|
: Compresses 16-bit weights to 4 bits, effectively reducing VRAM usage by ~75% (e.g., a 65B parameter model can be loaded with ~35GB instead of ~130GB).
The paper explains why NF4 is superior to standard 4-bit integers (Int4) or floating-point (Float4) formats: NF4.rar
: RNF4 mediates the degradation of the PML-RARα fusion protein. : Compresses 16-bit weights to 4 bits, effectively
💡 : If you are looking for the software/machine learning paper, search for "QLoRA" or "4-bit NormalFloat" on arXiv . NF4.rar