SDSN-demo / udfPreprocess /paramconfig.cfg
prashant
haystack SDG classification
4a6159c
raw
history blame
313 Bytes
[lexical_search]
TOP_K = 10
THRESHOLD = 0.1
[semantic_search]
TOP_K = 10
MAX_SEQ_LENGTH = 64
MODEL_NAME = msmarco-distilbert-cos-v5
THRESHOLD = 0.1
[sdg]
THRESHOLD = 0.85
MODEL = 'jonas/sdg_classifier_osdg'
SPLIT_BY = 'word'
SPLIT_LENGTH = 110
[preprocessor]
SPLIT_OVERLAP_WORD = 10
SPLIT_OVERLAP_SENTENCE = 1