Upload tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +5 -1
- tokenizer.json +18 -0
- tokenizer_config.json +23 -4
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|end_of_turn|>": 32000,
|
| 3 |
+
"<|pad_0|>": 32001
|
| 4 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,8 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
|
@@ -7,7 +11,7 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|end_of_turn|>",
|
| 4 |
+
"<|pad_0|>"
|
| 5 |
+
],
|
| 6 |
"bos_token": {
|
| 7 |
"content": "<s>",
|
| 8 |
"lstrip": false,
|
|
|
|
| 11 |
"single_word": false
|
| 12 |
},
|
| 13 |
"eos_token": {
|
| 14 |
+
"content": "<|end_of_turn|>",
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": false,
|
| 17 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -34,6 +34,24 @@
|
|
| 34 |
"rstrip": false,
|
| 35 |
"normalized": false,
|
| 36 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
}
|
| 38 |
],
|
| 39 |
"normalizer": {
|
|
|
|
| 34 |
"rstrip": false,
|
| 35 |
"normalized": false,
|
| 36 |
"special": true
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"id": 32000,
|
| 40 |
+
"content": "<|end_of_turn|>",
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"normalized": false,
|
| 45 |
+
"special": true
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"id": 32001,
|
| 49 |
+
"content": "<|pad_0|>",
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"normalized": false,
|
| 54 |
+
"special": true
|
| 55 |
}
|
| 56 |
],
|
| 57 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -25,13 +25,32 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
| 31 |
"bos_token": "<s>",
|
| 32 |
-
"chat_template": "{{ bos_token }}{% for message in messages %}{
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
-
"eos_token": "
|
| 35 |
"legacy": true,
|
| 36 |
"max_length": 2048,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
|
@@ -43,5 +62,5 @@
|
|
| 43 |
"truncation_side": "right",
|
| 44 |
"truncation_strategy": "longest_first",
|
| 45 |
"unk_token": "<unk>",
|
| 46 |
-
"use_default_system_prompt":
|
| 47 |
}
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<|end_of_turn|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32001": {
|
| 38 |
+
"content": "<|pad_0|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
}
|
| 45 |
},
|
| 46 |
+
"additional_special_tokens": [
|
| 47 |
+
"<|end_of_turn|>",
|
| 48 |
+
"<|pad_0|>"
|
| 49 |
+
],
|
| 50 |
"bos_token": "<s>",
|
| 51 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
|
| 52 |
"clean_up_tokenization_spaces": false,
|
| 53 |
+
"eos_token": "<|end_of_turn|>",
|
| 54 |
"legacy": true,
|
| 55 |
"max_length": 2048,
|
| 56 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 62 |
"truncation_side": "right",
|
| 63 |
"truncation_strategy": "longest_first",
|
| 64 |
"unk_token": "<unk>",
|
| 65 |
+
"use_default_system_prompt": true
|
| 66 |
}
|