PR #17523 gguf_convert_endian.py: skip MXFP4 data

Commits

gguf_convert_endian.py: skip MXFP4 data

AlekseiNikiforovIBM committed 126 days ago
Use gguf.constants.GGML_QUANT_SIZES to determine block sizes

AlekseiNikiforovIBM committed 126 days ago

llama.cpp gguf_convert_endian.py: skip MXFP4 data #17523 Merged