Locutusque
commited on
Commit
•
7a6e4ff
1
Parent(s):
4ec1ddf
Upload 7 files
Browse files- special_tokens_map.json +23 -0
- tokenizer.json +27 -0
- tokenizer_config.json +29 -1
special_tokens_map.json
CHANGED
@@ -1,4 +1,20 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
@@ -13,6 +29,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|ASSISTANT|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|USER|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
"bos_token": {
|
19 |
"content": "<s>",
|
20 |
"lstrip": false,
|
|
|
29 |
"rstrip": false,
|
30 |
"single_word": false
|
31 |
},
|
32 |
+
"pad_token": {
|
33 |
+
"content": "[PAD]",
|
34 |
+
"lstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
},
|
39 |
"unk_token": {
|
40 |
"content": "<unk>",
|
41 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -29,6 +29,33 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 32000,
|
35 |
+
"content": "<|ASSISTANT|>",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 32001,
|
44 |
+
"content": "<|USER|>",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 32002,
|
53 |
+
"content": "[PAD]",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"special": true
|
59 |
}
|
60 |
],
|
61 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -23,14 +23,42 @@
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
},
|
|
|
|
|
|
|
|
|
28 |
"bos_token": "<s>",
|
29 |
"clean_up_tokenization_spaces": false,
|
30 |
"eos_token": "</s>",
|
31 |
"legacy": false,
|
32 |
"model_max_length": 1000000000000000019884624838656,
|
33 |
-
"pad_token":
|
34 |
"padding_side": "right",
|
35 |
"sp_model_kwargs": {},
|
36 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
+
},
|
27 |
+
"32000": {
|
28 |
+
"content": "<|ASSISTANT|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32001": {
|
36 |
+
"content": "<|USER|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"32002": {
|
44 |
+
"content": "[PAD]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
}
|
51 |
},
|
52 |
+
"additional_special_tokens": [
|
53 |
+
"<|ASSISTANT|>",
|
54 |
+
"<|USER|>"
|
55 |
+
],
|
56 |
"bos_token": "<s>",
|
57 |
"clean_up_tokenization_spaces": false,
|
58 |
"eos_token": "</s>",
|
59 |
"legacy": false,
|
60 |
"model_max_length": 1000000000000000019884624838656,
|
61 |
+
"pad_token": "[PAD]",
|
62 |
"padding_side": "right",
|
63 |
"sp_model_kwargs": {},
|
64 |
"tokenizer_class": "LlamaTokenizer",
|