1st commit, upload model/basic setting

README.md

@@ -0,0 +1,4 @@
+# Model Description
+This checkpoint is a direct conversion of [BERT_Large_trained_on_MSMARCO.zip](https://drive.google.com/open?id=1crlASTMlsihALlkabAQP6JTYIZwC1Wm8) from the original [repo](https://github.com/nyu-dl/dl4marco-bert/).
+The corresponding model class is BertForSequenceClassification, and its purpose is for MS MARCO passage ranking.
+Please find the original repo for more detail of its training settings regarding hyperparameter/device/data.

config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "dl4marco_bert/model.ckpt-100000.index",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178c52bfa88ba93d0a29fae6f38c42dc4cd6a5fa8eb2975dfa47c515b0272ffb
+size 1340742099

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": "bert-large-uncased"}