initial commit

added_tokens.json

@@ -0,0 +1 @@
+{"[STARTQ]": 28996, "[ENDQ]": 28997, "[URL]": 28998, "[NEWLINE]": 28999, "[UNU]": 29000, "[USER0]": 29001, "[USER1]": 29002, "[USER2]": 29003, "[USER3]": 29004, "[USER4]": 29005, "[USER5]": 29006, "[USER6]": 29007, "[USER7]": 29008, "[USER8]": 29009, "[USER9]": 29010}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "../smlm_pretrained_iter2_0/model",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.8.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29011
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f661cd9aa21b3d3457c88eb67c2a25493ee06b3346d72968dc049f0dbcf4e7
+size 433494187

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": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "bos_token": "[CLS]", "eos_token": "[SEP]", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/subhabratad/.cache/huggingface/transformers/226a307193a9f4344264cdc76a12988448a25345ba172f2c7421f3b6810fddad.3dab63143af66769bbb35e3811f75f7e16b2320e12b7935e216bd6159ce6d9a6", "name_or_path": "../smlm_pretrained_iter2_0/tokenizer", "tokenizer_class": "BertTokenizer"}