Upload tokenizer

README.md

@@ -1,15 +1,15 @@
 ---
+language:
+- de
+license: apache-2.0
 library_name: transformers
 tags:
 - deutsch
 - german
 - seedbox
 - mistral
-license: apache-2.0
 datasets:
 - seedboxai/multitask_german_examples_32k
-language:
-- de
 pipeline_tag: text-generation
 ---
 

special_tokens_map.json

@@ -18,13 +18,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<unk>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -67,12 +67,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -88,12 +82,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -105,24 +93,9 @@
           "id": "B",
           "type_id": 1
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 1
-        }
       }
     ],
     "special_tokens": {
-      "</s>": {
-        "id": "</s>",
-        "ids": [
-          2
-        ],
-        "tokens": [
-          "</s>"
-        ]
-      },
       "<s>": {
         "id": "<s>",
         "ids": [

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",