Upload 7 files

artifact.metadata

@@ -0,0 +1,51 @@
+{
+    "nprobe": 2,
+    "ncandidates": 8192,
+    "index_path": null,
+    "nbits": 1,
+    "kmeans_niters": 20,
+    "similarity": "l2",
+    "bsize": 192,
+    "accumsteps": 6,
+    "lr": 3e-6,
+    "maxsteps": 91287,
+    "save_every": null,
+    "resume": false,
+    "warmup": null,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": false,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 180,
+    "mask_punctuation": true,
+    "checkpoint": "bert-base-uncased",
+    "triples": "\/u\/franzm\/ws\/nq\/ws\/g\/okhattab\/share\/OpenQA\/2021-Mar\/experiments\/Feb26.NQ\/triples\/ColBERT.C3\/3_20_biased200.json",
+    "collection": "\/dccstor\/revanth7\/dpr\/DPR\/data\/wikipedia_split\/psgs_w100.tsv",
+    "queries": "\/dccstor\/avi7\/neural_ir\/colbert\/data\/train-questions.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/dccstor\/colbert-ir\/franzm\/experiments\/",
+    "experiment": "feb2_3_3",
+    "index_root": null,
+    "name": "2022-02\/03\/17.24.40",
+    "rank": 0,
+    "nranks": 1,
+    "amp": true,
+    "gpus": 1,
+    "meta": {
+        "hostname": "cccxc536",
+        "git_branch": "new_api",
+        "git_hash": "6eb7ff53982de71c18ea8e4762faa9d646f6d727",
+        "git_commit_datetime": "2021-12-24 12:17:41-08:00",
+        "current_datetime": "Feb 04, 2022 ;  2:08PM EST (-0500)",
+        "cmd": "\/u\/franzm\/git8\/ColBERT_omar_ColBERTv2\/ColBERT\/colbert\/run_trainer.py --amp --doc_maxlen 180 --mask-punctuation --bsize 192 --accum 6 --maxsteps 91287 --triples \/u\/franzm\/ws\/nq\/ws\/g\/okhattab\/share\/OpenQA\/2021-Mar\/experiments\/Feb26.NQ\/triples\/ColBERT.C3\/3_20_biased200.json --collection \/dccstor\/revanth7\/dpr\/DPR\/data\/wikipedia_split\/psgs_w100.tsv --queries \/dccstor\/avi7\/neural_ir\/colbert\/data\/train-questions.tsv --root \/dccstor\/colbert-ir\/franzm\/experiments\/ --experiment feb2_3_3 --similarity l2 --run feb2_3_3_1",
+        "version": "colbert-v0.4"
+    }
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.10.0",
+  "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:a902b595e2283022d8cf8f506f3417006b970adcf2474ac64f0d54fb161324f8
+size 438405935

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, "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, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}