Upload tokenizer

special_tokens_map.json

@@ -17,7 +17,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<eos>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589010dea7549124effd1492249c97eda9e370cb025f963d1f8fcbeb0bd02d2e
-size 17478369
+oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",
@@ -60,9 +60,9 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
   "legacy": null,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<eos>",
-  "padding_side": "left",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",