nick commited on
Commit
ed78802
1 Parent(s): cbc2071

Upload from seopbo

Browse files
README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: ko
3
+ tags:
4
+ - korean
5
+ - lassl
6
+ mask_token: "[MASK]"
7
+ widget:
8
+ - text: 대한민국의 수도는 [MASK] 입니다.
9
+ ---
10
+
11
+ # LASSL roberta-ko-small
12
+ Pretrained `roberta-ko-small` on korean language was trained by [LASSL](https://github.com/lassl/lassl) framework. Below performance was evaluated at 2021/12/15.
13
+
14
+ | nsmc | klue_nli | klue_sts | korquadv1 | klue_mrc | avg |
15
+ | ---- | -------- | -------- | --------- | ---- | -------- |
16
+ | 87.8846 | 66.3086 | 83.8353 | 83.1780 | 42.4585 | 72.7330 |
17
+
18
+ ## How to use
19
+
20
+ ```python
21
+ from transformers import AutoModel, AutoTokenizer
22
+ model = AutoModel.from_pretrained("lassl/roberta-ko-small")
23
+ tokenizer = AutoTokenizer.from_pretrained("lassl/roberta-ko-small")
24
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 256,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1024,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 4,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.12.5",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 51200
26
+ }
merges.txt 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 sha256:345d994e07efd29cbf1e319578215dd256dd4fe41c6fb8341aa72858a122c32e
3
+ size 91374436
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "datasets/roberta", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff