Push

.gitattributes

@@ -1,21 +0,0 @@
-data/.cache/lilac/concept/lilac/negative-sentiment/cohere.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/non-english/cohere.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/non-english/openai.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/question/cohere.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/question/gte-base.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/question/openai.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/question/palm.pkl filter=lfs diff=lfs merge=lfs -text
-data/.cache/lilac/concept/lilac/source-code/cohere.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/.cache/lilac/concept/lilac/negative-sentiment/cohere.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:13bcab9d52ff84f47fe4311d1bbde68efde777a5f3e99bd843ecf69895a4f6a3
-size 2088021

data/.cache/lilac/concept/lilac/non-english/cohere.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8073ad4261c03aac8350bcee76a40669df0a529b89b605e4a991189c7ad549ed
-size 3374534

data/.cache/lilac/concept/lilac/non-english/openai.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3c924d11c7e0b61a76dfcafd4bd1cbf4f80afab97a5e537c0fb7ebb18db25a5d
-size 1275037

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fc23e270e1824e258a51ea5419de53e74b6cc23fa31ff586b6c2f0f0f7549b91
-size 1857652

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f6c694a83f498be11182ea462dba84e93970c502f687504f5b684a47f175c411
-size 17413997

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3287d4d06a78e0757f0b8586651e24fc7ac8f9d742a0091b24dd5bfc3b4c441f
-size 3301326

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6f25837df92c799823a7ea284d3046d10fd2d146e97610d739fd088a44172e57
-size 1672960

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6c199a5348b201c91db1926c12c47ec370b69badde06981d18dead800210acc2
-size 6558076

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:17cbb10cf538ab7e823d4db1fddf81977a155e3270a986b182370297e5a48380
-size 3301322

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:132800020bbe32723942388c651eac45ae9da9aa98e7bfdd46b3f5820e02a339
-size 1672951

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f2ce2b4f9bf3dba7d6afa146aad9b443d35987b230366b668fbf15325b27fcf8
-size 6254200

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fd6e9243c20ec84229419814178411b7f6f80a6d8e2f9e244fcc4f752d6ec5f0
-size 1194951

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b998b1370a2982689e6c5e0f099659f103130a52090f0f9f2b234abdc3c8d2b0
-size 2362458

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:98e077a03707541da691311fd28d9bed00ec9fb2a22a915adde2bc436f6362e6
-size 1194947

data/.cache/lilac/concept/lilac/source-code/cohere.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad4234a60f17ac8a068c3b407af1b63fd460800c9fd6c014da70d8eb3b0c0939
-size 1284715

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc3d3f95d84b64657ec4697ce899aee940d62725e0fb88c9f8b38f03298d89b3
-size 19602537

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0e9363d2faacb10fe0528f06df2237a44f9b1686f4100d3cca2cdb1a621a90c2
-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:b094a716fcbda3cd5b686457bf2510c0a17cabddac21d88d8c97f6a6908266ec
-size 1886446

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:08ee50c3a7679c15e442d12996ddac07bd9ffb8de30f8a607f6b4dd72e7f0343
-size 7384512

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e9d54189781c5a3e56f8640a7ed3516c82a411b09798e7dca84c6ba0f7efe48d
-size 3719128

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:654c96a6ef52b60a0f81d099c8bf4cda9957dde8d9aaea43f21cddc6c54c1ab5
-size 1886440

