Add model and tokenizer files

config.json

@@ -1,28 +1,33 @@
 {
-  "_name_or_path": "camembert-base",
+  "_name_or_path": "voidful/albert_chinese_tiny",
   "architectures": [
-    "CamembertForMaskedLM"
+    "AlbertForMaskedLM"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 5,
-  "classifier_dropout": null,
-  "eos_token_id": 6,
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 312,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "camembert",
+  "inner_group_num": 1,
+  "intermediate_size": 1248,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 4,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.18.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 32005
+  "type_vocab_size": 2,
+  "vocab_size": 21128
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49bcca0a8b0e23a9d13e5cc64b16ad539f5316ec5f50e56d2062960592481075
-size 442691115
+oid sha256:ea6fdff436dcdd23221febab548ccbf74e8a2cca394bd993d5289d9fc6dd9d95
+size 16190158

special_tokens_map.json

@@ -1 +1 @@
-{"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": false}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -1 +1 @@
-{"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"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "camembert-base", "tokenizer_class": "CamembertTokenizer"}
+{"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, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "voidful/albert_chinese_tiny", "tokenizer_class": "BertTokenizer"}