YukiTomita-CC
commited on
Commit
•
30badbc
1
Parent(s):
67d8cca
Upload folder using huggingface_hub
Browse files- special_tokens_map.json +7 -1
- tokenizer.model +3 -0
- tokenizer_config.json +7 -6
special_tokens_map.json
CHANGED
@@ -1,5 +1,11 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"eos_token": {
|
4 |
"content": "<EOS>",
|
5 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<BOS>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
"eos_token": {
|
10 |
"content": "<EOS>",
|
11 |
"lstrip": false,
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7045fbbd49ed4155b265012f963e5dbf480d316bb8a3ed6bcc8be8199b6a4466
|
3 |
+
size 791613
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
"content": "<BOS>",
|
@@ -34,15 +35,15 @@
|
|
34 |
"special": true
|
35 |
}
|
36 |
},
|
37 |
-
"additional_special_tokens": [],
|
38 |
"bos_token": "<BOS>",
|
39 |
-
"clean_up_tokenization_spaces":
|
40 |
"eos_token": "<EOS>",
|
41 |
-
"extra_ids": 0,
|
42 |
"legacy": false,
|
43 |
"model_max_length": 1000000000000000019884624838656,
|
44 |
"pad_token": "<PAD>",
|
45 |
"sp_model_kwargs": {},
|
46 |
-
"
|
47 |
-
"
|
|
|
|
|
48 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<BOS>",
|
|
|
35 |
"special": true
|
36 |
}
|
37 |
},
|
|
|
38 |
"bos_token": "<BOS>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
"eos_token": "<EOS>",
|
|
|
41 |
"legacy": false,
|
42 |
"model_max_length": 1000000000000000019884624838656,
|
43 |
"pad_token": "<PAD>",
|
44 |
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"unk_token": "<UNK>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
}
|