Upload folder using huggingface_hub
Browse files- added_tokens.json +3 -0
- config.json +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +18 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +27 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"$START": 32000
|
3 |
+
}
|
config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bad55b2f3585d80eaa1eccc2c74c666c616a48e60cecc96a09b313286c4e89f
|
3 |
+
size 482338845
|
special_tokens_map.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"$START"
|
4 |
+
],
|
5 |
+
"bos_token": "<s>",
|
6 |
+
"cls_token": "<cls>",
|
7 |
+
"eos_token": "</s>",
|
8 |
+
"mask_token": {
|
9 |
+
"content": "<mask>",
|
10 |
+
"lstrip": true,
|
11 |
+
"normalized": false,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "<sep>",
|
17 |
+
"unk_token": "<unk>"
|
18 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
|
3 |
+
size 798011
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"additional_special_tokens": [
|
4 |
+
"<eop>",
|
5 |
+
"<eod>"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"cls_token": "<cls>",
|
9 |
+
"do_lower_case": false,
|
10 |
+
"eos_token": "</s>",
|
11 |
+
"keep_accents": false,
|
12 |
+
"mask_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<mask>",
|
15 |
+
"lstrip": true,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"name_or_path": "models/stage2/xlnet-base-cased/5k/seed12/best",
|
21 |
+
"pad_token": "<pad>",
|
22 |
+
"remove_space": true,
|
23 |
+
"sep_token": "<sep>",
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "XLNetTokenizer",
|
26 |
+
"unk_token": "<unk>"
|
27 |
+
}
|