Upload tokenizer
Browse files- dialog/added_tokens.json +3 -0
- dialog/special_tokens_map.json +9 -0
- dialog/tokenizer.json +9 -0
- dialog/tokenizer_config.json +12 -1
- entity/tokenizer_config.json +1 -1
- word/added_tokens.json +3 -0
- word/special_tokens_map.json +9 -0
- word/tokenizer.json +9 -0
- word/tokenizer_config.json +12 -1
dialog/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<item>": 50257
|
3 |
+
}
|
dialog/special_tokens_map.json
CHANGED
@@ -1,4 +1,13 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<|endoftext|>",
|
4 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<item>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
}
|
10 |
+
],
|
11 |
"bos_token": {
|
12 |
"content": "<|endoftext|>",
|
13 |
"lstrip": false,
|
dialog/tokenizer.json
CHANGED
@@ -11,6 +11,15 @@
|
|
11 |
"rstrip": false,
|
12 |
"normalized": true,
|
13 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
}
|
15 |
],
|
16 |
"normalizer": null,
|
|
|
11 |
"rstrip": false,
|
12 |
"normalized": true,
|
13 |
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 50257,
|
17 |
+
"content": "<item>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
}
|
24 |
],
|
25 |
"normalizer": null,
|
dialog/tokenizer_config.json
CHANGED
@@ -9,10 +9,21 @@
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
}
|
13 |
},
|
|
|
|
|
|
|
14 |
"bos_token": "<|endoftext|>",
|
15 |
-
"chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
|
16 |
"clean_up_tokenization_spaces": true,
|
17 |
"eos_token": "<|endoftext|>",
|
18 |
"errors": "replace",
|
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "<item>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
}
|
21 |
},
|
22 |
+
"additional_special_tokens": [
|
23 |
+
"<item>"
|
24 |
+
],
|
25 |
"bos_token": "<|endoftext|>",
|
26 |
+
"chat_template": "{% for message in messages %}{{ message.role + '\n' + message.content | replace('<e>', '') | replace('</e>', '') | replace('_', ' ') }}{{ eos_token }}{% endfor %}{{ 'assistant\n' }}",
|
27 |
"clean_up_tokenization_spaces": true,
|
28 |
"eos_token": "<|endoftext|>",
|
29 |
"errors": "replace",
|
entity/tokenizer_config.json
CHANGED
@@ -56505,7 +56505,7 @@
|
|
56505 |
"special": false
|
56506 |
}
|
56507 |
},
|
56508 |
-
"chat_template": "{% for message in messages %}{
|
56509 |
"clean_up_tokenization_spaces": true,
|
56510 |
"init_inputs": [
|
56511 |
[
|
|
|
56505 |
"special": false
|
56506 |
}
|
56507 |
},
|
56508 |
+
"chat_template": "{% for message in messages %}{{ message.content + ' ' }}{% endfor %}",
|
56509 |
"clean_up_tokenization_spaces": true,
|
56510 |
"init_inputs": [
|
56511 |
[
|
word/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<item>": 50265
|
3 |
+
}
|
word/special_tokens_map.json
CHANGED
@@ -1,4 +1,13 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"cls_token": "<s>",
|
4 |
"eos_token": "</s>",
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<item>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
}
|
10 |
+
],
|
11 |
"bos_token": "<s>",
|
12 |
"cls_token": "<s>",
|
13 |
"eos_token": "</s>",
|
word/tokenizer.json
CHANGED
@@ -47,6 +47,15 @@
|
|
47 |
"rstrip": false,
|
48 |
"normalized": false,
|
49 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
}
|
51 |
],
|
52 |
"normalizer": null,
|
|
|
47 |
"rstrip": false,
|
48 |
"normalized": false,
|
49 |
"special": true
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 50265,
|
53 |
+
"content": "<item>",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"special": true
|
59 |
}
|
60 |
],
|
61 |
"normalizer": null,
|
word/tokenizer_config.json
CHANGED
@@ -40,10 +40,21 @@
|
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
}
|
44 |
},
|
|
|
|
|
|
|
45 |
"bos_token": "<s>",
|
46 |
-
"chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
|
47 |
"clean_up_tokenization_spaces": true,
|
48 |
"cls_token": "<s>",
|
49 |
"eos_token": "</s>",
|
|
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
43 |
+
},
|
44 |
+
"50265": {
|
45 |
+
"content": "<item>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
}
|
52 |
},
|
53 |
+
"additional_special_tokens": [
|
54 |
+
"<item>"
|
55 |
+
],
|
56 |
"bos_token": "<s>",
|
57 |
+
"chat_template": "{% for message in messages %}{{ message.role + '\n' + message.content | replace('<e>', '') | replace('</e>', '') | replace('_', ' ') }}{{ eos_token }}{% endfor %}",
|
58 |
"clean_up_tokenization_spaces": true,
|
59 |
"cls_token": "<s>",
|
60 |
"eos_token": "</s>",
|