data/lilac.yml

@@ -0,0 +1,1969 @@
+# Lilac project config.
+# See https://lilacml.com/api_reference/index.html#lilac.Config for details.
+
+datasets:
+ - namespace: lilac
+ name: imdb
+ source:
+ dataset_name: imdb
+ source_name: huggingface
+ embeddings:
+ - path: text
+ embedding: gte-small
+ signals:
+ - path: text
+ signal:
+ signal_name: near_dup
+ - path: text
+ signal:
+ signal_name: pii
+ - path: text
+ signal:
+ signal_name: lang_detection
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: text
+ signal:
+ signal_name: text_statistics
+ settings:
+ ui:
+ media_paths:
+ - text
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: open-asssistant-conversations
+ source:
+ dataset_name: OpenAssistant/oasst1
+ source_name: huggingface
+ embeddings:
+ - path: text
+ embedding: gte-small
+ signals:
+ - path: text
+ signal:
+ signal_name: near_dup
+ - path: text
+ signal:
+ signal_name: pii
+ - path: text
+ signal:
+ signal_name: lang_detection
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: text
+ signal:
+ signal_name: text_statistics
+ settings:
+ ui:
+ media_paths:
+ - text
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: wikitext-2-raw-v1
+ source:
+ dataset_name: wikitext
+ config_name: wikitext-2-raw-v1
+ source_name: huggingface
+ embeddings:
+ - path: text
+ embedding: gte-small
+ signals:
+ - path: text
+ signal:
+ signal_name: near_dup
+ - path: text
+ signal:
+ signal_name: pii
+ - path: text
+ signal:
+ signal_name: lang_detection
+ - path: text
+ signal:
+ signal_name: text_statistics
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ settings:
+ ui:
+ media_paths:
+ - text
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: squad_v2
+ source:
+ dataset_name: squad_v2
+ source_name: huggingface
+ embeddings:
+ - path: context
+ embedding: gte-small
+ signals:
+ - path: context
+ signal:
+ signal_name: near_dup
+ - path: context
+ signal:
+ signal_name: pii
+ - path: context
+ signal:
+ signal_name: lang_detection
+ - path: context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: context
+ signal:
+ signal_name: text_statistics
+ - path: question
+ signal:
+ signal_name: near_dup
+ - path: question
+ signal:
+ signal_name: pii
+ - path: question
+ signal:
+ signal_name: lang_detection
+ - path: question
+ signal:
+ signal_name: text_statistics
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ signal_name: near_dup
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ signal_name: pii
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ signal_name: lang_detection
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ signal_name: text_statistics
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path:
+ - answers
+ - text
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ settings:
+ ui:
+ media_paths:
+ - context
+ - question
+ - - answers
+ - text
+ - '*'
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: databricks-dolly-15k-curated-en
+ source:
+ dataset_name: argilla/databricks-dolly-15k-curated-en
+ source_name: huggingface
+ embeddings:
+ - path: original-context
+ embedding: gte-small
+ - path:
+ - new-context
+ - value
+ - '*'
+ embedding: gte-small
+ signals:
+ - path: original-instruction
+ signal:
+ signal_name: near_dup
+ - path: original-instruction
+ signal:
+ signal_name: pii
+ - path: original-instruction
+ signal:
+ signal_name: lang_detection
+ - path: original-instruction
+ signal:
+ signal_name: text_statistics
+ - path: original-context
+ signal:
+ signal_name: near_dup
+ - path: original-context
+ signal:
+ signal_name: pii
+ - path: original-context
+ signal:
+ signal_name: lang_detection
+ - path: original-context
+ signal:
+ signal_name: text_statistics
+ - path: original-response
+ signal:
+ signal_name: near_dup
+ - path: original-response
+ signal:
+ signal_name: pii
+ - path: original-response
+ signal:
+ signal_name: lang_detection
+ - path: original-response
+ signal:
+ signal_name: text_statistics
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ signal_name: near_dup
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ signal_name: pii
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ signal_name: lang_detection
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ signal_name: text_statistics
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ signal_name: near_dup
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ signal_name: pii
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ signal_name: lang_detection
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ signal_name: text_statistics
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ signal_name: near_dup
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ signal_name: pii
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ signal_name: lang_detection
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ signal_name: text_statistics
+ - path: original-instruction
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: original-instruction
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: original-instruction
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: original-instruction
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: original-instruction
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: original-instruction
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: original-instruction
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: original-instruction
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: original-context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: original-context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: original-context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: original-context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: original-context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: original-context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: original-context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: original-context
