Upload folder using huggingface_hub
Browse files- merges.txt +0 -0
- no-oscar+mc4-spm.model +3 -0
- no-oscar+mc4-spm.vocab +0 -0
- special_tokens_map.json +3 -21
- tokenizer.json +0 -0
- vocab.json +0 -0
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
no-oscar+mc4-spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4710591f95516d9552e684759564a27d29a22a82c4c168fa670d1ec192bc34e
|
3 |
+
size 1082849
|
no-oscar+mc4-spm.vocab
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -1,23 +1,5 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
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 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|