    "29": "I-MISC",
+    "30": "I-ORG",
+    "31": "I-PER",
+    "32": "I-PERI",
+    "33": "I-POS",
+    "34": "I-PROC",
+    "35": "I-ROA",
+    "36": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AMOU": 0,
+    "B-CED": 1,
+    "B-CONC": 2,
+    "B-DATE": 3,
+    "B-DOSE": 4,
+    "B-FORM": 5,
+    "B-FREQ": 6,
+    "B-IDTY": 7,
+    "B-LAB": 8,
+    "B-LOC": 9,
+    "B-MED": 10,
+    "B-MISC": 11,
+    "B-ORG": 12,
+    "B-PER": 13,
+    "B-PERI": 14,
+    "B-POS": 15,
+    "B-PROC": 16,
+    "B-ROA": 17,
+    "I-AMOU": 18,
+    "I-CED": 19,
+    "I-CONC": 20,
+    "I-DATE": 21,
+    "I-DOSE": 22,
+    "I-FORM": 23,
+    "I-FREQ": 24,
+    "I-IDTY": 25,
+    "I-LAB": 26,
+    "I-LOC": 27,
+    "I-MED": 28,
+    "I-MISC": 29,
+    "I-ORG": 30,
+    "I-PER": 31,
+    "I-PERI": 32,
+    "I-POS": 33,
+    "I-PROC": 34,
+    "I-ROA": 35,
+    "O": 36
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df21e50b8a8d4dc770df52adeaac53aa461e8c39578a34c2592abc787ebb5f7
+size 496386543

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": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "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": false, "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, "do_lower_case": false, "special_tokens_map_file": "spanberta-ner/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "spanberta-ner"}