Upload tokenizer

special_tokens_map.json

@@ -1,9 +1,4 @@
 {
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -18,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 2,
-    "pad_type_id": 0,
-    "pad_token": "</s>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,
@@ -43,23 +31,13 @@
       "special": true
     }
   ],
-  "normalizer": {
-    "type": "Sequence",
-    "normalizers": [
-      {
-        "type": "Prepend",
-        "prepend": "▁"
-      },
-      {
-        "type": "Replace",
-        "pattern": {
-          "String": " "
-        },
-        "content": "▁"
-      }
-    ]
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "prepend_scheme": "first",
+    "split": false
   },
-  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
@@ -74,12 +52,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -95,12 +67,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -112,24 +78,9 @@
           "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,
   "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
@@ -28,27 +28,16 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
-  ],
+  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
-  "max_length": 512,
+  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
-  "pad_token": "</s>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
+  "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }