[SmoothQuantModifier(index=None, group=None, start=None, end=None, update=None, initialized_=True, finalized_=True, started_=True, ended_=True, smoothing_strength=0.5, mappings=[LayerMap(balance_layers=['re:.*q_proj', 're:.*k_proj', 're:.*v_proj'], smooth_layers='re:.*input_layernorm'), LayerMap(balance_layers=['re:.*gate_proj', 're:.*up_proj'], smooth_layers='re:.*post_attention_layernorm')], ignore=[], num_calibration_steps=None, calibration_function=None), GPTQModifier(config_groups=None, targets=['Linear'], ignore=[], scheme='W4A16', kv_cache_scheme=None, weight_observer=None, input_observer=None, output_observer=None, observer=None, bypass_divisibility_checks=False, index=None, group=None, start=None, end=None, update=None, initialized_=True, finalized_=True, started_=True, ended_=True, sequential_targets=None, block_size=128, dampening_frac=0.01, actorder=static, offload_hessians=False)]

Note: This model card was automatically generated. All structural modifiers and parameters used during compression are logged above.