Add pretrained model wangchanberta-base-wiki-20210520-news-spm (checkpoint 50k steps)

config.json

@@ -0,0 +1,26 @@
+{
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 25005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1322729a2e3a38b61fea02cfd26c60e158f7cf0540841aae14f960890d3050cf
+size 210593537

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfda5168b8b07c637cd71a88aaff45312de75e3e4e8bc5c6cf5346f92f206cdc
+size 1017584

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED", "▁"], "special_tokens_map_file": null, "tokenizer_file": null}