initial commit

README.md

@@ -0,0 +1,17 @@
+---
+language:
+- en
+tags:
+- retrieval
+- document-rewriting
+datasets:
+- irds:msmarco-passage
+library_name: transformers
+---
+
+A DeepCT model based on `bert-base-uncased` and trained on MS MARCO. This is a version of [the checkpoint released by the original authors](http://boston.lti.cs.cmu.edu/appendices/arXiv2019-DeepCT-Zhuyun-Dai/outputs/marco.zip), converted to pytorch format and ready for use in PyTerrier.
+
+## References
+
+ - [Dai19]: Zhuyun Dai, Jamie Callan. Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval. https://arxiv.org/abs/1910.10687
+ - [Macdonald20]: Craig Macdonald, Nicola Tonellotto. Declarative Experimentation in Information Retrieval using PyTerrier. Craig Macdonald and Nicola Tonellotto. In Proceedings of ICTIR 2020. https://arxiv.org/abs/2007.14271

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "macavaney/deepct",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d2162ad03215a242d2a29a62154303a3cfc8c1cde03c5a5c44ccc317478d80
+size 435637297

special_tokens_map.json

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

tokenizer_config.json

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