Add wangchanberta-base-thwiki-spm model

- Vocab: SentencePiece
- Vocab size: 24,000
- Tokenizer class: thai2transformers.tokenizers.ThaiRobertaTokenizer
- Checkpoint: 7,000

README.md

@@ -1 +1 @@
-wangchanberta-base-wiki-spm
+## wangchanberta-base-wiki-spm

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": 24000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9559c5fd6e545c17f4b7e73255c02e48cd17c0844ac5cbc7e4078cc793fbb0
+size 418088102