initial release

README.md

@@ -0,0 +1,26 @@
+---
+language:
+- "th"
+tags:
+- "thai"
+- "masked-lm"
+- "wikipedia"
+license: "apache-2.0"
+pipeline_tag: "fill-mask"
+mask_token: "[MASK]"
+---
+
+# deberta-base-thai
+
+## Model Description
+
+This is a DeBERTa(V2) model pre-trained on Thai Wikipedia texts. You can fine-tune `deberta-base-thai` for downstream tasks, such as [POS-tagging](https://huggingface.co/KoichiYasuoka/deberta-base-thai-upos), dependency-parsing, and so on.
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModelForMaskedLM
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-base-thai")
+model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/deberta-base-thai")
+```
+

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": null,
+  "position_biased_input": true,
+  "relative_attention": false,
+  "tokenizer_class": "DebertaV2TokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.2",
+  "type_vocab_size": 0,
+  "vocab_size": 3000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae5ca6dee9919446aedf425af5b921345fb9eb15be5f48e2f65189e5b0c8df0
+size 353465581

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": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": true, "keep_accents": true, "model_max_length": 512, "tokenizer_class": "DebertaV2TokenizerFast"}