Update file

config.json

@@ -1,26 +1,28 @@
 {
-  "_name_or_path": "../pretrained-bert-tiny",
+  "_name_or_path": "../../seeder-sbert/pretrain-models/wangchanberta-base-att-spm-uncased",
   "architectures": [
-    "BertModel"
+    "CamembertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 128,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
-  "pad_token_id": 0,
+  "model_type": "camembert",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.9.0",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 25005
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed78334801bbb4de7a6b130534bf0156c7cecf252c2ce640e03d832de00a27a
-size 17563927
+oid sha256:afea29fbbd81463e32d3807d316b0d5a7459a0c03daa043aa86f458c9c1d8172
+size 421064183

special_tokens_map.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED", "<_>"]}

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "../pretrained-bert-tiny", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "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, "name_or_path": "../../seeder-sbert/pretrain-models/wangchanberta-base-att-spm-uncased", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}