{ "config_groups": { "group_0": { "targets": [ "Linear" ], "weights": { "num_bits": 4, "type": "float", "symmetric": true, "group_size": 32, "strategy": "group", "block_structure": null, "dynamic": false, "actorder": null, "scale_dtype": "torch.uint8", "zp_dtype": null, "observer": "memoryless_minmax", "observer_kwargs": {} }, "input_activations": { "num_bits": 4, "type": "float", "symmetric": true, "group_size": 32, "strategy": "group", "block_structure": null, "dynamic": true, "actorder": null, "scale_dtype": "torch.uint8", "zp_dtype": null, "observer": null, "observer_kwargs": {} }, "output_activations": null, "format": null } }, "quant_method": "compressed-tensors", "kv_cache_scheme": null, "format": "mxfp4-pack-quantized", "quantization_status": "compressed", "global_compression_ratio": null, "ignore": [ "lm_head", "model.embed_tokens", "model.layers.0.input_layernorm", "model.layers.0.mlp.down_proj", "model.layers.0.mlp.gate_proj", "model.layers.0.mlp.up_proj", "model.layers.0.post_attention_layernorm", "model.layers.0.self_attn.k_norm", "model.layers.0.self_attn.k_proj", "model.layers.0.self_attn.o_proj", "model.layers.0.self_attn.q_norm", "model.layers.0.self_attn.q_proj", "model.layers.0.self_attn.v_proj", "model.layers.1.input_layernorm", "model.layers.1.mlp.down_proj", "model.layers.1.mlp.gate_proj", "model.layers.1.mlp.up_proj", "model.layers.1.post_attention_layernorm", "model.layers.1.self_attn.k_norm", "model.layers.1.self_attn.k_proj", "model.layers.1.self_attn.o_proj", "model.layers.1.self_attn.q_norm", "model.layers.1.self_attn.q_proj", "model.layers.1.self_attn.v_proj", "model.layers.10.input_layernorm", "model.layers.10.mlp.down_proj", "model.layers.10.mlp.gate_proj", "model.layers.10.mlp.up_proj", "model.layers.10.post_attention_layernorm", "model.layers.10.self_attn.k_norm", "model.layers.10.self_attn.k_proj", "model.layers.10.self_attn.o_proj", "model.layers.10.self_attn.q_norm", "model.layers.10.self_attn.q_proj", "model.layers.10.self_attn.v_proj", "model.layers.11.input_layernorm", "model.layers.11.mlp.down_proj", "model.layers.11.mlp.gate_proj", "model.layers.11.mlp.up_proj", "model.layers.11.post_attention_layernorm", "model.layers.11.self_attn.k_norm", "model.layers.11.self_attn.k_proj", "model.layers.11.self_attn.o_proj", "model.layers.11.self_attn.q_norm", "model.layers.11.self_attn.q_proj", "model.layers.11.self_attn.v_proj", "model.layers.12.input_layernorm", "model.layers.12.mlp.down_proj", "model.layers.12.mlp.gate_proj", "model.layers.12.mlp.up_proj", "model.layers.12.post_attention_layernorm", "model.layers.12.self_attn.k_norm", "model.layers.12.self_attn.k_proj", "model.layers.12.self_attn.o_proj", "model.layers.12.self_attn.q_norm", "model.layers.12.self_attn.q_proj", "model.layers.12.self_attn.v_proj", "model.layers.13.input_layernorm", "model.layers.13.mlp.down_proj", "model.layers.13.mlp.gate_proj", "model.layers.13.mlp.up_proj", "model.layers.13.post_attention_layernorm", "model.layers.13.self_attn.k_norm", "model.layers.13.self_attn.k_proj", "model.layers.13.self_attn.o_proj", "model.layers.13.self_attn.q_norm", "model.layers.13.self_attn.q_proj", "model.layers.13.self_attn.v_proj", "model.layers.14.input_layernorm", "model.layers.14.mlp.down_proj", "model.layers.14.mlp.gate_proj", "model.layers.14.mlp.up_proj", "model.layers.14.post_attention_layernorm", "model.layers.14.self_attn.k_norm", "model.layers.14.self_attn.k_proj", "model.layers.14.self_attn.o_proj", "model.layers.14.self_attn.q_norm", "model.layers.14.self_attn.q_proj", "model.layers.14.self_attn.v_proj", "model.layers.15.input_layernorm", "model.layers.15.mlp.down_proj", "model.layers.15.mlp.gate_proj", "model.layers.15.mlp.up_proj", "model.layers.15.post_attention_layernorm", "model.layers.15.self_attn.k_norm", "model.layers.15.self_attn.k_proj", "model.layers.15.self_attn.o_proj", "model.layers.15.self_attn.q_norm", "model.layers.15.self_attn.q_proj", "model.layers.15.self_attn.v_proj", "model.layers.16.input_layernorm", "model.layers.16.mlp.down_proj", "model.layers.16.mlp.gate_proj", "model.layers.16.mlp.up_proj", "model.layers.16.post_attention_layernorm", "model.layers.16.self_attn.k_norm", "model.layers.16.self_attn.k_proj", "model.layers.16.self_attn.o_proj", "model.layers.16.self_attn.q_norm", "model.layers.16.self_attn.q_proj", "model.layers.16.self_attn.v_proj", "model.layers.17.input_layernorm", "model.layers.17.mlp.down_proj", "model.layers.17.mlp.gate_proj", "model.layers.17.mlp.up_proj", "model.layers.17.post_attention_layernorm", "model.layers.17.self_attn.k_norm", "model.layers.17.self_attn.k_proj", "model.layers.17.self_attn.o_proj", "model.layers.17.self_attn.q_norm", "model.layers.17.self_attn.q_proj", "model.layers.17.self_attn.v_proj", "model.layers.18.input_layernorm", "model.layers.18.mlp.down_proj", "model.layers.18.mlp.gate_proj", "model.layers.18.mlp.up_proj", "model.layers.18.post_attention_layernorm", "model.layers.18.self_attn.k_norm", "model.layers.18.self_attn.k_proj", "model.layers.18.self_attn.o_proj", "model.layers.18.self_attn.q_norm", "model.layers.18.self_attn.q_proj", "model.layers.18.self_attn.v_proj", "model.layers.19.input_layernorm", "model.layers.19.mlp.down_proj", "model.layers.19.mlp.gate_proj", "model.layers.19.mlp.up_proj", "model.layers.19.post_attention_layernorm", "model.layers.19.self_attn.k_norm", "model.layers.19.self_attn.k_proj", "model.layers.19.self_attn.o_proj", "model.layers.19.self_attn.q_norm", "model.layers.19.self_attn.q_proj", "model.layers.19.self_attn.v_proj", "model.layers.2.input_layernorm", "model.layers.2.mlp.down_proj", "model.layers.2.mlp.gate_proj", "model.layers.2.mlp.up_proj", "model.layers.2.post_attention_layernorm", "model.layers.2.self_attn.k_norm", "model.layers.2.self_attn.k_proj", "model.layers.2.self_attn.o_proj", "model.layers.2.self_attn.q_norm", "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.v_proj", "model.layers.20.input_layernorm", "model.layers.20.mlp.down_proj", "model.layers.20.mlp.gate_proj", "model.layers.20.mlp.up_proj", "model.layers.20.post_attention_layernorm", "model.layers.20.self_attn.k_norm", "model.layers.20.self_attn.k_proj", "model.layers.20.self_attn.o_proj", "model.layers.20.self_attn.q_norm", "model.layers.20.self_attn.q_proj", "model.layers.20.self_attn.v_proj", "model.layers.21.input_layernorm", "model.layers.21.mlp.down_proj", "model.layers.21.mlp.gate_proj", "model.layers.21.mlp.up_proj", "model.layers.21.post_attention_layernorm", "model.layers.21.self_attn.k_norm", "model.layers.21.self_attn.k_proj", "model.layers.21.self_attn.o_proj", "model.layers.21.self_attn.q_norm", "model.layers.21.self_attn.q_proj", "model.layers.21.self_attn.v_proj", "model.layers.22.input_layernorm", "model.layers.22.mlp.down_proj", "model.layers.22.mlp.gate_proj", "model.layers.22.mlp.up_proj", "model.layers.22.post_attention_layernorm", "model.layers.22.self_attn.k_norm", "model.layers.22.self_attn.k_proj", "model.layers.22.self_attn.o_proj", "model.layers.22.self_attn.q_norm", "model.layers.22.self_attn.q_proj", "model.layers.22.self_attn.v_proj", "model.layers.23.input_layernorm", "model.layers.23.mlp.down_proj", "model.layers.23.mlp.gate_proj", "model.layers.23.mlp.up_proj", "model.layers.23.post_attention_layernorm", "model.layers.23.self_attn.k_norm", "model.layers.23.self_attn.k_proj", "model.layers.23.self_attn.o_proj", "model.layers.23.self_attn.q_norm", "model.layers.23.self_attn.q_proj", "model.layers.23.self_attn.v_proj", "model.layers.24.input_layernorm", "model.layers.24.mlp.down_proj", "model.layers.24.mlp.gate_proj", "model.layers.24.mlp.up_proj", "model.layers.24.post_attention_layernorm", "model.layers.24.self_attn.k_norm", "model.layers.24.self_attn.k_proj", "model.layers.24.self_attn.o_proj", "model.layers.24.self_attn.q_norm", "model.layers.24.self_attn.q_proj", "model