commit model

README.md

@@ -1,3 +1,19 @@
 ---
 license: mit
 ---
+
+DPR Model trained from XLM-Align with C3 pretraining and retrieval finetuned on MSMARCO. 
+
+This model is meant to serve English queries and Chinese documents. 
+
+Please consider citing the following paper:
+
+```bibtex
+@inproceedings{sigir2022c3,
+    author = {Eugene Yang and Suraj Nair and Ramraj Chandradevan and Rebecca Iglesias-Flores and Douglas W. Oard},
+    title = {C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval},
+    booktitle = {Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (Short Paper)},
+    year = {2022},
+    url = {https://arxiv.org/abs/2204.11989}
+}
+```

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/exp/eyang/data/checkpoints/sigir-rerun-xlm-align-base.con2.maxsim-cosine.clirmatrix.zhen-step100000",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e880e4016175d84501647108ec812727d143943f5524c668cd858483a115310c
+size 1112255985

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "name_or_path": "/exp/eyang/data/checkpoints/sigir-rerun-xlm-align-base.con2.maxsim-cosine.clirmatrix.zhen-step100000", "tokenizer_file": "/exp/eyang/data/checkpoints/sigir-rerun-xlm-align-base.con2.maxsim-cosine.clirmatrix.zhen-step100000/tokenizer.json", "tokenizer_class": "XLMRobertaTokenizer"}