first commit

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "/scratch/j20200059/ConSERT/bert-base-uncased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "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": "4.6.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2da7dd5736ce9124f8116a026b22e203994c7d77d38f0d688b3860720bd854
+size 438015479

sentence_bert_config.json

@@ -0,0 +1,3 @@
+{
+  "max_seq_length": 64
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "special_tokens_map_file": null, "tokenizer_file": "/scratch/j20200059/ConSERT/bert-base-uncased/tokenizer.json", "name_or_path": "/scratch/j20200059/ConSERT/bert-base-uncased"}