Add pretrained wangchanberta-base-wiki-ssg model

Vocab: syllable (ssg)
Vocab size: 59,235
Tokenizer class: thai2transformers.tokenizers.ThaiWordsSyllableTokenizer
Checkpoint: 5,000

Version 1.0

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 4,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "unk_token_id": 3,
+  "vocab_size": 59235
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed5aa8e6c07ee2532b8b5d9d75e34a6fd2622b9840483c0dc5cd33e6a09d69b
+size 526470948