Upload tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +2 -2
- tokenizer.json +19 -8
- tokenizer_config.json +51 -5
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 32000,
|
3 |
+
"<|im_start|>": 32001
|
4 |
+
}
|
special_tokens_map.json
CHANGED
@@ -7,13 +7,13 @@
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "</s>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,14 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
-
"padding":
|
5 |
-
"strategy": "BatchLongest",
|
6 |
-
"direction": "Left",
|
7 |
-
"pad_to_multiple_of": null,
|
8 |
-
"pad_id": 1,
|
9 |
-
"pad_type_id": 0,
|
10 |
-
"pad_token": "<s>"
|
11 |
-
},
|
12 |
"added_tokens": [
|
13 |
{
|
14 |
"id": 0,
|
@@ -36,6 +29,24 @@
|
|
36 |
"rstrip": false,
|
37 |
"normalized": false,
|
38 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
}
|
40 |
],
|
41 |
"normalizer": {
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 32000,
|
35 |
+
"content": "<|im_end|>",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 32001,
|
44 |
+
"content": "<|im_start|>",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"special": false
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -25,19 +25,65 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
-
"bos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
"legacy": true,
|
36 |
"model_max_length": 1000000000000000019884624838656,
|
37 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
-
"
|
42 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
}
|
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|im_end|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|im_start|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
}
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
47 |
+
"bos_token": {
|
48 |
+
"__type": "AddedToken",
|
49 |
+
"content": "<s>",
|
50 |
+
"lstrip": false,
|
51 |
+
"normalized": true,
|
52 |
+
"rstrip": false,
|
53 |
+
"single_word": false
|
54 |
+
},
|
55 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
56 |
"clean_up_tokenization_spaces": false,
|
57 |
+
"eos_token": {
|
58 |
+
"__type": "AddedToken",
|
59 |
+
"content": "<|im_end|>",
|
60 |
+
"lstrip": false,
|
61 |
+
"normalized": true,
|
62 |
+
"rstrip": false,
|
63 |
+
"single_word": false
|
64 |
+
},
|
65 |
"legacy": true,
|
66 |
"model_max_length": 1000000000000000019884624838656,
|
67 |
+
"pad_token": {
|
68 |
+
"__type": "AddedToken",
|
69 |
+
"content": "</s>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false
|
74 |
+
},
|
75 |
"sp_model_kwargs": {},
|
76 |
"spaces_between_special_tokens": false,
|
77 |
"tokenizer_class": "LlamaTokenizer",
|
78 |
+
"trust_remote_code": true,
|
79 |
+
"unk_token": {
|
80 |
+
"__type": "AddedToken",
|
81 |
+
"content": "<unk>",
|
82 |
+
"lstrip": false,
|
83 |
+
"normalized": true,
|
84 |
+
"rstrip": false,
|
85 |
+
"single_word": false
|
86 |
+
},
|
87 |
+
"use_default_system_prompt": false,
|
88 |
+
"use_fast": true
|
89 |
}
|