initial release

README.md

@@ -0,0 +1,26 @@
+---
+language:
+- "vi"
+tags:
+- "vietnamese"
+- "masked-lm"
+- "wikipedia"
+license: "cc-by-sa-4.0"
+pipeline_tag: "fill-mask"
+mask_token: "[MASK]"
+---
+
+# roberta-base-vietnamese
+
+## Model Description
+
+This is a RoBERTa model pre-trained on Vietnamese Wikipedia texts. You can fine-tune `roberta-base-vietnamese` for downstream tasks, such as [POS-tagging](https://huggingface.co/KoichiYasuoka/roberta-base-vietnamese-upos), [dependency-parsing](https://huggingface.co/KoichiYasuoka/roberta-base-vietnamese-ud-goeswith), and so on.
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModelForMaskedLM
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-base-vietnamese")
+model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/roberta-base-vietnamese")
+```
+

config.json

@@ -0,0 +1,27 @@
+{
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eda73204b75d9a05fe9e3d2f4ef473986df523c2d259a01795dab1e52616061
+size 442675435

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "do_lowercase": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": [
+    "[CLS]",
+    "[PAD]",
+    "[SEP]",
+    "[UNK]",
+    "[MASK]"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizerFast",
+  "unk_token": "[UNK]"
+}