Push

.gitattributes

@@ -1,114 +0,0 @@
-data/.cache/lilac/concept/lilac/negative-sentiment/cohere.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/positive-sentiment/cohere.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/profanity/cohere.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/profanity/gte-base.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/profanity/gte-small.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/profanity/openai.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/profanity/palm.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/profanity/sbert.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/toxicity/cohere.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/toxicity/gte-base.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/toxicity/gte-small.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/toxicity/openai.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/toxicity/palm.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/toxicity/sbert.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/question/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/question/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/question/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/question/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/question/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/question/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/question/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/response/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/response/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/response/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/response/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/response/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/response/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/local/OpenOrca-100k/response/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/goal/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/goal/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/goal/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/sol1/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/sol1/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/sol1/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/sol2/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/sol2/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/piqa/sol2/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/pile-of-law-atticus-contracts/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/choices/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/choices/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/choices/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/choices/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/choices/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/choices/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/choices/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/question/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/question/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/question/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/question/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/question/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/question/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/mmlu_professional_law/question/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/pile-of-law-r-legaladvice/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/pile-of-law-r-legaladvice/text/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/pile-of-law-r-legaladvice/text/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/pile-of-law-r-legaladvice/text/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/pile-of-law-r-legaladvice/text/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/pile-of-law-r-legaladvice/text/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/pile-of-law-r-legaladvice/text/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/pile-of-law-r-legaladvice/text/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/open-asssistant-conversations/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/open-asssistant-conversations/text/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/open-asssistant-conversations/text/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/open-asssistant-conversations/text/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/open-asssistant-conversations/text/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/open-asssistant-conversations/text/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/open-asssistant-conversations/text/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/open-asssistant-conversations/text/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/answers/text/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/answers/text/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/answers/text/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/answers/text/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/context/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/context/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/context/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/context/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/context/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/context/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/context/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/question/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/question/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/question/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/squad_v2/question/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/imdb/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/imdb/text/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/imdb/text/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/imdb/text/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/imdb/text/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/imdb/text/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/imdb/text/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/imdb/text/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/databricks-dolly-15k-curated-en/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/databricks-dolly-15k-curated-en/new-context/value/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/databricks-dolly-15k-curated-en/original-context/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/wikitext-2-raw-v1/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/wikitext-2-raw-v1/text/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/wikitext-2-raw-v1/text/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/wikitext-2-raw-v1/text/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/wikitext-2-raw-v1/text/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/wikitext-2-raw-v1/text/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/medical_dialog/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/medical_dialog/dialogue_turns/utterance/gte-small/hnsw.hnswlib.bin filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/medical_dialog/dialogue_turns/utterance/gte-small/hnsw.lookup.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/medical_dialog/dialogue_turns/utterance/gte-small/spans.pkl filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/medical_dialog/dialogue_turns/utterance/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/medical_dialog/dialogue_turns/utterance/near_dup/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/medical_dialog/dialogue_turns/utterance/pii/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
-data/datasets/lilac/medical_dialog/dialogue_turns/utterance/text_statistics/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text

data/.cache/lilac/concept/lilac/negative-sentiment/cohere.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:be0a6613703986f991d3795a6b3cfdccd40b75ce1c6cbf36e852403c8d8a6b7b
-size 2088021

data/.cache/lilac/concept/lilac/positive-sentiment/cohere.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d654cd9eb459aba5509d6b21d48e2f2560c84457608a0ddefc0d7e26a685b7ef
-size 1857652

data/.cache/lilac/concept/lilac/profanity/cohere.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0d68aeb0d88c4a501e21173ed3e5e53fa4998447ece6812d046c1c48b2595739
-size 17413997

data/.cache/lilac/concept/lilac/profanity/gte-base.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:20c4454090ac980db7f02e5f2ff974b0fe75e26982c40e323891fae4b3785d38
-size 3301326

data/.cache/lilac/concept/lilac/profanity/gte-small.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ef20b176c6faec04280e7f4fcc5edfd01c8261b4838eab2955885a171e46590d
-size 1672960

data/.cache/lilac/concept/lilac/profanity/openai.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6a8e4c306cbbdbfa1d5dde1504fa67ee8e5ffa02ab77f1e8d06d15b9ea777398
-size 6558076

data/.cache/lilac/concept/lilac/profanity/palm.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0450ba56a6af797838a696e5d1046e84dbca2d6c6a00724c3bf403465980b1f5
-size 3301322

