File size: 926 Bytes
49a314a 3d34c75 43cd965 1d3978a 43cd965 49a314a a4bf4e8 7af394d a4bf4e8 2663a97 a4bf4e8 550b85d 2370cfa eaa8795 7d78a3b 49a314a 1d77594 685552c ce1209f 1d3978a ce1209f 40debb1 1e18f9c 2663a97 9dca2b8 2663a97 9dca2b8 2663a97 495891a 2663a97 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
[lexical_search]
TOP_K = 20
SPLIT_BY = word
SPLIT_LENGTH = 120
SPLIT_OVERLAP = 0
REMOVE_PUNC = 0
[semantic_search]
RETRIEVER_TOP_K = 10
MAX_SEQ_LENGTH = 384
RETRIEVER = all-mpnet-base-v2
RETRIEVER_FORMAT = sentence_transformers
EMBEDDING_DIM = 768
RETRIEVER_EMB_LAYER = -1
READER = deepset/tinyroberta-squad2
READER_TOP_K = 10
READER_TOP_K_PER_CANDIDATE = 1
SPLIT_BY = word
SPLIT_LENGTH = 120
SPLIT_OVERLAP = 10
RESPECT_SENTENCE_BOUNDARY = 1
REMOVE_PUNC = 0
[sdg]
THRESHOLD = 0.85
MODEL = jonas/sdg_classifier_osdg
SPLIT_BY = word
REMOVE_PUNC = 0
SPLIT_LENGTH = 120
SPLIT_OVERLAP = 10
RESPECT_SENTENCE_BOUNDARY = 1
TOP_KEY = 15
[coherence]
RETRIEVER_TOP_K = 10
MAX_SEQ_LENGTH = 512
RETRIEVER = msmarco-distilbert-dot-v5
RETRIEVER_FORMAT = sentence_transformers
RETRIEVER_EMB_LAYER = -1
EMBEDDING_DIM = 768
THRESHOLD = 0.55
SPLIT_BY = word
SPLIT_LENGTH = 120
SPLIT_OVERLAP = 10
RESPECT_SENTENCE_BOUNDARY = 1
REMOVE_PUNC = 0 |