Upload folder using huggingface_hub

.gitattributes

@@ -56,3 +56,11 @@ data/datasets/lilac/pile-of-law-r-legaladvice/text/lang_detection/data-00000-of-
 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/open-asssistant-conversations/config.yml

@@ -0,0 +1,21 @@
+embeddings:
+- {embedding: gte-small, path: text}
+name: open-asssistant-conversations
+namespace: local
+settings:
+  preferred_embedding: gte-small
+  ui:
+    media_paths: [text]
+signals:
+- path: text
+  signal: {signal_name: text_statistics}
+- path: text
+  signal: {signal_name: lang_detection}
+- path: text
+  signal: {signal_name: near_dup}
+- path: text
+  signal: {signal_name: spacy_ner}
+- path: text
+  signal: {signal_name: pii}
+source: {dataset_name: OpenAssistant/oasst1, source_name: huggingface}
+tags: [machine-learning]

data/datasets/lilac/open-asssistant-conversations/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d53dbedb539cf7fa3f89d739f698fd3ccf1fbbd86dac20bd0b74cf674cc508e8
+size 42071566

data/datasets/lilac/open-asssistant-conversations/manifest.json

@@ -0,0 +1,118 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "data_schema": {
+    "fields": {
+      "message_id": {
+        "dtype": "string"
+      },
+      "parent_id": {
+        "dtype": "string"
+      },
+      "user_id": {
+        "dtype": "string"
+      },
+      "created_date": {
+        "dtype": "string"
+      },
+      "text": {
+        "dtype": "string"
+      },
+      "role": {
+        "dtype": "string"
+      },
+      "lang": {
+        "dtype": "string"
+      },
+      "review_count": {
+        "dtype": "int32"
+      },
+      "review_result": {
+        "dtype": "boolean"
+      },
+      "deleted": {
+        "dtype": "boolean"
+      },
+      "rank": {
+        "dtype": "int32"
+      },
+      "synthetic": {
+        "dtype": "boolean"
+      },
+      "model_name": {
+        "dtype": "string"
+      },
+      "detoxify": {
+        "fields": {
+          "toxicity": {
+            "dtype": "float64"
+          },
+          "severe_toxicity": {
+            "dtype": "float64"
+          },
+          "obscene": {
+            "dtype": "float64"
+          },
+          "identity_attack": {
+            "dtype": "float64"
+          },
+          "insult": {
+            "dtype": "float64"
+          },
+          "threat": {
+            "dtype": "float64"
+          },
+          "sexual_explicit": {
+            "dtype": "float64"
+          }
+        }
+      },
+      "message_tree_id": {
+        "dtype": "string"
+      },
+      "tree_state": {
+        "dtype": "string"
+      },
+      "emojis": {
+        "fields": {
+          "name": {
+            "repeated_field": {
+              "dtype": "string"
+            }
+          },
+          "count": {
+            "repeated_field": {
+              "dtype": "int32"
+            }
+          }
+        }
+      },
+      "labels": {
+        "fields": {
+          "name": {
+            "repeated_field": {
+              "dtype": "string"
+            }
+          },
+          "value": {
+            "repeated_field": {
+              "dtype": "float64"
+            }
+          },
+          "count": {
+            "repeated_field": {
+              "dtype": "int32"
+            }
+          }
+        }
+      },
+      "__hfsplit__": {
+        "dtype": "string"
+      },
+      "__rowid__": {
+        "dtype": "string"
+      }
+    }
+  }
+}

data/datasets/lilac/open-asssistant-conversations/text/gte-small/hnsw.hnswlib.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138c8efe1e911904c3702c582b892acc8c5616062a35773c31872a8969e2badf
+size 327991072

data/datasets/lilac/open-asssistant-conversations/text/gte-small/hnsw.lookup.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bcd3f617d324acd7e13d0d0fabd38065012bea40141579e16681bcdfdcaf46
+size 6171232

data/datasets/lilac/open-asssistant-conversations/text/gte-small/signal_manifest.json

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

data/datasets/lilac/open-asssistant-conversations/text/gte-small/spans.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1cda70a8dc3259ff058e5e3ffc24cfbaaafe3fb9ba5c1b836e0757180114e28
+size 5164058

data/datasets/lilac/open-asssistant-conversations/text/lang_detection/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8944421e23764080d8fde7460d08aa683ebbafc6fad2bd65654ea701ba50ca
+size 2980981

data/datasets/lilac/open-asssistant-conversations/text/lang_detection/signal_manifest.json

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

data/datasets/lilac/open-asssistant-conversations/text/near_dup/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2949cfca1b91bb99c56364fdb47679301b90d1f51bd1963f04fbbcbe093d15c
+size 3486319

data/datasets/lilac/open-asssistant-conversations/text/near_dup/signal_manifest.json

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

data/datasets/lilac/open-asssistant-conversations/text/pii/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c010e414a4379f8c1637c54864c46c7872a7ed0dc26990c5b755581d2073f8b
+size 2953059

data/datasets/lilac/open-asssistant-conversations/text/pii/signal_manifest.json

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

data/datasets/lilac/open-asssistant-conversations/text/text_statistics/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0f5af1af587a3b083dd7859f9cd4a5cf2943e41396c776db9a2a4f59eb4c9d
+size 3827015

data/datasets/lilac/open-asssistant-conversations/text/text_statistics/signal_manifest.json

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