add model

README.md

@@ -1,3 +1,9 @@
 ---
 license: apache-2.0
 ---
+
+# 🦮 LaPraDoR
+
+Pretrained checkpoint for Findings of ACL 2022 paper [LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval](https://arxiv.org/abs/2203.06169).
+
+To use this model, please refer to our [GitHub repo](https://github.com/JetRunner/LaPraDoR).

config.json

@@ -0,0 +1,24 @@
+{
+ "_name_or_path": "saved_models/ICT-iterative-shared-distilbert-self-dis-c4-1m/checkpoint-last/doc_encoder",
+ "activation": "gelu",
+ "architectures": [
+ "DistilBertModel"
+ ],
+ "attention_dropout": 0.1,
+ "dim": 768,
+ "dropout": 0.1,
+ "hidden_dim": 3072,
+ "initializer_range": 0.02,
+ "max_position_embeddings": 512,
+ "model_type": "distilbert",
+ "n_heads": 12,
+ "n_layers": 6,
+ "pad_token_id": 0,
+ "qa_dropout": 0.1,
+ "seq_classif_dropout": 0.2,
+ "sinusoidal_pos_embds": false,
+ "tie_weights_": true,
+ "torch_dtype": "float32",
+ "transformers_version": "4.9.2",
+ "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910bcae9b526e9f5f7176bc9c74ce699731b9c80673bf43cdac985c7641cb140
+size 265491187

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, "special_tokens_map_file": null, "tokenizer_file": "/home/t-dayaguo/.cache/huggingface/transformers/75abb59d7a06f4f640158a9bfcde005264e59e8d566781ab1415b139d2e4c603.7f2721073f19841be16f41b0a70b600ca6b880c8f3df6f3535cbc704371bdfa4", "name_or_path": "saved_models/ICT-iterative-shared-distilbert-self-dis-c4-1m/checkpoint-last/doc_encoder", "tokenizer_class": "DistilBertTokenizer"}