data/.cache/lilac/concept/lilac/profanity/sbert.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:44f41da69be02fb8ffe4db5d7d16cdd0e8f4357f8147d4259ae5518863577087
-size 1672951

data/.cache/lilac/concept/lilac/toxicity/cohere.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ec3b151a149f0664813f50ba599001bc3a44cc7b6f8c35a48e213ee9c9682fb
-size 19602537

data/.cache/lilac/concept/lilac/toxicity/gte-base.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bd428cfda7f66401cf3b6ec9f1b356c3e0d79ab5bce8675c271e562c24de3580
-size 3719127

data/.cache/lilac/concept/lilac/toxicity/gte-small.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b9bab578121263c97f51049e82846b7b517b79655bfd9b6ad5fe861dbefd1212
-size 1886446

data/.cache/lilac/concept/lilac/toxicity/openai.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4e9be59c226a117c78c32cdb0f4befaf771b74a7af820af25f86053e1cf80614
-size 7384512

data/.cache/lilac/concept/lilac/toxicity/palm.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b334cd21b80823eb0b7a6c177ba2f6ed8cadc504b642e7b89481f0e583dcfece
-size 3719128

data/.cache/lilac/concept/lilac/toxicity/sbert.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:64540327c019de743fa40b494f21cf1a5a7b0af80df6243eb44b56cf3810ccbf
-size 1886440

data/datasets/lilac/databricks-dolly-15k-curated-en/config.yml

@@ -1,67 +0,0 @@
-embeddings:
-- embedding: gte-small
-  path: [new-context, value, '*']
-- {embedding: gte-small, path: original-context}
-name: databricks-dolly-15k-curated-en
-namespace: lilac
-settings:
-  preferred_embedding: gte-small
-  ui:
-    media_paths:
-    - original-instruction
-    - original-context
-    - original-response
-    - [new-instruction, value, '*']
-    - [new-context, value, '*']
-    - [new-response, value, '*']
-signals:
-- path: original-instruction
-  signal: {signal_name: near_dup}
-- path: original-instruction
-  signal: {signal_name: text_statistics}
-- path: original-instruction
-  signal: {signal_name: pii}
-- path: original-instruction
-  signal: {signal_name: lang_detection}
-- path: original-context
-  signal: {signal_name: near_dup}
-- path: original-context
-  signal: {signal_name: text_statistics}
-- path: original-context
-  signal: {signal_name: lang_detection}
-- path: original-context
-  signal: {signal_name: pii}
-- path: original-response
-  signal: {signal_name: near_dup}
-- path: original-response
-  signal: {signal_name: text_statistics}
-- path: original-response
-  signal: {signal_name: pii}
-- path: original-response
-  signal: {signal_name: lang_detection}
-- path: [new-instruction, value, '*']
-  signal: {signal_name: near_dup}
-- path: [new-instruction, value, '*']
-  signal: {signal_name: text_statistics}
-- path: [new-instruction, value, '*']
-  signal: {signal_name: pii}
-- path: [new-instruction, value, '*']
-  signal: {signal_name: lang_detection}
-- path: [new-context, value, '*']
-  signal: {signal_name: near_dup}
-- path: [new-context, value, '*']
-  signal: {signal_name: text_statistics}
-- path: [new-context, value, '*']
-  signal: {signal_name: lang_detection}
-- path: [new-context, value, '*']
-  signal: {signal_name: pii}
-- path: [new-response, value, '*']
-  signal: {signal_name: near_dup}
-- path: [new-response, value, '*']
-  signal: {signal_name: text_statistics}
-- path: [new-response, value, '*']
-  signal: {signal_name: pii}
-- path: [new-response, value, '*']
-  signal: {signal_name: lang_detection}
-source: {dataset_name: argilla/databricks-dolly-15k-curated-en, source_name: huggingface}
-tags: [machine-learning]

data/datasets/lilac/databricks-dolly-15k-curated-en/data-00000-of-00001.parquet

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad225b50d5880a097ea66eb4ca70fc529c0321cf8a5652bd8fbe7a638d016851
-size 15882489

