CaptainLazarus
commited on
Commit
•
f105e4d
1
Parent(s):
edacbb5
Upload tokenizer
Browse files- special_tokens_map.json +0 -1
- tokenizer.json +0 -0
- tokenizer.model +2 -2
- tokenizer_config.json +5 -8
special_tokens_map.json
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
-
"pad_token": "</s>",
|
5 |
"unk_token": "<unk>"
|
6 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
|
|
4 |
"unk_token": "<unk>"
|
5 |
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
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:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
|
3 |
+
size 534194
|
tokenizer_config.json
CHANGED
@@ -5,7 +5,7 @@
|
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
"lstrip": false,
|
8 |
-
"normalized":
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
@@ -13,7 +13,7 @@
|
|
13 |
"1": {
|
14 |
"content": "<s>",
|
15 |
"lstrip": false,
|
16 |
-
"normalized":
|
17 |
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
"special": true
|
@@ -21,7 +21,7 @@
|
|
21 |
"2": {
|
22 |
"content": "</s>",
|
23 |
"lstrip": false,
|
24 |
-
"normalized":
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
@@ -33,13 +33,10 @@
|
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
"model_max_length": 2048,
|
36 |
-
"pad_token":
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
-
"tokenizer_file": null,
|
41 |
-
"trust_remote_code": false,
|
42 |
"unk_token": "<unk>",
|
43 |
-
"use_default_system_prompt": true
|
44 |
-
"use_fast": true
|
45 |
}
|
|
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
|
|
13 |
"1": {
|
14 |
"content": "<s>",
|
15 |
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
"special": true
|
|
|
21 |
"2": {
|
22 |
"content": "</s>",
|
23 |
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
"model_max_length": 2048,
|
36 |
+
"pad_token": null,
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
40 |
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": true
|
|
|
42 |
}
|