{ "architectures": [ "InklingForConditionalGeneration" ], "model_type": "inkling_mm_model", "eos_token_id": 200006, "text_config": { "model_max_length": 1048576, "torch_dtype": "bfloat16", "hidden_size": 6144, "num_hidden_layers": 66, "vocab_size": 201024, "num_attention_heads": 64, "num_key_value_heads": 8, "head_dim": 128, "d_rel": 16, "rel_extent": 1024, "q_bias": false, "o_bias": false, "log_scaling_n_floor": 128000, "log_scaling_alpha": 0.1, "rms_norm_eps": 1e-06, "use_embed_norm": true, "local_layer_ids": [ 0, 1, 2, 3, 4, 6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 18, 19, 20, 21, 22, 24, 25, 26, 27, 28, 30, 31, 32, 33, 34, 36, 37, 38, 39, 40, 42, 43, 44, 45, 46, 48, 49, 50, 51, 52, 54, 55, 56, 57, 58, 60, 61, 62, 63, 64 ], "dense_mlp_idx": 2, "use_sconv": true, "sconv_kernel_size": 4, "unpadded_vocab_size": 200058, "logits_mup_width_multiplier": 24.0, "final_logit_softcapping": null, "swa_head_dim": 128, "swa_num_attention_heads": 64, "swa_num_key_value_heads": 16, "sliding_window_size": 512, "n_routed_experts": 256, "num_experts_per_tok": 6, "n_shared_experts": 2, "shared_expert_sink": true, "dense_intermediate_size": 24576, "intermediate_size": 3072, "route_scale": 8.0, "use_gate_bias": true, "gate_activation": "sigmoid", "norm_after_topk": true, "use_global_scale": true }, "audio_config": { "decoder_dmodel": 6144, "n_mel_bins": 80, "mel_vocab_size": 16, "bias": false, "dmel_min_value": -7.0, "dmel_max_value": 2.0, "use_audio_norm": true, "audio_mode": "dmel" }, "vision_config": { "vision_encoder_type": "hmlp", "decoder_dmodel": 6144, "patch_size": 40, "temporal_patch_size": 2, "n_channels": 3, "n_layers": 4, "use_vision_norm": true }, "mtp_config": { "num_nextn_predict_layers": 8, "chain_hidden_post_norm": false, "local_layer_ids": [ 0, 2, 4, 5, 6, 7 ] }, "quantization_config": { "global_quant_config": { "input_tensors": { "dtype": "fp4", "is_dynamic": true, "qscheme": "per_group", "ch_axis": -1, "group_size": 32, "block_size": null, "symmetric": null, "round_method": "half_even", "scale_type": "float", "scale_format": "e8m0", "scale_calculation_mode": "even", "mx_element_dtype": null, "observer_cls": "PerBlockMXObserver", "is_scale_quant": false, "enable_buffer_reuse": false, "max_input_numel": 4194304 }, "output_tensors": null, "weight": { "dtype": "fp4", "is_dynamic": false, "qscheme": "per_group", "ch_axis": -1, "group_size": 32, "block_size": null, "symmetric": null, "round_method": "half_even", "scale_type": "float", "scale_format": "e8m0", "scale_calculation_mode": "even", "mx_element_dtype": null, "observer_cls": "PerBlockMXObserver", "is_scale_quant": false, "enable_buffer_reuse": false, "max_input_numel": 4194304 }, "bias": null, "target_device": null }, "exclude": [ "model.audio.encoder", "model.llm.layers.0.attn.k_sconv", "model.llm.layers.0.attn.v_sconv", "model.llm.layers.0.attn.wk_dv", "model.llm.layers.0.attn.wo_ud", "model.llm.layers.0.attn.wq_du", "model.llm.layers.0.attn.wr_du", "model.llm.layers.0.attn.wv_dv", "model.llm.layers.0.attn_sconv", "model.llm.layers.0.mlp.w13_dn", "model.llm.layers.0.mlp.w2_md", "model.llm.layers.0.mlp_sconv", "model.llm.layers.1.attn.k_sconv", "model.llm.layers.1.attn.v_sconv", "model.llm.layers.1.attn.wk_dv", "model.llm.layers.1.attn.wo_ud", "model.llm.layers.1.attn.wq_du", "model.llm.layers.1.attn.wr_du", "model.llm.layers.1.attn.wv_dv", "model.llm.layers.1.attn_sconv", "model.llm.layers.1.mlp.w13_dn", "model.llm.layers.1.mlp.w2_md", "model.llm.layers.1.mlp_sconv", "model.llm.layers.10.attn.k_sconv", "model.llm.layers.10.attn.v_sconv", "model.llm.layers.10.attn.wk_dv", "model.llm.layers.10.attn.wo_ud", "model.llm.layers.10.attn.wq_du", "model.llm.layers.10.attn.wr_du", "model.llm.layers.10.attn.wv_dv", "model.llm.layers.10.attn_sconv", "model.llm.layers.10.mlp.gate", "model.llm.layers.10.mlp_sconv", "model.llm.layers.11.attn.k_sconv", "model.llm.layers.11.attn.v_sconv", "model.llm.layers.11.attn.wk_dv", "model.llm.layers.11.attn.wo_ud", "model.llm.layers.11.attn.wq_du", "model.llm.layers.11.attn.wr_du", "model.llm.layers.11.attn.wv_dv", "model.llm.layers.11.attn_sconv", "model.llm.layers.11.mlp.gate", "model.llm.layers.11.mlp_sconv", "model.llm.layers.12.attn.k_sconv", "model.llm.layers.12.attn.v_sconv", "model.llm.layers.12.attn.wk_dv", "model.llm.layers.12.attn.wo_ud", "model.llm.layers.12.attn.wq_du", "model.llm.layers.12.attn.wr_du", "model.llm.layers.12.attn.wv_dv", "model.llm.layers.12.attn_sconv", "model.llm.layers.12.mlp.gate", "model.llm.layers.12.mlp_sconv", "model.llm.layers.13.attn.k_sconv", "model.llm.layers.13.attn.v_sconv", "model.llm.layers.13.attn.wk_dv", "model.llm.layers.13.attn.wo_ud", "model.llm.layers.13.attn.wq_du", "model.llm.layers.13.attn.wr_du", "model.llm.layers.13.attn.wv_dv", "model.llm.layers.13.attn_sconv", "model.llm.layers.13.mlp.gate", "model.llm.layers.13.mlp_sconv", "model.llm.layers.14.attn.k_sconv", "model.llm.layers.14.attn.v_sconv", "model.llm.layers.14.attn.wk_dv", "model.llm.layers.14.attn.wo_ud", "model.llm.layers.14.attn.wq_du", "model.llm.layers.14.attn.wr_du", "model.llm.layers.14.attn.wv_dv", "model.llm.layers.14.attn_sconv", "model.llm.layers.14.mlp.gate", "model.llm.layers.14.mlp_sconv", "model.llm.layers.15.attn.k_sconv", "model.llm.layers.15.attn.v_sconv", "model.llm.layers.15.attn.wk_dv", "model.llm.layers.15.attn.wo_ud", "model.llm.layers.15.attn.wq_du", "model.llm.layers.15.attn.wr_du", "model.llm.layers.15.attn.wv_dv", "model.llm.layers.15.attn_sconv", "model.llm.layers.15.mlp.gate", "model.llm.layers.15.mlp_sconv", "model.llm.layers.16.attn.k_sconv", "model.llm.layers.16.attn.v_sconv", "model.llm.layers.16.attn.wk_dv", "model.llm.layers.16.attn.wo_ud", "model.llm.layers.16.attn.wq_du", "model.llm.layers.16.attn.wr_du", "model.llm.layers.16.attn.wv_dv", "model.llm.layers.16.attn_sconv", "model.llm.layers.16.mlp.gate", "model.llm.layers.16.mlp_sconv", "model.llm.layers.17.attn.k_sconv", "model.llm.layers.17.attn.v_sconv", "model.llm.layers.17.attn.wk_dv", "model.llm.layers.17.attn.wo_ud", "model.llm.layers.17.attn.wq_du", "model.llm.layers.17.attn.wr_du", "model.llm.layers.17.attn.wv_dv", "model.llm.layers.17.attn_sconv", "model.llm.layers.17.mlp.gate", "model.llm.layers.17.mlp_sconv", "model.llm.layers.18.attn.k_sconv", "model.llm.layers.18.attn.v_sconv", "model.llm.layers.18.attn.wk_dv", "model.llm.layers.18.attn.wo_ud", "model.llm.layers.18.attn.wq_du", "model.llm.layers.18.attn.wr_du", "model.llm.layers.18.attn.wv_dv", "model.llm.layers.18.attn_sconv", "model.llm.layers.18.mlp.gate", "model.llm.layers.18.mlp_sconv", "model.llm.layers.19.attn.k_sconv", "model.llm.layers.19.attn.v_sconv", "model.llm.layers.19.attn.wk_dv", "model.llm.layers.19.attn.wo_ud", "model.llm.layers.19.attn.wq_du", "model.llm.layers.19.attn.wr_du", "model.llm.layers.19.attn.wv_dv", "model.llm.layers.19.attn_sconv", "model.llm.layers.19.mlp.gate", "model.llm.layers.19.mlp_sconv", "model.llm.layers.2.attn.k_sconv", "model.llm.layers.2.attn.v_sconv", "model.llm.layers.2.attn.wk_dv", "model.llm.layers.2.attn.wo_ud", "model.llm.layers.2.attn.wq_du", "model.llm.layers.2.attn.wr_du", "model.llm.layers.2.attn.wv_dv", "model.llm.layers.2.attn_sconv", "model.llm.layers.2.mlp.experts.w13_weight", "model.llm.layers.2.mlp.experts.w2_weight", "model.llm.layers.2.mlp.gate", "model.llm.layers.2.mlp_sconv", "model.llm.layers.20.attn.k_sconv", "model.llm.layers.20.attn.v_sconv", "model.llm.layers.20.attn.wk_dv", "model.llm.layers.20.attn.wo_ud", "model.llm.layers.20.attn.wq_du", "model.llm.layers.20.attn.wr_du", "model.llm.layers.20.attn.wv_dv", "model.llm.layers.20.attn_sconv", "model.llm.layers.20.mlp.gate", "model.llm.layers.20.mlp_sconv", "model.llm.layers.21.attn.k_sconv", "model.llm.layers.21.attn.v_sconv", "model.llm.layers.21.attn.wk_dv", "model.llm.layers.21.attn.wo_ud", "model.llm.layers.21.attn.wq_du", "model.llm.layers.21.attn.wr_du", "model.llm.layers.21.attn.wv_dv", "model.llm.layers.21.attn_sconv", "model.llm.layers.21.mlp.gate", "model.llm.layers.21.mlp_sconv", "model.llm.layers.22.attn.k_sconv", "model.llm.layers.22.attn.v_sconv", "model.llm.layers.22.attn.wk_dv", "model.llm.layers.22.attn.wo_ud", "model.llm.layers.22.attn.wq_du", "model.llm.layers.22.attn.wr_du", "model.llm.layers.22.attn.wv_dv", "model.llm.layers.22.attn_sconv", "model.llm.layers.22.mlp.gate", "model.llm.layers.22.mlp_sconv", "model.llm.layers.23.attn.k_sconv", "model.llm.layers.23.attn.v_sconv", "model.llm.layers.23.attn.wk_dv", "model.llm.layers.23.attn.wo_ud", "model.llm.layers.23.attn.wq_du", "model.llm.layers.23.attn.wr_du", "model.llm.layers.23.attn.wv_dv", "model.llm.layers.23.attn_sconv", "model.llm.layers.23.mlp.gate", "model.llm.layers.23.mlp_sconv", "model.llm.layers.24.attn.k_sconv", "model.llm.layers.24.attn.v_sconv", "model.llm.layers.24.attn.wk_dv", "model.llm.layers.24.attn.wo_ud", "model.llm.layers.24.attn.wq_du", "model.llm.layers.24.attn.wr_du", "model.llm.layers.24.attn.wv_dv", "model.llm.layers.24.attn_sconv", "model.llm.layers.24.mlp.gate", "model.llm.layers.24.mlp_sconv", "model.llm.layers.25.attn.k_sconv", "model.llm.layers.25.attn.v_sconv", "model.llm.layers.25.attn.wk_dv", "model.llm.layers.25.attn.wo_ud", "model.llm.layers.25.attn.wq_du", "model.llm.layers.25.attn.wr_du", "model.llm.layers.25.attn.wv_dv", "model.llm.layers.25.attn_sconv", "model.llm.layers.25.mlp.gate", "model.llm.layers.25.mlp_sconv", "model.llm.layers.26.attn.k_sconv", "model.llm.layers.26.attn.v_sconv", "model.llm.layers.26.attn.wk_dv", "model.llm.layers.26.attn.wo_ud", "model.llm.layers.26.attn.wq_du", "model.llm.layers.26.attn.wr_du", "model.llm.layers.26.attn.wv_dv", "model.llm.layers.26.attn_sconv", "model.llm.layers.26.mlp.gate", "model.llm.layers.26.mlp_sconv", "model.llm.layers.27.attn.k_sconv", "model.llm.layers.27.attn.v_sconv", "model.llm.layers.27.attn.wk_dv", "model.llm.layers.27.attn.wo_ud", "model.llm.layers.27.attn.wq_du", "model.llm.layers.27.attn.wr_du", "model.llm.layers.27.attn.wv_dv", "model.llm.layers.27.attn_sconv", "model.llm.layers.27.mlp.gate", "model.llm.layers.27.mlp_sconv", "model.llm.layers.28.attn.k_sconv", "model.llm.layers.28.attn.v_sconv", "model.llm.layers.28.attn.wk_dv", "model.llm.layers.28.attn.wo_ud", "model.llm.layers.28.attn.wq_du", "model.llm.layers.28.attn.wr_du", "model.llm.layers.28.attn.wv_dv", "model.llm.layers.28.attn_sconv", "model.llm.layers.28.mlp.gate", "model.llm.layers.28.mlp_sconv", "model.llm.layers.29.attn.k_sconv", "model.llm.layers.29.attn.v_sconv", "model.llm.layers.29.attn.wk_dv", "model.llm.layers.29.attn.wo_ud", "model.llm.layers.29.attn.wq_du", "model.llm.layers.29.attn.wr_du", "model.llm.layers.29.attn.wv_dv", "model.llm.layers.29.attn_sconv", "model.llm.layers.29.mlp.gate", "model.llm.layers.29.mlp_sconv", "model.llm.layers.3.attn.k_sconv", "model.llm.layers.3.attn.v_sconv", "model.llm.layers.3.attn.wk_dv", "model.llm.layers.3.attn.wo_ud", "model.llm.layers.3.attn.wq_du", "model.llm.layers.3.attn.wr_du", "model.llm.layers.3.attn.wv_dv", "model.llm.layers.3.attn_sconv", "model.llm.layers.3.mlp.gate", "model.llm.layers.3.mlp_sconv", "model.llm.layers.30.attn.k_sconv", "model.llm.layers.30.attn.v_sconv", "model.llm.layers.30.attn.wk_dv", "model.llm.layers.30.attn.wo_ud", "model.llm.layers.30.attn.wq_du", "model.llm.layers.30.attn.wr_du", "model.llm.layers.30.attn.wv_dv", "model.llm.layers.30.attn_sconv", "model.llm.layers.30.mlp.gate", "model.llm.layers.30.mlp_sconv", "model.llm.layers.31.attn.k_sconv", "model.llm.layers.31.attn.v_sconv", "model