Upload tokenizer
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +0 -4
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 2048,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
tokenizer_config.json
CHANGED
@@ -305,12 +305,8 @@
|
|
305 |
"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 %}",
|
306 |
"clean_up_tokenization_spaces": true,
|
307 |
"eos_token": "<|endoftext|>",
|
308 |
-
"max_length": 2048,
|
309 |
"model_max_length": 2048,
|
310 |
"pad_token": "<|endoftext|>",
|
311 |
-
"stride": 0,
|
312 |
"tokenizer_class": "GPT2Tokenizer",
|
313 |
-
"truncation_side": "right",
|
314 |
-
"truncation_strategy": "longest_first",
|
315 |
"unk_token": "<|endoftext|>"
|
316 |
}
|
|
|
305 |
"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 %}",
|
306 |
"clean_up_tokenization_spaces": true,
|
307 |
"eos_token": "<|endoftext|>",
|
|
|
308 |
"model_max_length": 2048,
|
309 |
"pad_token": "<|endoftext|>",
|
|
|
310 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
311 |
"unk_token": "<|endoftext|>"
|
312 |
}
|