data/datasets/lilac/databricks-dolly-15k-curated-en/manifest.json

@@ -1,87 +0,0 @@
-{
-  "files": [
-    "data-00000-of-00001.parquet"
-  ],
-  "data_schema": {
-    "fields": {
-      "id": {
-        "dtype": "string"
-      },
-      "category": {
-        "dtype": "string"
-      },
-      "original-instruction": {
-        "dtype": "string"
-      },
-      "original-context": {
-        "dtype": "string"
-      },
-      "original-response": {
-        "dtype": "string"
-      },
-      "new-instruction": {
-        "fields": {
-          "user_id": {
-            "repeated_field": {
-              "dtype": "string"
-            }
-          },
-          "value": {
-            "repeated_field": {
-              "dtype": "string"
-            }
-          },
-          "status": {
-            "repeated_field": {
-              "dtype": "string"
-            }
-          }
-        }
-      },
-      "new-context": {
-        "fields": {
-          "user_id": {
-            "repeated_field": {
-              "dtype": "string"
-            }
-          },
-          "value": {
-            "repeated_field": {
-              "dtype": "string"
-            }
-          },
-          "status": {
-            "repeated_field": {
-              "dtype": "string"
-            }
-          }
-        }
-      },
-      "new-response": {
-        "fields": {
-          "user_id": {
-            "repeated_field": {
-              "dtype": "string"
-            }
-          },
-          "value": {
-            "repeated_field": {
-              "dtype": "string"
-            }
-          },
-          "status": {
-            "repeated_field": {
-              "dtype": "string"
-            }
-          }
-        }
-      },
-      "external_id": {
-        "dtype": "string"
-      },
-      "__hfsplit__": {
-        "dtype": "string"
-      }
-    }
-  }
-}

data/datasets/lilac/databricks-dolly-15k-curated-en/new-context/value/gte-small/hnsw.hnswlib.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dd30fd8659fca42a569c12fa3fb37e62b97ae62349f535a5e2aac97d8a5b2750
-size 32553584

data/datasets/lilac/databricks-dolly-15k-curated-en/new-context/value/gte-small/signal_manifest.json

@@ -1,40 +0,0 @@
-{
-  "files": [],
-  "parquet_id": "new-context.value.gte-small",
-  "data_schema": {
-    "fields": {
-      "new-context": {
-        "fields": {
-          "value": {
-            "repeated_field": {
-              "fields": {
-                "gte-small": {
-                  "repeated_field": {
-                    "fields": {
-                      "embedding": {
-                        "dtype": "embedding"
-                      }
-                    },
-                    "dtype": "string_span"
-                  },
-                  "signal": {
-                    "signal_name": "gte-small"
-                  }
-                }
-              }
-            }
-          }
-        }
-      }
-    }
-  },
-  "signal": {
-    "signal_name": "gte-small"
-  },
-  "enriched_path": [
-    "new-context",
-    "value",
-    "*"
-  ],
-  "vector_store": "hnsw"
-}

data/datasets/lilac/databricks-dolly-15k-curated-en/new-context/value/lang_detection/signal_manifest.json

@@ -1,36 +0,0 @@
-{
-  "files": [
-    "data-00000-of-00001.parquet"
-  ],
-  "parquet_id": "new-context.value.lang_detection",
-  "data_schema": {
-    "fields": {
-      "new-context": {
-        "fields": {
-          "value": {
-            "repeated_field": {
-              "fields": {
-                "lang_detection": {
-                  "dtype": "string",
-                  "signal": {
-                    "split_by_paragraph": false,
-                    "signal_name": "lang_detection"
-                  }
-                }
-              }
-            }
-          }
-        }
-      }
-    }
-  },
-  "signal": {
-    "split_by_paragraph": false,
-    "signal_name": "lang_detection"
-  },
-  "enriched_path": [
-    "new-context",
-    "value",
-    "*"
-  ]
-}

data/datasets/lilac/databricks-dolly-15k-curated-en/new-context/value/near_dup/signal_manifest.json

@@ -1,41 +0,0 @@
-{
-  "files": [
-    "data-00000-of-00001.parquet"
-  ],
-  "parquet_id": "new-context.value.near_dup",
-  "data_schema": {
-    "fields": {
-      "new-context": {
-        "fields": {
-          "value": {
-            "repeated_field": {
-              "fields": {
-                "near_dup": {
-                  "fields": {
-                    "cluster_id": {
-                      "dtype": "uint32",
-                      "categorical": true
-                    }
-                  },
-                  "signal": {
-                    "threshold": 0.85,
-                    "signal_name": "near_dup"
-                  }
-                }
-              }
-            }
-          }
-        }
-      }
-    }
-  },
-  "signal": {
-    "threshold": 0.85,
-    "signal_name": "near_dup"
-  },
-  "enriched_path": [
-    "new-context",
-    "value",
-    "*"
-  ]
-}

data/datasets/lilac/databricks-dolly-15k-curated-en/new-context/value/pii/signal_manifest.json

