ClinicalDistilBERT model and tokeniser

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "clinical-models/models/ClinicalDistilBERT/final/model",
+  "_name_or_path": "/users/engs2263/clinical-models/models/ClinicalDistilBERT/final/model",
   "activation": "gelu",
   "adapters": {
     "adapters": {},
@@ -26,6 +26,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.17.0",
+  "transformers_version": "4.27.0.dev0",
   "vocab_size": 28996
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb1dc80bc92fa1693723ff05a194d3e5f8700dbc66758a100be42ff7ec0fda90
-size 263292335
+oid sha256:fda1b5c485698ea0792e89873108ec3e0f51d0dd00780a8c9f7ff6646029a1e5
+size 263281391

special_tokens_map.json

@@ -1 +1,7 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,14 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-cased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}