Upload from seopbo

README.md

@@ -0,0 +1,24 @@
+---
+language: ko
+tags:
+  - korean
+  - lassl
+mask_token: "[MASK]"
+widget:
+  - text: 대한민국의 수도는 [MASK] 입니다.
+---
+
+# LASSL roberta-ko-small
+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.
+
+| nsmc | klue_nli | klue_sts | korquadv1 | klue_mrc | avg |
+| ---- | -------- | -------- | --------- | ---- | -------- |
+| 87.8846 | 66.3086 | 83.8353 | 83.1780 | 42.4585 | 72.7330 |
+
+## How to use
+
+```python
+from transformers import AutoModel, AutoTokenizer
+model = AutoModel.from_pretrained("lassl/roberta-ko-small")
+tokenizer = AutoTokenizer.from_pretrained("lassl/roberta-ko-small")
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 512,
+  "model_type": "roberta",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 51200
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:345d994e07efd29cbf1e319578215dd256dd4fe41c6fb8341aa72858a122c32e
+size 91374436

special_tokens_map.json

@@ -0,0 +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_config.json

@@ -0,0 +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"}