Upload 7 files
Browse files- config.json +29 -0
- model.safetensors +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "klue/roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 4096,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"tokenizer_class": "BertTokenizer",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.36.2",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d070a5ef96757fa8d93f1794c73ed38fd32e7b2912ad29c7dd0f19283916511b
|
3 |
+
size 1346809984
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"unk_token": "[UNK]",
|
3 |
+
"sep_token": "[SEP]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"cls_token": "[CLS]",
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"bos_token": "[CLS]",
|
8 |
+
"eos_token": "[SEP]"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": false,
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"never_split": null,
|
5 |
+
"unk_token": "[UNK]",
|
6 |
+
"sep_token": "[SEP]",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"cls_token": "[CLS]",
|
9 |
+
"mask_token": "[MASK]",
|
10 |
+
"bos_token": "[CLS]",
|
11 |
+
"eos_token": "[SEP]",
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"strip_accents": null,
|
14 |
+
"model_max_length": 512,
|
15 |
+
"tokenizer_class": "BertTokenizer"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab1e1ec0711a0f78119eb68655d7f5290b54997fcbfb31ac48a77ea3d5f6e390
|
3 |
+
size 4207
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|