Upload tokenizer
Browse files- special_tokens_map.json +6 -3
- tokenizer.json +1 -6
- tokenizer_config.json +27 -31
special_tokens_map.json
CHANGED
@@ -4,14 +4,16 @@
|
|
4 |
"lstrip": false,
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
-
"single_word": false
|
|
|
8 |
},
|
9 |
"eos_token": {
|
10 |
"content": "</s>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
-
"single_word": false
|
|
|
15 |
},
|
16 |
"pad_token": "</s>",
|
17 |
"unk_token": {
|
@@ -19,6 +21,7 @@
|
|
19 |
"lstrip": false,
|
20 |
"normalized": false,
|
21 |
"rstrip": false,
|
22 |
-
"single_word": false
|
|
|
23 |
}
|
24 |
}
|
|
|
4 |
"lstrip": false,
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
+
"single_word": false,
|
8 |
+
"special": true
|
9 |
},
|
10 |
"eos_token": {
|
11 |
"content": "</s>",
|
12 |
"lstrip": false,
|
13 |
"normalized": false,
|
14 |
"rstrip": false,
|
15 |
+
"single_word": false,
|
16 |
+
"special": true
|
17 |
},
|
18 |
"pad_token": "</s>",
|
19 |
"unk_token": {
|
|
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
}
|
27 |
}
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 4096,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
tokenizer_config.json
CHANGED
@@ -1,42 +1,38 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"
|
5 |
-
|
6 |
-
"
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
"special": true
|
13 |
-
},
|
14 |
-
"1": {
|
15 |
-
"content": "<s>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": false,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false,
|
20 |
-
"special": true
|
21 |
-
},
|
22 |
-
"2": {
|
23 |
-
"content": "</s>",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": false,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false,
|
28 |
-
"special": true
|
29 |
-
}
|
30 |
},
|
31 |
-
"bos_token": "<s>",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
"legacy": false,
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
-
"pad_token":
|
37 |
"padding_side": "right",
|
38 |
"sp_model_kwargs": {},
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
-
"unk_token":
|
41 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
},
|
|
|
13 |
"clean_up_tokenization_spaces": false,
|
14 |
+
"eos_token": {
|
15 |
+
"__type": "AddedToken",
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false,
|
21 |
+
"special": false
|
22 |
+
},
|
23 |
"legacy": false,
|
24 |
"model_max_length": 1000000000000000019884624838656,
|
25 |
+
"pad_token": null,
|
26 |
"padding_side": "right",
|
27 |
"sp_model_kwargs": {},
|
28 |
"tokenizer_class": "LlamaTokenizer",
|
29 |
+
"unk_token": {
|
30 |
+
"__type": "AddedToken",
|
31 |
+
"content": "<unk>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
}
|
38 |
}
|