| quant_stage: | |
| quant_modifiers: | |
| AWQModifier: | |
| config_groups: | |
| group_0: | |
| targets: [Linear] | |
| weights: | |
| num_bits: 4 | |
| type: int | |
| symmetric: true | |
| group_size: 32 | |
| strategy: group | |
| block_structure: null | |
| dynamic: false | |
| actorder: null | |
| observer: mse | |
| observer_kwargs: {} | |
| input_activations: null | |
| output_activations: null | |
| format: null | |
| targets: [Linear] | |
| ignore: [lm_head, model.embed_tokens, 're:.*input_layernorm$', 're:.*post_attention_layernorm$', | |
| model.norm, 're:.*mlp.gate$'] | |
| mappings: | |
| - smooth_layer: re:.*input_layernorm$ | |
| balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$'] | |
| - smooth_layer: re:.*v_proj$ | |
| balance_layers: ['re:.*o_proj$'] | |
| - smooth_layer: re:.*post_attention_layernorm$ | |
| balance_layers: ['re:.*mlp.experts.*.gate_proj$', 're:.*mlp.experts.*.up_proj$'] | |
| - smooth_layer: re:.*up_proj$ | |
| balance_layers: ['re:.*down_proj$'] | |
| duo_scaling: true | |