Upload tokenizer

special_tokens_map.json

@@ -18,7 +18,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<eos>",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cb779a1eb2eb8017531c657f505134b83ca3ee16599f601354216a0282c840
-size 17518624
+oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
+size 17518525

tokenizer_config.json

@@ -1747,15 +1747,11 @@
   "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% 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' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
-  "max_length": 3500,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<eos>",
+  "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "GemmaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }