test

config.json

@@ -0,0 +1,21 @@
+{
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 32000,
+  "tokenizer_class": "BertTokenizer"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258288f517aee6574eb650662dc0c5e8c22cac935825739c874b15b9a5d4e32e
+size 1346794065

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "unk_token": "[UNK]",
+  "sep_token": "[SEP]",
+  "pad_token": "[PAD]",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "bos_token": "[CLS]",
+  "eos_token": "[SEP]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "do_lower_case": false,
+  "do_basic_tokenize": true,
+  "never_split": null,
+  "unk_token": "[UNK]",
+  "sep_token": "[SEP]",
+  "pad_token": "[PAD]",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "bos_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "tokenize_chinese_chars": true,
+  "strip_accents": null,
+  "model_max_length": 512,
+  "tokenizer_class": "BertTokenizer"
+}