It intelligently segments text into meaningful semantic chunks. Could be useful for RAG systems as text-chunking module.
-
mirth/chonky_distilbert_base_uncased_1
Token Classification • 66.4M • Updated • 24.8k • • 15 -
mirth/chonky_mmbert_small_multilingual_1
Token Classification • 0.1B • Updated • 188 • 23 -
mirth/chonky_modernbert_base_1
Token Classification • 0.1B • Updated • 32.5k • • 6 -
mirth/chonky_modernbert_large_1
Token Classification • 0.4B • Updated • 2.09k • • 2