add full metadata

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.bib filter=lfs diff=lfs merge=lfs -text
 collection.json filter=lfs diff=lfs merge=lfs -text
 dataset.json filter=lfs diff=lfs merge=lfs -text
+index/metadata.json filter=lfs diff=lfs merge=lfs -text

index/metadata.json

@@ -1,62 +1,3 @@
-{
-    "config": {
-        "query_token_id": "[unused0]",
-        "doc_token_id": "[unused1]",
-        "query_token": "[Q]",
-        "doc_token": "[D]",
-        "ncells": null,
-        "centroid_score_threshold": null,
-        "ndocs": null,
-        "load_index_with_mmap": false,
-        "index_path": null,
-        "nbits": 2,
-        "kmeans_niters": 4,
-        "resume": false,
-        "similarity": "cosine",
-        "bsize": 64,
-        "accumsteps": 1,
-        "lr": 3e-6,
-        "maxsteps": 500000,
-        "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": null,
-        "query_maxlen": 32,
-        "attend_to_mask_tokens": false,
-        "interaction": "colbert",
-        "dim": 128,
-        "doc_maxlen": 10,
-        "mask_punctuation": true,
-        "checkpoint": "colbert-ir\/colbertv2.0",
-        "triples": null,
-        "collection": [
-            "list with 46880 elements starting with...",
-            [
-                "Position paper for YRRSDS 2023",
-                "In this position paper, I will present the research interests in my PostDoc on safety and robustness specific to conversational AI, including then relevant overlap from my PhD.",
-                "Speech production is nuanced and unique to every individual, but today{'}s Spoken Dialogue Systems (SDSs) are trained to use general speech patterns to successfully improve performance on various evaluation metrics. However, these patterns do not apply to certain user groups - often the very people that can benefit the most from SDSs. For example, people with dementia produce more disfluent speech than the general population. The healthcare domain is now a popular setting for spoken dialogue and human-robot interaction research. This trend is similar when observing company behaviour. Charities promote industry voice assistants, the creators are getting HIPAA compliance, and their features sometimes target vulnerable user groups. It is therefore critical to adapt SDSs to be more accessible."
-            ]
-        ],
-        "queries": null,
-        "index_name": "index-1",
-        "overwrite": false,
-        "root": "\/content\/experiments",
-        "experiment": "notebook",
-        "index_root": null,
-        "name": "2024-04\/14\/15.49.20",
-        "rank": 0,
-        "nranks": 1,
-        "amp": true,
-        "gpus": 1
-    },
-    "num_chunks": 2,
-    "num_partitions": 8192,
-    "num_embeddings": 440546,
-    "avg_doclen": 9.39731228668942
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:fabe6f5e95f0eb8bee525adc7ab82d7fe275dc862e354f200eb494a74b2b23ea
+size 45753744