Upload tokenizer

special_tokens_map.json

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

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