Upload tokenizer

special_tokens_map.json

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

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
@@ -160,12 +155,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -175,36 +164,14 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "B",
           "type_id": 1
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 1
-        }
       }
     ],
-    "special_tokens": {
-      "<|endoftext|>": {
-        "id": "<|endoftext|>",
-        "ids": [
-          32000
-        ],
-        "tokens": [
-          "<|endoftext|>"
-        ]
-      }
-    }
+    "special_tokens": {}
   },
   "decoder": {
     "type": "Sequence",

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": false,
-  "add_eos_token": true,
+  "add_eos_token": false,
   "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
@@ -122,7 +122,7 @@
   "eos_token": "<|endoftext|>",
   "legacy": false,
   "model_max_length": 4096,
-  "pad_token": "<unk>",
+  "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",