@@ -1,50 +0,0 @@
-{
-  "files": [
-    "data-00000-of-00001.parquet"
-  ],
-  "parquet_id": "new-context.value.pii",
-  "data_schema": {
-    "fields": {
-      "new-context": {
-        "fields": {
-          "value": {
-            "repeated_field": {
-              "fields": {
-                "pii": {
-                  "fields": {
-                    "emails": {
-                      "repeated_field": {
-                        "dtype": "string_span"
-                      }
-                    },
-                    "ip_addresses": {
-                      "repeated_field": {
-                        "dtype": "string_span"
-                      }
-                    },
-                    "secrets": {
-                      "repeated_field": {
-                        "dtype": "string_span"
-                      }
-                    }
-                  },
-                  "signal": {
-                    "signal_name": "pii"
-                  }
-                }
-              }
-            }
-          }
-        }
-      }
-    }
-  },
-  "signal": {
-    "signal_name": "pii"
-  },
-  "enriched_path": [
-    "new-context",
-    "value",
-    "*"
-  ]
-}

data/datasets/lilac/databricks-dolly-15k-curated-en/new-context/value/text_statistics/signal_manifest.json

@@ -1,64 +0,0 @@
-{
-  "files": [
-    "data-00000-of-00001.parquet"
-  ],
-  "parquet_id": "new-context.value.text_statistics",
-  "data_schema": {
-    "fields": {
-      "new-context": {
-        "fields": {
-          "value": {
-            "repeated_field": {
-              "fields": {
-                "text_statistics": {
-                  "fields": {
-                    "num_characters": {
-                      "dtype": "int32"
-                    },
-                    "readability": {
-                      "dtype": "float32"
-                    },
-                    "log(type_token_ratio)": {
-                      "dtype": "float32"
-                    },
-                    "frac_non_ascii": {
-                      "dtype": "float32",
-                      "bins": [
-                        [
-                          "Low",
-                          null,
-                          0.15
-                        ],
-                        [
-                          "Medium",
-                          0.15,
-                          0.3
-                        ],
-                        [
-                          "High",
-                          0.3,
-                          null
-                        ]
-                      ]
-                    }
-                  },
-                  "signal": {
-                    "signal_name": "text_statistics"
-                  }
-                }
-              }
-            }
-          }
-        }
-      }
-    }
-  },
-  "signal": {
-    "signal_name": "text_statistics"
-  },
-  "enriched_path": [
-    "new-context",
-    "value",
-    "*"
-  ]
-}

data/datasets/lilac/databricks-dolly-15k-curated-en/new-instruction/value/lang_detection/signal_manifest.json

@@ -1,36 +0,0 @@
-{
-  "files": [
-    "data-00000-of-00001.parquet"
-  ],
-  "parquet_id": "new-instruction.value.lang_detection",
-  "data_schema": {
-    "fields": {
-      "new-instruction": {
-        "fields": {
-          "value": {
-            "repeated_field": {
-              "fields": {
-                "lang_detection": {
-                  "dtype": "string",
-                  "signal": {
-                    "split_by_paragraph": false,
-                    "signal_name": "lang_detection"
-                  }
-                }
-              }
-            }
-          }
-        }
-      }
-    }
-  },
-  "signal": {
-    "split_by_paragraph": false,
-    "signal_name": "lang_detection"
-  },
-  "enriched_path": [
-    "new-instruction",
-    "value",
-    "*"
-  ]
-}

data/datasets/lilac/databricks-dolly-15k-curated-en/new-instruction/value/near_dup/signal_manifest.json

@@ -1,41 +0,0 @@
-{
-  "files": [
-    "data-00000-of-00001.parquet"
-  ],
-  "parquet_id": "new-instruction.value.near_dup",
-  "data_schema": {
-    "fields": {
-      "new-instruction": {
-        "fields": {
-          "value": {
-            "repeated_field": {
-              "fields": {
-                "near_dup": {
-                  "fields": {
-                    "cluster_id": {
-                      "dtype": "uint32",
-                      "categorical": true
-                    }
-                  },
-                  "signal": {
-                    "threshold": 0.85,
-                    "signal_name": "near_dup"
-                  }
-                }
-              }
-            }
-          }
-        }
-      }
-    }
-  },
-  "signal": {
-    "threshold": 0.85,
-    "signal_name": "near_dup"
-  },
-  "enriched_path": [
-    "new-instruction",
-    "value",
-    "*"
-  ]
-}