Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: distilbert/distilgpt2
 tags:
 - generated_from_trainer
+base_model: distilbert/distilgpt2
 model-index:
 - name: medical_chatbot_ruslanmv_ai-medical-chatbot
   results: []

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|startoftext|>": 50257
+}

special_tokens_map.json

@@ -1,6 +1,18 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -9,7 +9,16 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50257,
+      "content": "<|startoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
       "special": true
     }
   ],

tokenizer_config.json

@@ -4,13 +4,21 @@
     "50256": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
+  "bos_token": "<|startoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,