.layers.24.self_attn.v_proj", "model.layers.25.input_layernorm", "model.layers.25.mlp.down_proj", "model.layers.25.mlp.gate_proj", "model.layers.25.mlp.up_proj", "model.layers.25.post_attention_layernorm", "model.layers.25.self_attn.k_norm", "model.layers.25.self_attn.k_proj", "model.layers.25.self_attn.o_proj", "model.layers.25.self_attn.q_norm", "model.layers.25.self_attn.q_proj", "model.layers.25.self_attn.v_proj", "model.layers.26.input_layernorm", "model.layers.26.mlp.down_proj", "model.layers.26.mlp.gate_proj", "model.layers.26.mlp.up_proj", "model.layers.26.post_attention_layernorm", "model.layers.26.self_attn.k_norm", "model.layers.26.self_attn.k_proj", "model.layers.26.self_attn.o_proj", "model.layers.26.self_attn.q_norm", "model.layers.26.self_attn.q_proj", "model.layers.26.self_attn.v_proj", "model.layers.27.input_layernorm", "model.layers.27.mlp.down_proj", "model.layers.27.mlp.gate_proj", "model.layers.27.mlp.up_proj", "model.layers.27.post_attention_layernorm", "model.layers.27.self_attn.k_norm", "model.layers.27.self_attn.k_proj", "model.layers.27.self_attn.o_proj", "model.layers.27.self_attn.q_norm", "model.layers.27.self_attn.q_proj", "model.layers.27.self_attn.v_proj", "model.layers.3.input_layernorm", "model.layers.3.mlp.down_proj", "model.layers.3.mlp.gate_proj", "model.layers.3.mlp.up_proj", "model.layers.3.post_attention_layernorm", "model.layers.3.self_attn.k_norm", "model.layers.3.self_attn.k_proj", "model.layers.3.self_attn.o_proj", "model.layers.3.self_attn.q_norm", "model.layers.3.self_attn.q_proj", "model.layers.3.self_attn.v_proj", "model.layers.4.input_layernorm", "model.layers.4.mlp.down_proj", "model.layers.4.mlp.gate_proj", "model.layers.4.mlp.up_proj", "model.layers.4.post_attention_layernorm", "model.layers.4.self_attn.k_norm", "model.layers.4.self_attn.k_proj", "model.layers.4.self_attn.o_proj", "model.layers.4.self_attn.q_norm", "model.layers.4.self_attn.q_proj", "model.layers.4.self_attn.v_proj", "model.layers.5.input_layernorm", "model.layers.5.mlp.down_proj", "model.layers.5.mlp.gate_proj", "model.layers.5.mlp.up_proj", "model.layers.5.post_attention_layernorm", "model.layers.5.self_attn.k_norm", "model.layers.5.self_attn.k_proj", "model.layers.5.self_attn.o_proj", "model.layers.5.self_attn.q_norm", "model.layers.5.self_attn.q_proj", "model.layers.5.self_attn.v_proj", "model.layers.6.input_layernorm", "model.layers.6.mlp.down_proj", "model.layers.6.mlp.gate_proj", "model.layers.6.mlp.up_proj", "model.layers.6.post_attention_layernorm", "model.layers.6.self_attn.k_norm", "model.layers.6.self_attn.k_proj", "model.layers.6.self_attn.o_proj", "model.layers.6.self_attn.q_norm", "model.layers.6.self_attn.q_proj", "model.layers.6.self_attn.v_proj", "model.layers.7.input_layernorm", "model.layers.7.mlp.down_proj", "model.layers.7.mlp.gate_proj", "model.layers.7.mlp.up_proj", "model.layers.7.post_attention_layernorm", "model.layers.7.self_attn.k_norm", "model.layers.7.self_attn.k_proj", "model.layers.7.self_attn.o_proj", "model.layers.7.self_attn.q_norm", "model.layers.7.self_attn.q_proj", "model.layers.7.self_attn.v_proj", "model.layers.8.input_layernorm", "model.layers.8.mlp.down_proj", "model.layers.8.mlp.gate_proj", "model.layers.8.mlp.up_proj", "model.layers.8.post_attention_layernorm", "model.layers.8.self_attn.k_norm", "model.layers.8.self_attn.k_proj", "model.layers.8.self_attn.o_proj", "model.layers.8.self_attn.q_norm", "model.layers.8.self_attn.q_proj", "model.layers.8.self_attn.v_proj", "model.layers.9.input_layernorm", "model.layers.9.mlp.down_proj", "model.layers.9.mlp.gate_proj", "model.layers.9.mlp.up_proj", "model.layers.9.post_attention_layernorm", "model.layers.9.self_attn.k_norm", "model.layers.9.self_attn.k_proj", "model.layers.9.self_attn.o_proj", "model.layers.9.self_attn.q_norm", "model.layers.9.self_attn.q_proj", "model.layers.9.self_attn.v_proj", "model.norm" ], "provider": "auto-round" }