Upload tokenizer
Browse files- special_tokens_map.json +1 -23
- tokenizer.json +2 -2
- tokenizer_config.json +6 -21
special_tokens_map.json
CHANGED
@@ -1,23 +1 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<s>",
|
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 |
-
"unk_token": {
|
17 |
-
"content": "<unk>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
}
|
23 |
-
}
|
|
|
1 |
+
{}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5b1a1ec52b4958a1d1d7bd1542233797d3d42d3faa26ea81b07ac0a2c95b926
|
3 |
+
size 17814156
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<pad>",
|
@@ -26,25 +23,13 @@
|
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
"special": true
|
29 |
-
},
|
30 |
-
"3": {
|
31 |
-
"content": "</s>",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": true
|
37 |
}
|
38 |
},
|
39 |
-
"
|
40 |
-
"
|
41 |
-
|
42 |
-
|
|
|
43 |
"model_max_length": 1000000000000000019884624838656,
|
44 |
-
"
|
45 |
-
"sp_model_kwargs": {},
|
46 |
-
"spaces_between_special_tokens": false,
|
47 |
-
"tokenizer_class": "LlamaTokenizer",
|
48 |
-
"unk_token": "<unk>",
|
49 |
-
"use_default_system_prompt": false
|
50 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<pad>",
|
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
},
|
28 |
+
"clean_up_tokenization_spaces": true,
|
29 |
+
"model_input_names": [
|
30 |
+
"input_ids",
|
31 |
+
"attention_mask"
|
32 |
+
],
|
33 |
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
|
|
|
|
35 |
}
|