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: original-response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: original-response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: original-response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: original-response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: original-response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: original-response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: original-response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: original-response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path:
+ - new-instruction
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path:
+ - new-context
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path:
+ - new-response
+ - value
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ settings:
+ ui:
+ media_paths:
+ - original-instruction
+ - original-context
+ - original-response
+ - - new-instruction
+ - value
+ - '*'
+ - - new-context
+ - value
+ - '*'
+ - - new-response
+ - value
+ - '*'
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: piqa
+ source:
+ dataset_name: piqa
+ source_name: huggingface
+ embeddings:
+ - path: goal
+ embedding: gte-small
+ - path: sol1
+ embedding: gte-small
+ - path: sol2
+ embedding: gte-small
+ signals:
+ - path: goal
+ signal:
+ signal_name: near_dup
+ - path: goal
+ signal:
+ signal_name: pii
+ - path: goal
+ signal:
+ signal_name: lang_detection
+ - path: goal
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: goal
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: goal
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: goal
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: goal
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: goal
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: goal
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: goal
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: goal
+ signal:
+ signal_name: text_statistics
+ - path: sol1
+ signal:
+ signal_name: near_dup
+ - path: sol1
+ signal:
+ signal_name: pii
+ - path: sol1
+ signal:
+ signal_name: lang_detection
+ - path: sol1
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: sol1
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: sol1
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: sol1
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: sol1
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: sol1
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: sol1
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: sol1
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: sol1
+ signal:
+ signal_name: text_statistics
+ - path: sol2
+ signal:
+ signal_name: near_dup
+ - path: sol2
+ signal:
+ signal_name: pii
+ - path: sol2
+ signal:
+ signal_name: lang_detection
+ - path: sol2
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: sol2
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: sol2
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: sol2
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: sol2
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: sol2
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: sol2
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: sol2
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: sol2
+ signal:
+ signal_name: text_statistics
+ settings:
+ ui:
+ media_paths:
+ - sol1
+ - sol2
+ - goal
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: OpenOrca-100k
+ source:
+ dataset_name: Open-Orca/OpenOrca
+ sample_size: 100000
+ source_name: huggingface
+ embeddings:
+ - path: question
+ embedding: gte-small
+ - path: response
+ embedding: gte-small
+ signals:
+ - path: question
+ signal:
+ signal_name: near_dup
+ - path: question
+ signal:
+ signal_name: pii
+ - path: question
+ signal:
+ signal_name: lang_detection
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: question
+ signal:
+ signal_name: text_statistics
+ - path: response
+ signal:
+ signal_name: near_dup
+ - path: response
+ signal:
+ signal_name: pii
+ - path: response
+ signal:
+ signal_name: lang_detection
+ - path: response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: response
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: response
+ signal:
+ signal_name: text_statistics
+ settings:
+ ui:
+ media_paths:
+ - question
+ - response
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: opus100-en-es-validation
+ source:
+ dataset_name: opus100
+ config_name: en-es
+ split: validation
+ source_name: huggingface
+ embeddings:
+ - path:
+ - translation
+ - en
+ embedding: gte-small
+ - path:
+ - translation
+ - es
+ embedding: gte-small
+ signals:
+ - path:
+ - translation
+ - en
+ signal:
+ signal_name: near_dup
+ - path:
+ - translation
+ - en
+ signal:
+ signal_name: pii
+ - path:
+ - translation
+ - en
+ signal:
+ signal_name: lang_detection
+ - path:
+ - translation
+ - en
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path:
+ - translation
+ - en
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path:
+ - translation
+ - en
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path:
+ - translation
+ - en
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path:
+ - translation
+ - en
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path:
+ - translation
+ - en
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path:
+ - translation
+ - en
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path:
+ - translation
+ - en
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path:
+ - translation
+ - en
+ signal:
+ signal_name: text_statistics
+ - path:
+ - translation
+ - es
+ signal:
+ signal_name: near_dup
+ - path:
+ - translation
+ - es
+ signal:
+ signal_name: pii
+ - path:
+ - translation
+ - es
+ signal:
+ signal_name: lang_detection
+ - path:
+ - translation
+ - es
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path:
