Bronya Zaychik V13. Resized Embeddings for PAD token

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32001
+}

special_tokens_map.json

@@ -13,6 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 4096,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -29,6 +34,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32001,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {
@@ -32134,7 +32148,8 @@
       "왕": 31996,
       "收": 31997,
       "弘": 31998,
-      "给": 31999
+      "给": 31999,
+      "<pad": 32000
     },
     "merges": [
       "▁ t",

tokenizer_config.json

@@ -19,7 +19,14 @@
   },
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",