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 sha256:3fc405ab51c12f3927d4ec1fe6605dedb8cfa63b22f964f878419cf9dfcbb353
-size 17526849
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

tokenizer_config.json

@@ -1993,70 +1993,6 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "256000": {
-      "content": "<thinking>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "256001": {
-      "content": "<reflection>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "256002": {
-      "content": "<cite>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "256003": {
-      "content": "<output>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "256004": {
-      "content": "</thinking>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "256005": {
-      "content": "</reflection>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "256006": {
-      "content": "</cite>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "256007": {
-      "content": "</output>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "additional_special_tokens": [
@@ -2067,8 +2003,9 @@
   "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% if message['role'] == 'assistant' %}{{ eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_of_turn>model\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<eos>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",