Upload tokenizer
Browse files- added_tokens.json +7 -0
- special_tokens_map.json +4 -3
- tokenizer.json +18 -0
- tokenizer.model +3 -0
- tokenizer_config.json +24 -5
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0,
|
5 |
+
"<|im_end|>": 32000,
|
6 |
+
"<|im_start|>": 32001
|
7 |
+
}
|
special_tokens_map.json
CHANGED
@@ -2,10 +2,11 @@
|
|
2 |
"additional_special_tokens": [
|
3 |
"<unk>",
|
4 |
"<s>",
|
5 |
-
"</s>"
|
|
|
6 |
],
|
7 |
"bos_token": "<s>",
|
8 |
-
"eos_token": "
|
9 |
-
"pad_token": "
|
10 |
"unk_token": "<unk>"
|
11 |
}
|
|
|
2 |
"additional_special_tokens": [
|
3 |
"<unk>",
|
4 |
"<s>",
|
5 |
+
"</s>",
|
6 |
+
"<|im_end|>"
|
7 |
],
|
8 |
"bos_token": "<s>",
|
9 |
+
"eos_token": "<|im_end|>",
|
10 |
+
"pad_token": "<|im_end|>",
|
11 |
"unk_token": "<unk>"
|
12 |
}
|
tokenizer.json
CHANGED
@@ -27,8 +27,26 @@
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
+
"normalized": true,
|
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": false,
|
49 |
+
"special": false
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
CHANGED
@@ -19,27 +19,46 @@
|
|
19 |
"2": {
|
20 |
"content": "</s>",
|
21 |
"lstrip": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
},
|
28 |
"additional_special_tokens": [
|
29 |
"<unk>",
|
30 |
"<s>",
|
31 |
-
"</s>"
|
|
|
32 |
],
|
33 |
"bos_token": "<s>",
|
34 |
-
"chat_template": "{
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
-
"eos_token": "
|
37 |
"legacy": true,
|
38 |
"model_max_length": 1000000000000000019884624838656,
|
39 |
-
"pad_token": "
|
40 |
"sp_model_kwargs": {},
|
41 |
"spaces_between_special_tokens": false,
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
43 |
"unk_token": "<unk>",
|
44 |
-
"use_default_system_prompt": true
|
|
|
45 |
}
|
|
|
19 |
"2": {
|
20 |
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"32000": {
|
28 |
+
"content": "<|im_end|>",
|
29 |
+
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
+
},
|
35 |
+
"32001": {
|
36 |
+
"content": "<|im_start|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
}
|
43 |
},
|
44 |
"additional_special_tokens": [
|
45 |
"<unk>",
|
46 |
"<s>",
|
47 |
+
"</s>",
|
48 |
+
"<|im_end|>"
|
49 |
],
|
50 |
"bos_token": "<s>",
|
51 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
52 |
"clean_up_tokenization_spaces": false,
|
53 |
+
"eos_token": "<|im_end|>",
|
54 |
"legacy": true,
|
55 |
"model_max_length": 1000000000000000019884624838656,
|
56 |
+
"pad_token": "<|im_end|>",
|
57 |
"sp_model_kwargs": {},
|
58 |
"spaces_between_special_tokens": false,
|
59 |
"tokenizer_class": "LlamaTokenizer",
|
60 |
+
"trust_remote_code": false,
|
61 |
"unk_token": "<unk>",
|
62 |
+
"use_default_system_prompt": true,
|
63 |
+
"use_fast": true
|
64 |
}
|