Upload folder using huggingface_hub

.gitattributes

@@ -52,3 +52,19 @@ data/datasets/lilac/open-asssistant-conversations/text/lang_detection/data-00000
 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/squad_v2/answers/text/lang_detection/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03103ba132a7209461f86bd1045431d06db431930344e4bdf97236347cc2164
+size 4738120

data/datasets/lilac/squad_v2/answers/text/lang_detection/signal_manifest.json

@@ -0,0 +1,39 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "lang_detection(answers.text)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "answers": {
+        "fields": {
+          "text": {
+            "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": [
+    "answers",
+    "text",
+    "*"
+  ]
+}

data/datasets/lilac/squad_v2/answers/text/near_dup/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4ae7259d126104da2aea0e1fad0c7cd83033f7774f0d44a2436f7c891fde34
+size 5224344

data/datasets/lilac/squad_v2/answers/text/near_dup/signal_manifest.json

@@ -0,0 +1,44 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "near_dup(answers.text)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "answers": {
+        "fields": {
+          "text": {
+            "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": [
+    "answers",
+    "text",
+    "*"
+  ]
+}

data/datasets/lilac/squad_v2/answers/text/pii/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf2c35877ae9957a987049c40a9a1b2edbe4b2d93b1da86bfeb739fae240040
+size 4841393

data/datasets/lilac/squad_v2/answers/text/pii/signal_manifest.json

@@ -0,0 +1,53 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "pii(answers.text)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "answers": {
+        "fields": {
+          "text": {
+            "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": [
+    "answers",
+    "text",
+    "*"
+  ]
+}

data/datasets/lilac/squad_v2/answers/text/text_statistics/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b5ddbc51455341a26121c5427bd0f32639515dad34d77561402df81d8ab903
+size 5100206

data/datasets/lilac/squad_v2/answers/text/text_statistics/signal_manifest.json

@@ -0,0 +1,67 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "text_statistics(answers.text)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "answers": {
+        "fields": {
+          "text": {
+            "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": [
+    "answers",
+    "text",
+    "*"
+  ]
+}

data/datasets/lilac/squad_v2/config.yml

@@ -0,0 +1,44 @@
+embeddings:
+- {embedding: gte-small, path: context}
+name: squad_v2
+namespace: local
+settings:
+  preferred_embedding: gte-small
+  ui:
+    media_paths:
+    - context
+    - question
+    - [answers, text, '*']
+signals:
+- path: context
+  signal: {signal_name: text_statistics}
+- path: context
+  signal: {signal_name: pii}
+- path: context
+  signal: {signal_name: near_dup}
+- path: question
+  signal: {signal_name: spacy_ner}
+- path: question
+  signal: {signal_name: pii}
+- path: [answers, text, '*']
+  signal: {signal_name: pii}
+- path: [answers, text, '*']
+  signal: {signal_name: spacy_ner}
+- path: [answers, text, '*']
+  signal: {signal_name: near_dup}
+- path: context
+  signal: {signal_name: lang_detection}
+- path: [answers, text, '*']
+  signal: {signal_name: lang_detection}
+- path: question
+  signal: {signal_name: near_dup}
+- path: question
+  signal: {signal_name: lang_detection}
+- path: [answers, text, '*']
+  signal: {signal_name: text_statistics}
+- path: question
+  signal: {signal_name: text_statistics}
+- path: context
+  signal: {signal_name: spacy_ner}
+source: {dataset_name: squad_v2, source_name: huggingface}
+tags: [machine-learning]

data/datasets/lilac/squad_v2/context/gte-small/hnsw.hnswlib.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a940b774cac49c315e321d8ed7705687499d9d53857ef8824f690b3a8d40c226
+size 601394376

data/datasets/lilac/squad_v2/context/gte-small/hnsw.lookup.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc41116b96f4e1fa547697ce62afe0fe7aba054a8d694b308e1e0270474801da
+size 10694495

data/datasets/lilac/squad_v2/context/gte-small/signal_manifest.json

@@ -0,0 +1,35 @@
+{
+  "files": [],
+  "parquet_id": "gte-small(context)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "context": {
+        "fields": {
+          "gte-small": {
+            "repeated_field": {
+              "fields": {
+                "embedding": {
+                  "dtype": "embedding"
+                }
+              },
+              "dtype": "string_span"
+            },
+            "signal": {
+              "signal_name": "gte-small"
+            }
+          }
+        }
+      }
+    }
+  },
+  "signal": {
+    "signal_name": "gte-small"
+  },
+  "enriched_path": [
+    "context"
+  ],
+  "vector_store": "hnsw"
+}

