Upload tokenizer

README.md

@@ -1,19 +1,18 @@
 ---
-license: mit
 language:
 - fr
-pipeline_tag: fill-mask
+license: mit
+library_name: transformers
 tags:
 - biomedical
 - clinical
 - life sciences
 datasets:
 - rntc/biomed-fr
+pipeline_tag: fill-mask
 widget:
-- text: >-
-    Les médicaments <mask> typiques sont largement utilisés dans le traitement
+- text: Les médicaments <mask> typiques sont largement utilisés dans le traitement
     de première intention des patients schizophrènes.
-library_name: transformers
 ---
 
 <a href=https://camembert-bio-model.fr/>

special_tokens_map.json

@@ -1,7 +1,8 @@
 {
   "additional_special_tokens": [
     "<s>NOTUSED",
-    "</s>NOTUSED"
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
   ],
   "bos_token": "<s>",
   "cls_token": "<s>",

tokenizer.json

@@ -31,7 +31,7 @@
       "special": true
     },
     {
-      "id": 4,
+      "id": 3,
       "content": "<unk>",
       "single_word": false,
       "lstrip": false,
@@ -39,6 +39,15 @@
       "normalized": false,
       "special": true
     },
+    {
+      "id": 4,
+      "content": "<unk>NOTUSED",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
     {
       "id": 5,
       "content": "<s>",
@@ -80,7 +89,8 @@
       {
         "type": "Metaspace",
         "replacement": "▁",
-        "add_prefix_space": true
+        "prepend_scheme": "always",
+        "split": true
       }
     ]
   },
@@ -168,7 +178,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "prepend_scheme": "always",
+    "split": true
   },
   "model": {
     "type": "Unigram",
@@ -191,7 +202,7 @@
         0.0
       ],
       [
-        "<unk>",
+        "<unk>NOTUSED",
         -100.0
       ],
       [
@@ -128194,6 +128205,7 @@
         "<mask>",
         0.0
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,24 +1,83 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "additional_special_tokens": [
     "<s>NOTUSED",
-    "</s>NOTUSED"
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
   ],
   "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "camembert-base",
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "special_tokens_map_file": null,
   "tokenizer_class": "CamembertTokenizer",
   "unk_token": "<unk>"
 }