initial commit

config.json

@@ -0,0 +1,5 @@
+{
+  "model_type": "DualEncoder",
+  "shared": false,
+  "transformers_version": "4.20.1"
+}

doc_encoder/config.json

@@ -0,0 +1,14 @@
+{
+  "activation": "relu",
+  "architectures": [
+    "TransformerMLMSparseEncoder"
+  ],
+  "doc_quality": "no",
+  "model_type": "MLM",
+  "norm": "log1p",
+  "pool": "max",
+  "term_importance": "no",
+  "tf_base_model_name_or_dir": "distilbert-base-uncased",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1"
+}

doc_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594416ea602438fae234406a49c02375901c43f13d59dec6bc15469021b91835
+size 267977455

loss.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e067575663ecbca8629d3870eb9abfb013912e87e50bf69fc1b437f433861a66
+size 559

query_encoder/config.json

@@ -0,0 +1,10 @@
+{
+  "architectures": [
+    "BinaryEncoder"
+  ],
+  "model_type": "BINARY",
+  "scale": 0.3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "vocab_size": 30522
+}

query_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a0da240c2273946ec9b14f901943af502ba16c8488e3f80ed8ac3752b607e4
+size 747

tokenizer/class_config.json

@@ -0,0 +1 @@
+{"tokenizer_class": "lsr.tokenizer.HFTokenizer"}

tokenizer/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}