Upload tokenizer

special_tokens_map.json

@@ -16,7 +16,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -404,12 +404,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -425,12 +419,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -442,12 +430,6 @@
           "id": "B",
           "type_id": 1
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 1
-        }
       }
     ],
     "special_tokens": {
@@ -459,15 +441,6 @@
         "tokens": [
           "<s>"
         ]
-      },
-      "<|endoftext|>": {
-        "id": "<|endoftext|>",
-        "ids": [
-          32000
-        ],
-        "tokens": [
-          "<|endoftext|>"
-        ]
       }
     }
   },

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>",
@@ -338,6 +338,7 @@
   "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "legacy": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",