danielhanchen commited on
Commit
b044d3b
1 Parent(s): e7c914b

Upload tokenizer

Browse files
Files changed (2) hide show
  1. README.md +0 -1
  2. tokenizer_config.json +1 -2
README.md CHANGED
@@ -9,7 +9,6 @@ tags:
9
  - gemma
10
  - gemma-2b
11
  - bnb
12
-
13
  ---
14
 
15
  # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
 
9
  - gemma
10
  - gemma-2b
11
  - bnb
 
12
  ---
13
 
14
  # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
tokenizer_config.json CHANGED
@@ -1747,9 +1747,8 @@
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": 8192,
1751
  "pad_token": "<pad>",
1752
- "padding_side": "right",
1753
  "sp_model_kwargs": {},
1754
  "spaces_between_special_tokens": false,
1755
  "tokenizer_class": "GemmaTokenizer",
 
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",