alpindale
/

Meta-Llama-3.1-8B-Instruct-W8A8-INT8-Dynamic-Per-Token

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Meta-Llama-3.1-8B-Instruct-W8A8-INT8-Dynamic-Per-Token

File size: 170 Bytes

527114e

DEFAULT_stage:
  DEFAULT_modifiers:
    SmoothQuantModifier: {smoothing_strength: 0.8}
    GPTQModifier:
      targets: Linear
      ignore: [lm_head]
      scheme: W8A8