data/datasets/lilac/squad_v2/context/gte-small/spans.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69a524ee48c0c218eeb901ae265ae74b12511fee17fe31ae1627c0122e25f04
+size 8815907

data/datasets/lilac/squad_v2/context/lang_detection/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd10704958387059935d9e22f0415677a6daf3105105af8314314ce3c3114274
+size 4682949

data/datasets/lilac/squad_v2/context/lang_detection/signal_manifest.json

@@ -0,0 +1,31 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "lang_detection(context)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "context": {
+        "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": [
+    "context"
+  ]
+}

data/datasets/lilac/squad_v2/context/near_dup/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d3a359a05aa7c073900e4973569f808afa26c7bf0328c31e553efcc14bea90
+size 4962702

data/datasets/lilac/squad_v2/context/near_dup/signal_manifest.json

@@ -0,0 +1,36 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "near_dup(context)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "context": {
+        "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": [
+    "context"
+  ]
+}

data/datasets/lilac/squad_v2/context/pii/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0265330a9d7ff27498f4f0e9ddce89a027203d11941d6bc8f8d4334872346d9c
+size 4685328

data/datasets/lilac/squad_v2/context/pii/signal_manifest.json

@@ -0,0 +1,45 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "pii(context)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "context": {
+        "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": [
+    "context"
+  ]
+}

data/datasets/lilac/squad_v2/context/text_statistics/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1915970f9199dc82019cbb6089c85df3ddfd189848e0f34f549e34b617cd0f8
+size 5165481

data/datasets/lilac/squad_v2/context/text_statistics/signal_manifest.json

@@ -0,0 +1,59 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "text_statistics(context)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "context": {
+        "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": [
+    "context"
+  ]
+}

data/datasets/lilac/squad_v2/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f54db85b8bacd3ea30ecf70410441e300c783e621767c1d9746d6474852ceb
+size 27086838

data/datasets/lilac/squad_v2/manifest.json

@@ -0,0 +1,41 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "data_schema": {
+    "fields": {
+      "id": {
+        "dtype": "string"
+      },
+      "title": {
+        "dtype": "string"
+      },
+      "context": {
+        "dtype": "string"
+      },
+      "question": {
+        "dtype": "string"
+      },
+      "answers": {
+        "fields": {
+          "text": {
+            "repeated_field": {
+              "dtype": "string"
+            }
+          },
+          "answer_start": {
+            "repeated_field": {
+              "dtype": "int32"
+            }
+          }
+        }
+      },
+      "__hfsplit__": {
+        "dtype": "string"
+      },
+      "__rowid__": {
+        "dtype": "string"
+      }
+    }
+  }
+}

data/datasets/lilac/squad_v2/question/lang_detection/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d32aa3096865a6236fd620a16499876c919b245e26fe9a2809b3c02eebc13d
+size 4694280

data/datasets/lilac/squad_v2/question/lang_detection/signal_manifest.json

@@ -0,0 +1,31 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "lang_detection(question)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "question": {
+        "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": [
+    "question"
+  ]
+}

data/datasets/lilac/squad_v2/question/near_dup/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7e1d521750d16c37c70c378306ef22916e2d9715a565f1127d9e3626c966d4
+size 5571030

data/datasets/lilac/squad_v2/question/near_dup/signal_manifest.json

@@ -0,0 +1,36 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "near_dup(question)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "question": {
+        "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": [
+    "question"
+  ]
+}

data/datasets/lilac/squad_v2/question/pii/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72f4f32331de183cfe67be224ba473ec83ba8f855dafab97371580684718e4f
+size 4685523

data/datasets/lilac/squad_v2/question/pii/signal_manifest.json

@@ -0,0 +1,45 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "pii(question)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "question": {
+        "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": [
+    "question"
+  ]
+}

data/datasets/lilac/squad_v2/question/text_statistics/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36304efa2147c8737c1c4da192837aa855504ecfe9eb6f14d267c501bcaaa246
+size 5104750

data/datasets/lilac/squad_v2/question/text_statistics/signal_manifest.json

@@ -0,0 +1,59 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "text_statistics(question)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "question": {
+        "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": [
+    "question"
+  ]
+}