upload model puri-thai-albert-cased-v1

added_tokens.json

@@ -0,0 +1 @@
+{"<pad>": 100000}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "output_model_full-v1/checkpoint-117000/",
+  "architectures": [
+    "AlbertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "num_attention_heads": 64,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 100001
+}

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": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": "[MASK]", "max_len": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/root/workspace/thesis/tokenizer_v2/"}