verissimomanoel
commited on
Upload tokenizer
Browse files- arcade100k.tiktoken +0 -0
- special_tokens_map.json +5 -0
- tokenizer_config.json +18 -0
arcade100k.tiktoken
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {},
|
3 |
+
"auto_map": {
|
4 |
+
"AutoTokenizer": [
|
5 |
+
"stabilityai/stablelm-2-zephyr-1_6b--tokenization_arcade100k.Arcade100kTokenizer",
|
6 |
+
null
|
7 |
+
]
|
8 |
+
},
|
9 |
+
"bos_token": "<|endoftext|>",
|
10 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"eos_token": "<|endoftext|>",
|
13 |
+
"errors": "replace",
|
14 |
+
"model_max_length": 2048,
|
15 |
+
"pad_token": "<|endoftext|>",
|
16 |
+
"padding_side": "left",
|
17 |
+
"tokenizer_class": "Arcade100kTokenizer"
|
18 |
+
}
|