push model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,27 @@
 ---
 license: mit
+language: 
+- en
+- zh
+task_categories:
+- text-retrieval
+- zero-shot-retrieval
+- information-retrieval
+- zero-shot-information-retrieval
+task_ids:
+- passage-retrieval
+- cross-language-retrieval
 ---
+
+Model trained by [Suraj Nair](https://srnair.netlify.app/). 
+
+If you use the model, please cite our paper. 
+```bibtex
+@inproceedings{colbert-x,
+    author = {Suraj Nair and Eugene Yang and Dawn Lawrie and Kevin Duh and Paul McNamee and Kenton Murray and James Mayfield and Douglas W. Oard},
+    title = {Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models},
+    booktitle = {Proceedings of the 44th European Conference on Information Retrieval (ECIR)},
+    year = {2022},
+    url = {https://arxiv.org/abs/2201.08471}
+}
+```

artifact.metadata

@@ -0,0 +1,58 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "index_path": null,
+    "nbits": 1,
+    "kmeans_niters": 4,
+    "resume": false,
+    "similarity": "l2",
+    "bsize": 128,
+    "accumsteps": 1,
+    "lr": 3e-6,
+    "maxsteps": 200000,
+    "save_every": null,
+    "warmup": null,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": false,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "xlm-roberta-large",
+    "force_resize_embeddings": true,
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 180,
+    "mask_punctuation": true,
+    "checkpoint": "\/exp\/snair\/ColBERT\/msmarco\/zho\/MSMARCO-xlmr-scale21\/train.py\/MSMARCO-xlmr-scale21.l2\/checkpoints\/colbert.dnn",
+    "triples": "\/home\/hltcoe\/snair\/msmarco\/zho\/20210731-scale21-sockeye2-tm1_triples.tsv",
+    "collection": null,
+    "queries": null,
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/exp\/snair\/ColBERT\/msmarco\/zho\/",
+    "experiment": "MSMARCO-xlmr-scale21",
+    "index_root": null,
+    "name": "2023-07\/09\/23.01.51",
+    "rank": 0,
+    "nranks": 1,
+    "amp": true,
+    "gpus": 0,
+    "meta": {
+        "hostname": "test1",
+        "git_branch": "plaid-x",
+        "git_hash": "d3f4e70439129ae7a2383c46ad661d481d464cdf",
+        "git_commit_datetime": "2023-07-04 00:23:15-04:00",
+        "current_datetime": "Jul 09, 2023 ; 11:09PM EDT (-0400)",
+        "cmd": "\/home\/hltcoe\/eyang\/.conda\/envs\/interactive-new\/bin\/ipython --profile=eugene",
+        "version": "colbert-v0.4"
+    }
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250004
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4562882f98531609ea4b5936dc09aaf78a434437825fd8a33e6a28f632baa22f
+size 2240228465

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19ec03247ee31e5f42772ac32bde8dca2727b30c8310c2e585df4980a8db230
+size 17083032

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "xlm-roberta-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}