Upload tokenizer

special_tokens_map.json

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

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -404,12 +409,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -425,12 +424,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -442,12 +435,6 @@
           "id": "B",
           "type_id": 1
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 1
-        }
       }
     ],
     "special_tokens": {
@@ -459,15 +446,6 @@
         "tokens": [
           "<s>"
         ]
-      },
-      "<|endoftext|>": {
-        "id": "<|endoftext|>",
-        "ids": [
-          32000
-        ],
-        "tokens": [
-          "<|endoftext|>"
-        ]
       }
     }
   },
@@ -503,6 +481,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

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>",
@@ -340,8 +340,8 @@
   "eos_token": "<|endoftext|>",
   "legacy": false,
   "model_max_length": 4096,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "left",
+  "pad_token": "<unk>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",