[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), AWQModifier(config_groups=None, targets=['Linear'], ignore=[], scheme='W8A8', 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, mappings=[AWQMapping(smooth_layer='re:.*input_layernorm$', balance_layers=['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$'], activation_hook_target=None), AWQMapping(smooth_layer='re:.*v_proj$', balance_layers=['re:.*o_proj$'], activation_hook_target=None), AWQMapping(smooth_layer='re:.*post_attention_layernorm$', balance_layers=['re:.*gate_proj$', 're:.*up_proj$'], activation_hook_target=None), AWQMapping(smooth_layer='re:.*up_proj$', balance_layers=['re:.*down_proj$'], activation_hook_target=None)], offload_device='cpu', duo_scaling=True, n_grid=20)]

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