.llm.layers.31.attn.wk_dv", "model.llm.layers.31.attn.wo_ud", "model.llm.layers.31.attn.wq_du", "model.llm.layers.31.attn.wr_du", "model.llm.layers.31.attn.wv_dv", "model.llm.layers.31.attn_sconv", "model.llm.layers.31.mlp.gate", "model.llm.layers.31.mlp_sconv", "model.llm.layers.32.attn.k_sconv", "model.llm.layers.32.attn.v_sconv", "model.llm.layers.32.attn.wk_dv", "model.llm.layers.32.attn.wo_ud", "model.llm.layers.32.attn.wq_du", "model.llm.layers.32.attn.wr_du", "model.llm.layers.32.attn.wv_dv", "model.llm.layers.32.attn_sconv", "model.llm.layers.32.mlp.gate", "model.llm.layers.32.mlp_sconv", "model.llm.layers.33.attn.k_sconv", "model.llm.layers.33.attn.v_sconv", "model.llm.layers.33.attn.wk_dv", "model.llm.layers.33.attn.wo_ud", "model.llm.layers.33.attn.wq_du", "model.llm.layers.33.attn.wr_du", "model.llm.layers.33.attn.wv_dv", "model.llm.layers.33.attn_sconv", "model.llm.layers.33.mlp.gate", "model.llm.layers.33.mlp_sconv", "model.llm.layers.34.attn.k_sconv", "model.llm.layers.34.attn.v_sconv", "model.llm.layers.34.attn.wk_dv", "model.llm.layers.34.attn.wo_ud", "model.llm.layers.34.attn.wq_du", "model.llm.layers.34.attn.wr_du", "model.llm.layers.34.attn.wv_dv", "model.llm.layers.34.attn_sconv", "model.llm.layers.34.mlp.gate", "model.llm.layers.34.mlp_sconv", "model.llm.layers.35.attn.k_sconv", "model.llm.layers.35.attn.v_sconv", "model.llm.layers.35.attn.wk_dv", "model.llm.layers.35.attn.wo_ud", "model.llm.layers.35.attn.wq_du", "model.llm.layers.35.attn.wr_du", "model.llm.layers.35.attn.wv_dv", "model.llm.layers.35.attn_sconv", "model.llm.layers.35.mlp.gate", "model.llm.layers.35.mlp_sconv", "model.llm.layers.36.attn.k_sconv", "model.llm.layers.36.attn.v_sconv", "model.llm.layers.36.attn.wk_dv", "model.llm.layers.36.attn.wo_ud", "model.llm.layers.36.attn.wq_du", "model.llm.layers.36.attn.wr_du", "model.llm.layers.36.attn.wv_dv", "model.llm.layers.36.attn_sconv", "model.llm.layers.36.mlp.gate", "model.llm.layers.36.mlp_sconv", "model.llm.layers.37.attn.k_sconv", "model.llm.layers.37.attn.v_sconv", "model.llm.layers.37.attn.wk_dv", "model.llm.layers.37.attn.wo_ud", "model.llm.layers.37.attn.wq_du", "model.llm.layers.37.attn.wr_du", "model.llm.layers.37.attn.wv_dv", "model.llm.layers.37.attn_sconv", "model.llm.layers.37.mlp.gate", "model.llm.layers.37.mlp_sconv", "model.llm.layers.38.attn.k_sconv", "model.llm.layers.38.attn.v_sconv", "model.llm.layers.38.attn.wk_dv", "model.llm.layers.38.attn.wo_ud", "model.llm.layers.38.attn.wq_du", "model.llm.layers.38.attn.wr_du", "model.llm.layers.38.attn.wv_dv", "model.llm.layers.38.attn_sconv", "model.llm.layers.38.mlp.gate", "model.llm.layers.38.mlp_sconv", "model.llm.layers.39.attn.k_sconv", "model.llm.layers.39.attn.v_sconv", "model.llm.layers.39.attn.wk_dv", "model.llm.layers.39.attn.wo_ud", "model.llm.layers.39.attn.wq_du", "model.llm.layers.39.attn.wr_du", "model.llm.layers.39.attn.wv_dv", "model.llm.layers.39.attn_sconv", "model.llm.layers.39.mlp.gate", "model.llm.layers.39.mlp_sconv", "model.llm.layers.4.attn.k_sconv", "model.llm.layers.4.attn.v_sconv", "model.llm.layers.4.attn.wk_dv", "model.llm.layers.4.attn.wo_ud", "model.llm.layers.4.attn.wq_du", "model.llm.layers.4.attn.wr_du", "model.llm.layers.4.attn.wv_dv", "model.llm.layers.4.attn_sconv", "model.llm.layers.4.mlp.gate", "model.llm.layers.4.mlp_sconv", "model.llm.layers.40.attn.k_sconv", "model.llm.layers.40.attn.v_sconv", "model.llm.layers.40.attn.wk_dv", "model.llm.layers.40.attn.wo_ud", "model.llm.layers.40.attn.wq_du", "model.llm.layers.40.attn.wr_du", "model.llm.layers.40.attn.wv_dv", "model.llm.layers.40.attn_sconv", "model.llm.layers.40.mlp.gate", "model.llm.layers.40.mlp_sconv", "model.llm.layers.41.attn.k_sconv", "model.llm.layers.41.attn.v_sconv", "model.llm.layers.41.attn.wk_dv", "model.llm.layers.41.attn.wo_ud", "model.llm.layers.41.attn.wq_du", "model.llm.layers.41.attn.wr_du", "model.llm.layers.41.attn.wv_dv", "model.llm.layers.41.attn_sconv", "model.llm.layers.41.mlp.gate", "model.llm.layers.41.mlp_sconv", "model.llm.layers.42.attn.k_sconv", "model.llm.layers.42.attn.v_sconv", "model.llm.layers.42.attn.wk_dv", "model.llm.layers.42.attn.wo_ud", "model.llm.layers.42.attn.wq_du", "model.llm.layers.42.attn.wr_du", "model.llm.layers.42.attn.wv_dv", "model.llm.layers.42.attn_sconv", "model.llm.layers.42.mlp.gate", "model.llm.layers.42.mlp_sconv", "model.llm.layers.43.attn.k_sconv", "model.llm.layers.43.attn.v_sconv", "model.llm.layers.43.attn.wk_dv", "model.llm.layers.43.attn.wo_ud", "model.llm.layers.43.attn.wq_du", "model.llm.layers.43.attn.wr_du", "model.llm.layers.43.attn.wv_dv", "model.llm.layers.43.attn_sconv", "model.llm.layers.43.mlp.gate", "model.llm.layers.43.mlp_sconv", "model.llm.layers.44.attn.k_sconv", "model.llm.layers.44.attn.v_sconv", "model.llm.layers.44.attn.wk_dv", "model.llm.layers.44.attn.wo_ud", "model.llm.layers.44.attn.wq_du", "model.llm.layers.44.attn.wr_du", "model.llm.layers.44.attn.wv_dv", "model.llm.layers.44.attn_sconv", "model.llm.layers.44.mlp.gate", "model.llm.layers.44.mlp_sconv", "model.llm.layers.45.attn.k_sconv", "model.llm.layers.45.attn.v_sconv", "model.llm.layers.45.attn.wk_dv", "model.llm.layers.45.attn.wo_ud", "model.llm.layers.45.attn.wq_du", "model.llm.layers.45.attn.wr_du", "model.llm.layers.45.attn.wv_dv", "model.llm.layers.45.attn_sconv", "model.llm.layers.45.mlp.gate", "model.llm.layers.45.mlp_sconv", "model.llm.layers.46.attn.k_sconv", "model.llm.layers.46.attn.v_sconv", "model.llm.layers.46.attn.wk_dv", "model.llm.layers.46.attn.wo_ud", "model.llm.layers.46.attn.wq_du", "model.llm.layers.46.attn.wr_du", "model.llm.layers.46.attn.wv_dv", "model.llm.layers.46.attn_sconv", "model.llm.layers.46.mlp.gate", "model.llm.layers.46.mlp_sconv", "model.llm.layers.47.attn.k_sconv", "model.llm.layers.47.attn.v_sconv", "model.llm.layers.47.attn.wk_dv", "model.llm.layers.47.attn.wo_ud", "model.llm.layers.47.attn.wq_du", "model.llm.layers.47.attn.wr_du", "model.llm.layers.47.attn.wv_dv", "model.llm.layers.47.attn_sconv", "model.llm.layers.47.mlp.gate", "model.llm.layers.47.mlp_sconv", "model.llm.layers.48.attn.k_sconv", "model.llm.layers.48.attn.v_sconv", "model.llm.layers.48.attn.wk_dv", "model.llm.layers.48.attn.wo_ud", "model.llm.layers.48.attn.wq_du", "model.llm.layers.48.attn.wr_du", "model.llm.layers.48.attn.wv_dv", "model.llm.layers.48.attn_sconv", "model.llm.layers.48.mlp.gate", "model.llm.layers.48.mlp_sconv", "model.llm.layers.49.attn.k_sconv", "model.llm.layers.49.attn.v_sconv", "model.llm.layers.49.attn.wk_dv", "model.llm.layers.49.attn.wo_ud", "model.llm.layers.49.attn.wq_du", "model.llm.layers.49.attn.wr_du", "model.llm.layers.49.attn.wv_dv", "model.llm.layers.49.attn_sconv", "model.llm.layers.49.mlp.gate", "model.llm.layers.49.mlp_sconv", "model.llm.layers.5.attn.k_sconv", "model.llm.layers.5.attn.v_sconv", "model.llm.layers.5.attn.wk_dv", "model.llm.layers.5.attn.wo_ud", "model.llm.layers.5.attn.wq_du", "model.llm.layers.5.attn.wr_du", "model.llm.layers.5.attn.wv_dv", "model.llm.layers.5.attn_sconv", "model.llm.layers.5.mlp.gate", "model.llm.layers.5.mlp_sconv", "model.llm.layers.50.attn.k_sconv", "model.llm.layers.50.attn.v_sconv", "model.llm.layers.50.attn.wk_dv", "model.llm.layers.50.attn.wo_ud", "model.llm.layers.50.attn.wq_du", "model.llm.layers.50.attn.wr_du", "model.llm.layers.50.attn.wv_dv", "model.llm.layers.50.attn_sconv", "model.llm.layers.50.mlp.gate", "model.llm.layers.50.mlp_sconv", "model.llm.layers.51.attn.k_sconv", "model.llm.layers.51.attn.v_sconv", "model.llm.layers.51.attn.wk_dv", "model.llm.layers.51.attn.wo_ud", "model.llm.layers.51.attn.wq_du", "model.llm.layers.51.attn.wr_du", "model.llm.layers.51.attn.wv_dv", "model.llm.layers.51.attn_sconv", "model.llm.layers.51.mlp.gate", "model.llm.layers.51.mlp_sconv", "model.llm.layers.52.attn.k_sconv", "model.llm.layers.52.attn.v_sconv", "model.llm.layers.52.attn.wk_dv", "model.llm.layers.52.attn.wo_ud", "model.llm.layers.52.attn.wq_du", "model.llm.layers.52.attn.wr_du", "model.llm.layers.52.attn.wv_dv", "model.llm.layers.52.attn_sconv", "model.llm.layers.52.mlp.gate", "model.llm.layers.52.mlp_sconv", "model.llm.layers.53.attn.k_sconv", "model.llm.layers.53.attn.v_sconv", "model.llm.layers.53.attn.wk_dv", "model.llm.layers.53.attn.wo_ud", "model.llm.layers.53.attn.wq_du", "model.llm.layers.53.attn.wr_du", "model.llm.layers.53.attn.wv_dv", "model.llm.layers.53.attn_sconv", "model.llm.layers.53.mlp.gate", "model.llm.layers.53.mlp_sconv", "model.llm.layers.54.attn.k_sconv", "model.llm.layers.54.attn.v_sconv", "model.llm.layers.54.attn.wk_dv", "model.llm.layers.54.attn.wo_ud", "model.llm.layers.54.attn.wq_du", "model.llm.layers.54.attn.wr_du", "model.llm.layers.54.attn.wv_dv", "model.llm.layers.54.attn_sconv", "model.llm.layers.54.mlp.gate", "model.llm.layers.54.mlp_sconv", "model.llm.layers.55.attn.k_sconv", "model.llm.layers.55.attn.v_sconv", "model.llm.layers.55.attn.wk_dv", "model.llm.layers.55.attn.wo_ud", "model.llm.layers.55.attn.wq_du", "model.llm.layers.55.attn.wr_du", "model.llm.layers.55.attn.wv_dv", "model.llm.layers.55.attn_sconv", "model.llm.layers.55.mlp.gate", "model.llm.layers.55.mlp_sconv", "model.llm.layers.56.attn.k_sconv", "model.llm.layers.56.attn.v_sconv", "model.llm.layers.56.attn.wk_dv", "model.llm.layers.56.attn.wo_ud", "model.llm.layers.56.attn.wq_du", "model.llm.layers.56.attn.wr_du", "model.llm.layers.56.attn.wv_dv", "model.llm.layers.56.attn_sconv", "model.llm.layers.56.mlp.gate", "model.llm.layers.56.mlp_sconv", "model.llm.layers.57.attn.k_sconv", "model.llm.layers.57.attn.v_sconv", "model.llm.layers.57.attn.wk_dv", "model.llm.layers.57.attn.wo_ud", "model.llm.layers.57.attn.wq_du", "model.llm.layers.57.attn.wr_du", "model.llm.layers.57.attn.wv_dv", "model.llm.layers.57.attn_sconv", "model.llm.layers.57.mlp.gate", "model.llm.layers.57.mlp_sconv", "model.llm.layers.58.attn.k_sconv", "model.llm.layers.58.attn.v_sconv", "model.llm.layers.58.attn.wk_dv", "model.llm.layers.58.attn.wo_ud", "model.llm.layers.58.attn.wq_du", "model.llm.layers.58.attn.wr_du", "model.llm.layers.58.attn.wv_dv", "model.llm.layers.58.attn_sconv", "model.llm.layers.58.mlp.gate", "model.llm.layers.58.mlp_sconv", "model.llm.layers.59.attn.k_sconv", "model.llm.layers.59.attn.v_sconv", "model.llm.layers.59.attn.wk_dv", "model.llm.layers.59.attn.wo_ud", "model.llm.layers.59.attn.wq_du", "model.llm.layers.59.attn.wr_du", "model.llm.layers.59.attn.wv_dv", "model.llm.layers.59.attn_sconv", "model.llm.layers.59.mlp.gate", "model.llm.layers.59.mlp_sconv", "model.llm.layers.6.attn.k_sconv", "model.llm.layers.6.attn.v_sconv", "model.llm.layers.6.attn.wk_dv", "model.llm.layers.6.attn.wo_ud", "model.llm.layers.6.attn.wq_du", "model.llm.layers.6.attn.wr_du", "model.llm.layers.6.attn.wv_dv", "model.llm.layers.6.attn_sconv", "model.llm.layers.6.mlp.gate", "model.llm.layers.6.mlp_sconv", "model.llm.layers.60.attn.k_sconv", "model.llm.layers.60.attn.v_sconv", "model.llm.layers.60.attn.wk_dv", "model.llm.layers.60.attn.wo_ud", "model.llm.layers.60.attn.wq_du", "model.llm.layers.60.attn.wr_du", "model.llm.layers.60.attn.wv_dv", "model.llm.layers.60.attn_sconv", "model.llm.layers.60.mlp.gate", "model.llm.layers.60.mlp_sconv", "model.llm.layers.61.attn.k_sconv", "model.llm.layers.61.attn.v_sconv", "model.llm.layers.61.attn.wk_dv", "model.llm.layers.61.attn.wo_ud", "model.llm.layers.61.attn.wq_du", "model.llm.layers.61.attn.wr_du", "model.llm.layers.61.attn.wv_dv", "model.llm.layers.61.attn_sconv", "model.llm.layers.61.mlp.gate", "model.llm.layers.61.mlp_sconv", "model