Upload tokenizer
Browse files- tokenizer.json +2 -14
- tokenizer_config.json +0 -7
tokenizer.json
CHANGED
|
@@ -1,19 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 2048,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": "BatchLongest",
|
| 11 |
-
"direction": "Right",
|
| 12 |
-
"pad_to_multiple_of": null,
|
| 13 |
-
"pad_id": 100257,
|
| 14 |
-
"pad_type_id": 0,
|
| 15 |
-
"pad_token": "<|endoftext|>"
|
| 16 |
-
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 100256,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 100256,
|
tokenizer_config.json
CHANGED
|
@@ -329,15 +329,8 @@
|
|
| 329 |
"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 %}",
|
| 330 |
"clean_up_tokenization_spaces": true,
|
| 331 |
"eos_token": "</s>",
|
| 332 |
-
"max_length": 2048,
|
| 333 |
"model_max_length": 2048,
|
| 334 |
-
"pad_to_multiple_of": null,
|
| 335 |
"pad_token": "<|endoftext|>",
|
| 336 |
-
"pad_token_type_id": 0,
|
| 337 |
-
"padding_side": "right",
|
| 338 |
-
"stride": 0,
|
| 339 |
"tokenizer_class": "GPT2Tokenizer",
|
| 340 |
-
"truncation_side": "right",
|
| 341 |
-
"truncation_strategy": "longest_first",
|
| 342 |
"unk_token": "<unk>"
|
| 343 |
}
|
|
|
|
| 329 |
"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 %}",
|
| 330 |
"clean_up_tokenization_spaces": true,
|
| 331 |
"eos_token": "</s>",
|
|
|
|
| 332 |
"model_max_length": 2048,
|
|
|
|
| 333 |
"pad_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
| 334 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 335 |
"unk_token": "<unk>"
|
| 336 |
}
|