+ - translation
+ - es
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path:
+ - translation
+ - es
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path:
+ - translation
+ - es
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path:
+ - translation
+ - es
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path:
+ - translation
+ - es
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path:
+ - translation
+ - es
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path:
+ - translation
+ - es
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path:
+ - translation
+ - es
+ signal:
+ signal_name: text_statistics
+ settings:
+ ui:
+ media_paths:
+ - - translation
+ - es
+ - - translation
+ - en
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: mmlu_professional_law
+ source:
+ dataset_name: cais/mmlu
+ config_name: professional_law
+ source_name: huggingface
+ embeddings:
+ - path: question
+ embedding: gte-small
+ - path:
+ - choices
+ - '*'
+ embedding: gte-small
+ signals:
+ - path: question
+ signal:
+ signal_name: near_dup
+ - path: question
+ signal:
+ signal_name: pii
+ - path: question
+ signal:
+ signal_name: lang_detection
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: question
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: question
+ signal:
+ signal_name: text_statistics
+ - path:
+ - choices
+ - '*'
+ signal:
+ signal_name: near_dup
+ - path:
+ - choices
+ - '*'
+ signal:
+ signal_name: pii
+ - path:
+ - choices
+ - '*'
+ signal:
+ signal_name: lang_detection
+ - path:
+ - choices
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path:
+ - choices
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path:
+ - choices
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path:
+ - choices
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path:
+ - choices
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path:
+ - choices
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path:
+ - choices
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path:
+ - choices
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path:
+ - choices
+ - '*'
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path:
+ - choices
+ - '*'
+ signal:
+ signal_name: text_statistics
+ settings:
+ ui:
+ media_paths:
+ - question
+ - - choices
+ - '*'
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: pile-of-law-r-legaladvice
+ source:
+ dataset_name: pile-of-law/pile-of-law
+ config_name: r_legaladvice
+ source_name: huggingface
+ embeddings:
+ - path: text
+ embedding: gte-small
+ signals:
+ - path: text
+ signal:
+ signal_name: near_dup
+ - path: text
+ signal:
+ signal_name: pii
+ - path: text
+ signal:
+ signal_name: lang_detection
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: text
+ signal:
+ signal_name: text_statistics
+ settings:
+ ui:
+ media_paths:
+ - text
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: science-qa-derek-thomas
+ source:
+ dataset_name: derek-thomas/ScienceQA
+ source_name: huggingface
+ embeddings:
+ - path: lecture
+ embedding: gte-small
+ signals:
+ - path: lecture
+ signal:
+ signal_name: near_dup
+ - path: lecture
+ signal:
+ signal_name: pii
+ - path: lecture
+ signal:
+ signal_name: lang_detection
+ - path: lecture
+ signal:
+ signal_name: text_statistics
+ - path: lecture
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: lecture
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: lecture
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: lecture
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: lecture
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: lecture
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: lecture
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: lecture
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ settings:
+ ui:
+ media_paths:
+ - lecture
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: enron-emails
+ source:
+ dataset_name: EleutherAI/pile
+ config_name: enron_emails
+ sample_size: 100000
+ source_name: huggingface
+ embeddings:
+ - path: text
+ embedding: gte-small
+ signals:
+ - path: text
+ signal:
+ signal_name: near_dup
+ - path: text
+ signal:
+ signal_name: pii
+ - path: text
+ signal:
+ signal_name: lang_detection
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: text
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: text
+ signal:
+ signal_name: text_statistics
+ settings:
+ ui:
+ media_paths:
+ - text
+ preferred_embedding: gte-small
+ - namespace: lilac
+ name: the_movies_dataset
+ source:
+ filepaths:
+ - https://storage.googleapis.com/lilac-data/datasets/the_movies_dataset/the_movies_dataset.csv
+ source_name: csv
+ embeddings:
+ - path: overview
+ embedding: gte-small
+ signals:
+ - path: overview
+ signal:
+ signal_name: near_dup
+ - path: overview
+ signal:
+ signal_name: pii
+ - path: overview
+ signal:
+ signal_name: lang_detection
+ - path: overview
+ signal:
+ signal_name: text_statistics
+ - path: overview
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: legal-termination
+ signal_name: concept_score
+ - path: overview
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: negative-sentiment
+ signal_name: concept_score
+ - path: overview
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: non-english
+ signal_name: concept_score
+ - path: overview
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: positive-sentiment
+ signal_name: concept_score
+ - path: overview
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: profanity
+ signal_name: concept_score
+ - path: overview
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: question
+ signal_name: concept_score
+ - path: overview
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: source-code
+ signal_name: concept_score
+ - path: overview
+ signal:
+ embedding: gte-small
+ namespace: lilac
+ concept_name: toxicity
+ signal_name: concept_score
+ settings:
+ ui:
+ media_paths:
+ - overview
+ preferred_embedding: gte-small