nm-testing
/

Phi-3.5-MoE-instruct-FP8

Model card Files Files and versions Community

File size: 152 Bytes

5a393d8

quant_stage:
  quant_modifiers:
    QuantizationModifier:
      ignore: [lm_head, 're:.*block_sparse_moe.gate']
      scheme: FP8
      targets: Linear