.llm.layers.62.attn.k_sconv", "model.llm.layers.62.attn.v_sconv", "model.llm.layers.62.attn.wk_dv", "model.llm.layers.62.attn.wo_ud", "model.llm.layers.62.attn.wq_du", "model.llm.layers.62.attn.wr_du", "model.llm.layers.62.attn.wv_dv", "model.llm.layers.62.attn_sconv", "model.llm.layers.62.mlp.gate", "model.llm.layers.62.mlp_sconv", "model.llm.layers.63.attn.k_sconv", "model.llm.layers.63.attn.v_sconv", "model.llm.layers.63.attn.wk_dv", "model.llm.layers.63.attn.wo_ud", "model.llm.layers.63.attn.wq_du", "model.llm.layers.63.attn.wr_du", "model.llm.layers.63.attn.wv_dv", "model.llm.layers.63.attn_sconv", "model.llm.layers.63.mlp.gate", "model.llm.layers.63.mlp_sconv", "model.llm.layers.64.attn.k_sconv", "model.llm.layers.64.attn.v_sconv", "model.llm.layers.64.attn.wk_dv", "model.llm.layers.64.attn.wo_ud", "model.llm.layers.64.attn.wq_du", "model.llm.layers.64.attn.wr_du", "model.llm.layers.64.attn.wv_dv", "model.llm.layers.64.attn_sconv", "model.llm.layers.64.mlp.gate", "model.llm.layers.64.mlp_sconv", "model.llm.layers.65.attn.k_sconv", "model.llm.layers.65.attn.v_sconv", "model.llm.layers.65.attn.wk_dv", "model.llm.layers.65.attn.wo_ud", "model.llm.layers.65.attn.wq_du", "model.llm.layers.65.attn.wr_du", "model.llm.layers.65.attn.wv_dv", "model.llm.layers.65.attn_sconv", "model.llm.layers.65.mlp.gate", "model.llm.layers.65.mlp_sconv", "model.llm.layers.7.attn.k_sconv", "model.llm.layers.7.attn.v_sconv", "model.llm.layers.7.attn.wk_dv", "model.llm.layers.7.attn.wo_ud", "model.llm.layers.7.attn.wq_du", "model.llm.layers.7.attn.wr_du", "model.llm.layers.7.attn.wv_dv", "model.llm.layers.7.attn_sconv", "model.llm.layers.7.mlp.gate", "model.llm.layers.7.mlp_sconv", "model.llm.layers.8.attn.k_sconv", "model.llm.layers.8.attn.v_sconv", "model.llm.layers.8.attn.wk_dv", "model.llm.layers.8.attn.wo_ud", "model.llm.layers.8.attn.wq_du", "model.llm.layers.8.attn.wr_du", "model.llm.layers.8.attn.wv_dv", "model.llm.layers.8.attn_sconv", "model.llm.layers.8.mlp.gate", "model.llm.layers.8.mlp_sconv", "model.llm.layers.9.attn.k_sconv", "model.llm.layers.9.attn.v_sconv", "model.llm.layers.9.attn.wk_dv", "model.llm.layers.9.attn.wo_ud", "model.llm.layers.9.attn.wq_du", "model.llm.layers.9.attn.wr_du", "model.llm.layers.9.attn.wv_dv", "model.llm.layers.9.attn_sconv", "model.llm.layers.9.mlp.gate", "model.llm.layers.9.mlp_sconv", "model.mtp.layers.0.input_proj", "model.mtp.layers.0.transformer_block.attn.k_sconv", "model.mtp.layers.0.transformer_block.attn.v_sconv", "model.mtp.layers.0.transformer_block.attn.wk_dv", "model.mtp.layers.0.transformer_block.attn.wo_ud", "model.mtp.layers.0.transformer_block.attn.wq_du", "model.mtp.layers.0.transformer_block.attn.wr_du", "model.mtp.layers.0.transformer_block.attn.wv_dv", "model.mtp.layers.0.transformer_block.attn_sconv", "model.mtp.layers.0.transformer_block.mlp.w13_dn", "model.mtp.layers.0.transformer_block.mlp.w2_md", "model.mtp.layers.0.transformer_block.mlp_sconv", "model.mtp.layers.1.input_proj", "model.mtp.layers.1.transformer_block.attn.k_sconv", "model.mtp.layers.1.transformer_block.attn.v_sconv", "model.mtp.layers.1.transformer_block.attn.wk_dv", "model.mtp.layers.1.transformer_block.attn.wo_ud", "model.mtp.layers.1.transformer_block.attn.wq_du", "model.mtp.layers.1.transformer_block.attn.wr_du", "model.mtp.layers.1.transformer_block.attn.wv_dv", "model.mtp.layers.1.transformer_block.attn_sconv", "model.mtp.layers.1.transformer_block.mlp.w13_dn", "model.mtp.layers.1.transformer_block.mlp.w2_md", "model.mtp.layers.1.transformer_block.mlp_sconv", "model.mtp.layers.2.input_proj", "model.mtp.layers.2.transformer_block.attn.k_sconv", "model.mtp.layers.2.transformer_block.attn.v_sconv", "model.mtp.layers.2.transformer_block.attn.wk_dv", "model.mtp.layers.2.transformer_block.attn.wo_ud", "model.mtp.layers.2.transformer_block.attn.