feat: add 50000
Browse files- added_tokens.json +1 -1
- config.json +2 -3
- optimizer.pt +2 -2
- pytorch_model.bin +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- tokenizer.json +0 -0
- trainer_state.json +0 -0
- training_args.bin +1 -1
- vocab.txt +0 -2
added_tokens.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"</s>":
|
|
|
1 |
+
{"</s>": 6615, "<s>": 6614}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "roberta-small-
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
@@ -12,7 +12,6 @@
|
|
12 |
"hidden_size": 256,
|
13 |
"initializer_range": 0.02,
|
14 |
"intermediate_size": 768,
|
15 |
-
"is_decoder": true,
|
16 |
"layer_norm_eps": 1e-12,
|
17 |
"max_position_embeddings": 130,
|
18 |
"model_type": "roberta",
|
@@ -24,5 +23,5 @@
|
|
24 |
"transformers_version": "4.17.0",
|
25 |
"type_vocab_size": 2,
|
26 |
"use_cache": true,
|
27 |
-
"vocab_size":
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "roberta-small-japanese-aozora-char-custom",
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
|
|
12 |
"hidden_size": 256,
|
13 |
"initializer_range": 0.02,
|
14 |
"intermediate_size": 768,
|
|
|
15 |
"layer_norm_eps": 1e-12,
|
16 |
"max_position_embeddings": 130,
|
17 |
"model_type": "roberta",
|
|
|
23 |
"transformers_version": "4.17.0",
|
24 |
"type_vocab_size": 2,
|
25 |
"use_cache": true,
|
26 |
+
"vocab_size": 7000
|
27 |
}
|
optimizer.pt
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 sha256:9b431a20185b9d315699a6a732a9b1cbc63f7d93654b71433a7cd02597464ae5
|
3 |
+
size 78523353
|
pytorch_model.bin
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 sha256:8a2f1383976c493bad5dec68fc2de14227345adf6d5ed26989746abebf23fc26
|
3 |
+
size 39286699
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed583e01607e043950535d5c4ae00a739a783eeb23179f6faa3c9dd2060c9dec
|
3 |
size 14503
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:491092af1e8a06d583d09f4a90b42061f43f4540881fe6d647b0f3899893aee2
|
3 |
size 623
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2991
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:298530b9e00ad9dd7af7ffa84be7826dcf4271a9da04cc42af1604445e287b41
|
3 |
size 2991
|
vocab.txt
CHANGED
@@ -26,8 +26,6 @@
|
|
26 |
時
|
27 |
年
|
28 |
一
|
29 |
-
|
30 |
-
|
31 |
邊
|
32 |
即
|
33 |
公
|
|
|
26 |
時
|
27 |
年
|
28 |
一
|
|
|
|
|
29 |
邊
|
30 |
即
|
31 |
公
|