Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +4 -0
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95bcd63551d6a3ed47b5cb623b034ce28c7d19d84441b84f2b84ad1120f01e47
|
3 |
+
size 17518624
|
tokenizer_config.json
CHANGED
@@ -1747,11 +1747,15 @@
|
|
1747 |
"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 %}",
|
1748 |
"clean_up_tokenization_spaces": false,
|
1749 |
"eos_token": "<eos>",
|
|
|
1750 |
"model_max_length": 1000000000000000019884624838656,
|
1751 |
"pad_token": "<pad>",
|
1752 |
"sp_model_kwargs": {},
|
1753 |
"spaces_between_special_tokens": false,
|
|
|
1754 |
"tokenizer_class": "GemmaTokenizer",
|
|
|
|
|
1755 |
"unk_token": "<unk>",
|
1756 |
"use_default_system_prompt": false
|
1757 |
}
|
|
|
1747 |
"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 %}",
|
1748 |
"clean_up_tokenization_spaces": false,
|
1749 |
"eos_token": "<eos>",
|
1750 |
+
"max_length": 3800,
|
1751 |
"model_max_length": 1000000000000000019884624838656,
|
1752 |
"pad_token": "<pad>",
|
1753 |
"sp_model_kwargs": {},
|
1754 |
"spaces_between_special_tokens": false,
|
1755 |
+
"stride": 0,
|
1756 |
"tokenizer_class": "GemmaTokenizer",
|
1757 |
+
"truncation_side": "right",
|
1758 |
+
"truncation_strategy": "longest_first",
|
1759 |
"unk_token": "<unk>",
|
1760 |
"use_default_system_prompt": false
|
1761 |
}
|