add ms marco coCondenser

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "/bos/tmp0/luyug/outputs/condenser/models/l2-s6-km-L128-e8-lr1e-4-b256",
+  "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",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ed985be111a9df3f28ee416730a89a7b3a0bd893d70607ff4bfd0cc6d2024e
+size 56770200

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3c0f849d868c7ccc90c6d51707c51b5938b365601a937e7ec8a62d85913d41
+size 438147282

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 @@
+{"do_lower_case": true, "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, "model_max_length": 512, "name_or_path": "/bos/tmp0/luyug/outputs/condenser/models/l2-s6-km-L128-e8-lr1e-4-b256", "special_tokens_map_file": "/bos/tmp0/luyug/outputs/condenser/models/l2-s6-km-L128-e8-lr1e-4-b256/special_tokens_map.json", "tokenizer_file": null}