initial release

README.md

@@ -1,3 +1,26 @@
----
-license: apache-2.0
----
+---
+language:
+- "th"
+tags:
+- "thai"
+- "masked-lm"
+- "wikipedia"
+license: "apache-2.0"
+pipeline_tag: "fill-mask"
+mask_token: "[MASK]"
+---
+
+# roberta-base-thai-spm
+
+## Model Description
+
+This is a RoBERTa model pre-trained on Thai Wikipedia texts. You can fine-tune `roberta-base-thai-spm` for downstream tasks, such as [POS-tagging](https://huggingface.co/KoichiYasuoka/roberta-base-thai-spm-upos), dependency-parsing, and so on.
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModelForMaskedLM
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-base-thai-spm")
+model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/roberta-base-thai-spm")
+```
+

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": "RemBertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.14.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 3005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4bfb9340e8a9076f38f3cc977ee51cea6667aaa7dcd4e51089e25b0f5359c0
+size 353500459

sentencepiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b
+size 1

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "tokenizer_class": "RemBertTokenizerFast"}