Upload tokenizer
Browse files- .gitattributes +1 -0
- tokenizer.json +3 -0
- tokenizer_config.json +9 -1
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:656b75fb38a626c862a18a7bac538d650de34dfd5c1211973bff843c9b9211f9
|
3 |
+
size 17815145
|
tokenizer_config.json
CHANGED
@@ -3,6 +3,14 @@
|
|
3 |
"add_eos_token": false,
|
4 |
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"1": {
|
7 |
"content": "<unk>",
|
8 |
"lstrip": false,
|
@@ -36,7 +44,7 @@
|
|
36 |
"pad_token": null,
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
-
"tokenizer_class": "
|
40 |
"unk_token": "<unk>",
|
41 |
"use_default_system_prompt": false
|
42 |
}
|
|
|
3 |
"add_eos_token": false,
|
4 |
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<pad>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
"1": {
|
15 |
"content": "<unk>",
|
16 |
"lstrip": false,
|
|
|
44 |
"pad_token": null,
|
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 |
}
|