wq_du", "model.mtp.layers.2.transformer_block.attn.wr_du", "model.mtp.layers.2.transformer_block.attn.wv_dv", "model.mtp.layers.2.transformer_block.attn_sconv", "model.mtp.layers.2.transformer_block.mlp.w13_dn", "model.mtp.layers.2.transformer_block.mlp.w2_md", "model.mtp.layers.2.transformer_block.mlp_sconv", "model.mtp.layers.3.input_proj", "model.mtp.layers.3.transformer_block.attn.k_sconv", "model.mtp.layers.3.transformer_block.attn.v_sconv", "model.mtp.layers.3.transformer_block.attn.wk_dv", "model.mtp.layers.3.transformer_block.attn.wo_ud", "model.mtp.layers.3.transformer_block.attn.wq_du", "model.mtp.layers.3.transformer_block.attn.wr_du", "model.mtp.layers.3.transformer_block.attn.wv_dv", "model.mtp.layers.3.transformer_block.attn_sconv", "model.mtp.layers.3.transformer_block.mlp.w13_dn", "model.mtp.layers.3.transformer_block.mlp.w2_md", "model.mtp.layers.3.transformer_block.mlp_sconv", "model.mtp.layers.4.input_proj", "model.mtp.layers.4.transformer_block.attn.k_sconv", "model.mtp.layers.4.transformer_block.attn.v_sconv", "model.mtp.layers.4.transformer_block.attn.wk_dv", "model.mtp.layers.4.transformer_block.attn.wo_ud", "model.mtp.layers.4.transformer_block.attn.wq_du", "model.mtp.layers.4.transformer_block.attn.wr_du", "model.mtp.layers.4.transformer_block.attn.wv_dv", "model.mtp.layers.4.transformer_block.attn_sconv", "model.mtp.layers.4.transformer_block.mlp.w13_dn", "model.mtp.layers.4.transformer_block.mlp.w2_md", "model.mtp.layers.4.transformer_block.mlp_sconv", "model.mtp.layers.5.input_proj", "model.mtp.layers.5.transformer_block.attn.k_sconv", "model.mtp.layers.5.transformer_block.attn.v_sconv", "model.mtp.layers.5.transformer_block.attn.wk_dv", "model.mtp.layers.5.transformer_block.attn.wo_ud", "model.mtp.layers.5.transformer_block.attn.wq_du", "model.mtp.layers.5.transformer_block.attn.wr_du", "model.mtp.layers.5.transformer_block.attn.wv_dv", "model.mtp.layers.5.transformer_block.attn_sconv", "model.mtp.layers.5.transformer_block.mlp.w13_dn", "model.mtp.layers.5.transformer_block.mlp.w2_md", "model.mtp.layers.5.transformer_block.mlp_sconv", "model.mtp.layers.6.input_proj", "model.mtp.layers.6.transformer_block.attn.k_sconv", "model.mtp.layers.6.transformer_block.attn.v_sconv", "model.mtp.layers.6.transformer_block.attn.wk_dv", "model.mtp.layers.6.transformer_block.attn.wo_ud", "model.mtp.layers.6.transformer_block.attn.wq_du", "model.mtp.layers.6.transformer_block.attn.wr_du", "model.mtp.layers.6.transformer_block.attn.wv_dv", "model.mtp.layers.6.transformer_block.attn_sconv", "model.mtp.layers.6.transformer_block.mlp.w13_dn", "model.mtp.layers.6.transformer_block.mlp.w2_md", "model.mtp.layers.6.transformer_block.mlp_sconv", "model.mtp.layers.7.input_proj", "model.mtp.layers.7.transformer_block.attn.k_sconv", "model.mtp.layers.7.transformer_block.attn.v_sconv", "model.mtp.layers.7.transformer_block.attn.wk_dv", "model.mtp.layers.7.transformer_block.attn.wo_ud", "model.mtp.layers.7.transformer_block.attn.wq_du", "model.mtp.layers.7.transformer_block.attn.wr_du", "model.mtp.layers.7.transformer_block.attn.wv_dv", "model.mtp.layers.7.transformer_block.attn_sconv", "model.mtp.layers.7.transformer_block.mlp.w13_dn", "model.mtp.layers.7.transformer_block.mlp.w2_md", "model.mtp.layers.7.transformer_block.mlp_sconv", "model.visual.layers.linear_0", "model.visual.layers.linear_1", "model.visual.layers.linear_2", "model.visual.layers.linear_3" ], "algo_config": null, "softmax_quant_spec": null, "quant_method": "quark", "layer_type_quant_config": {}, "layer_quant_config": {}, "kv_cache_quant_config": {}, "kv_cache_post_rope": false, "quant_mode": "eager_mode", "version": "0.12.post1+rocm72.torch2.11", "export": { "kv_cache_group": [], "min_kv_scale": 0.0, "pack_method": "reorder", "weight_format": "real_quantized", "weight_merge_groups": null } } }