{ "architectures": [ "Llama4ForConditionalGeneration" ], "boi_token_index": 200080, "eoi_token_index": 200081, "image_token_index": 200092, "model_type": "llama4", "text_config": { "_attn_implementation_autoset": true, "attention_bias": false, "attention_chunk_size": 8192, "attention_dropout": 0.0, "bos_token_id": 200000, "eos_token_id": [ 200001, 200007, 200008 ], "for_llm_compressor": true, "head_dim": 128, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "interleave_moe_layer_step": 1, "intermediate_size": 8192, "intermediate_size_mlp": 16384, "max_position_embeddings": 10485760, "model_type": "llama4_text", "no_rope_layers": [], "num_attention_heads": 40, "num_experts_per_tok": 1, "num_hidden_layers": 48, "num_key_value_heads": 8, "num_local_experts": 16, "output_router_logits": false, "pad_token_id": 200018, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 16.0, "high_freq_factor": 1.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "torch_dtype": "bfloat16", "use_cache": true, "use_qk_norm": true, "vocab_size": 202048 }, "torch_dtype": "bfloat16", "transformers_version": "4.51.0.dev0", "vision_config": { "_attn_implementation_autoset": true, "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 1408, "image_size": 336, "initializer_range": 0.02, "intermediate_size": 5632, "model_type": "llama4_vision_model", "multi_modal_projector_bias": false, "norm_eps": 1e-05, "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 34, "patch_size": 14, "pixel_shuffle_ratio": 0.5, "projector_dropout": 0.0, "projector_input_dim": 4096, "projector_output_dim": 4096, "rope_theta": 10000, "vision_feature_layer": -1, "vision_feature_select_strategy": "default", "vision_output_dim": 4096 }, "quantization_config": { "config_groups": { "group_0": { "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": null, "observer_kwargs": {}, "strategy": "token", "symmetric": true, "type": "float" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "mse", "observer_kwargs": {}, "strategy": "channel", "symmetric": true, "type": "float" } } }, "format": "float-quantized", "global_compression_ratio": null, "ignore": [ "vision_model.patch_embedding.linear", "vision_model.model.layers.0.self_attn.q_proj", "vision_model.model.layers.0.self_attn.k_proj", "vision_model.model.layers.0.self_attn.v_proj", "vision_model.model.layers.0.self_attn.o_proj", "vision_model.model.layers.0.mlp.fc1", "vision_model.model.layers.0.mlp.fc2", "vision_model.model.layers.1.self_attn.q_proj", "vision_model.model.layers.1.self_attn.k_proj", "vision_model.model.layers.1.self_attn.v_proj", "vision_model.model.layers.1.self_attn.o_proj", "vision_model.model.layers.1.mlp.fc1", "vision_model.model.layers.1.mlp.fc2", "vision_model.model.layers.2.self_attn.q_proj", "vision_model.model.layers.2.self_attn.k_proj", "vision_model.model.layers.2.self_attn.v_proj", "vision_model.model.layers.2.self_attn.o_proj", "vision_model.model.layers.2.mlp.fc1", "vision_model.model.layers.2.mlp.fc2", "vision_model.model.layers.3.self_attn.q_proj", "vision_model.model.layers.3.self_attn.k_proj", "vision_model.model.layers.3.self_attn.v_proj", "vision_model.model.layers.3.self_attn.o_proj", "vision_model.model.layers.3.mlp.fc1", "vision_model.model.layers.3.mlp.fc2", "vision_model.model.layers.4.self_attn.q_proj", "vision_model.model.layers.4.self_attn.k_proj", "vision_model.model.layers.4.self_attn.v_proj", "vision_model.model.layers.4.self_attn.o_proj", "vision_model.model.layers.4.mlp.fc1", "vision_model.model.layers.4.mlp.fc2", "vision_model.model.layers.5.self_attn.q_proj", "vision_model.model.layers.5.self_attn.k_proj", "vision_model.model.layers.5.self_attn.v_proj", "vision_model.model.layers.5.self_attn.o_proj", "vision_model.model.layers.5.mlp.fc1", "vision_model.model.layers.5.mlp.fc2", "vision_model.model.layers.6.self_attn.q_proj", "vision_model.model.layers.6.self_attn.k_proj", "vision_model.model.layers.6.self_attn.v_proj", "vision_model.model.layers.6.self_attn.o_proj", "vision_model.model.layers.6.mlp.fc1", "vision_model.model.layers.6.mlp.fc2", "vision_model.model.layers.7.self_attn.q_proj", "vision_model.model.layers.7.self_attn.k_proj", "vision_model.model.layers.7.self_attn.v_proj", "vision_model.model.layers.7.self_attn.o_proj", "vision_model.model.layers.7.mlp.fc1", "vision_model.model.layers.7.mlp.fc2", "vision_model.model.layers.8.self_attn.q_proj", "vision_model.model.layers.8.self_attn.k_proj", "vision_model.model.layers.8.self_attn.v_proj", "vision_model.model.layers.8.self_attn.o_proj", "vision_model.model.layers.8.mlp.fc1", "vision_model.model.layers.8.mlp.fc2", "vision_model.model.layers.9.self_attn.q_proj", "vision_model.model.layers.9.self_attn.k_proj", "vision_model.model.layers.9.self_attn.v_proj", "vision_model.model.layers.9.self_attn.o_proj", "vision_model.model.layers.9.mlp.fc1", "vision_model.model.layers.9.mlp.fc2", "vision_model.model.layers.10.self_attn.q_proj", "vision_model.model.layers.10.self_attn.k_proj", "vision_model.model.layers.10.self_attn.v_proj", "vision_model.model.layers.10.self_attn.o_proj", "vision_model.model.layers.10.mlp.fc1", "vision_model.model.layers.10.mlp.fc2", "vision_model.model.layers.11.self_attn.q_proj", "vision_model.model.layers.11.self_attn.k_proj", "vision_model.model.layers.11.self_attn.v_proj", "vision_model.model.layers.11.self_attn.o_proj", "vision_model.model.layers.11.mlp.fc1", "vision_model.model.layers.11.mlp.fc2", "vision_model.model.layers.12.self_attn.q_proj", "vision_model.model.layers.12.self_attn.k_proj", "vision_model.model.layers.12.self_attn.v_proj", "vision_model.model.layers.12.self_attn.o_proj", "vision_model.model.layers.12.mlp.fc1", "vision_model.model.layers.12.mlp.fc2", "vision_model.model.layers.13.self_attn.q_proj", "vision_model.model.layers.13.self_attn.k_proj", "vision_model.model.layers.13.self_attn.v_proj", "vision_model.model.layers.13.self_attn.o_proj", "vision_model.model.layers.13.mlp.fc1", "vision_model.model.layers.13.mlp.fc2", "vision_model.model.layers.14.self_attn.q_proj", "vision_model.model.layers.14.self_attn.k_proj", "vision_model.model.layers.14.self_attn.v_proj", "vision_model.model.layers.14.self_attn.o_proj", "vision_model.model.layers.14.mlp.fc1", "vision_model.model.layers.14.mlp.fc2", "vision_model.model.layers.15.self_attn.q_proj", "vision_model.model.layers.15.self_attn.k_proj", "vision_model.model.layers.15.self_attn.v_proj", "vision_model.model.layers.15.self_attn.o_proj", "vision_model.model.layers.15.mlp.fc1", "vision_model.model.layers.15.mlp.fc2", "vision_model.model.layers.16.self_attn.q_proj", "vision_model.model.layers.16.self_attn.k_proj", "vision_model.model.layers.16.self_attn.v_proj", "vision_model.model.layers.16.self_attn.o_proj", "vision_model.model.layers.16.mlp.fc1", "vision_model.model.layers.16.mlp.fc2", "vision_model.model.layers.17.self_attn.q_proj", "vision_model.model.layers.17.self_attn.k_proj", "vision_model.model.layers.17.self_attn.v_proj", "vision_model.model.layers.17.self_attn.o_proj", "vision_model.model.layers.17.mlp.fc1", "vision_model.model.layers.17.mlp.fc2", "vision_model.model.layers.18.self_attn.q_proj", "vision_model.model.layers.18.self_attn.k_proj", "vision_model.model.layers.18.self_attn.v_proj", "vision_model.model.layers.18.self_attn.o_proj", "vision_model.model.layers.18.mlp.fc1", "vision_model.model.layers.18.mlp.fc2", "vision_model.model.layers.19.self_attn.q_proj", "vision_model.model.layers.19.self_attn.k_proj", "vision_model.model.layers.19.self_attn.v_proj", "vision_model.model.layers.19.self_attn.o_proj", "vision_model.model.layers.19.mlp.fc1", "vision_model.model.layers.19.mlp.fc2", "vision_model.model.layers.20.self_attn.q_proj", "vision_model.model.layers.20.self_attn.k_proj", "vision_model.model.layers.20.self_attn.v_proj", "vision_model.model.layers.20.self_attn.o_proj", "vision_model.model.layers.20.mlp.fc1", "vision_model.model.layers.20.mlp.fc2", "vision_model.model.layers.21.self_attn.q_proj", "vision_model.model.layers.21.self_attn.k_proj", "vision_model.model.layers.21.self_attn.v_proj", "vision_model.model.layers.21.self_attn.o_proj", "vision_model.model.layers.21.mlp.fc1", "vision_model.model.layers.21.mlp.fc2", "vision_model.model.layers.22.self_attn.q_proj", "vision_model.model.layers.22.self_attn.k_proj", "vision_model.model.layers.22.self_attn.v_proj", "vision_model.model.layers.22.self_attn.o_proj", "vision_model.model.layers.22.mlp.fc1", "vision_model.model.layers.22.mlp.fc2", "vision_model.model.layers.23.self_attn.q_proj", "vision_model.model.layers.23.self_attn.k_proj", "vision_model.model.layers.23.self_attn.v_proj", "vision_model.model.layers.23.self_attn.o_proj", "vision_model.model.layers.23.mlp.fc1", "vision_model.model.layers.23.mlp.fc2", "vision_model.model.layers.24.self_attn.q_proj", "vision_model.model.layers.24.self_attn.k_proj", "vision_model.model.layers.24.self_attn.v_proj", "vision_model.model.layers.24.self_attn.o_proj", "vision_model.model.layers.24.mlp.fc1", "vision_model.model.layers.24.mlp.fc2", "vision_model.model.layers.25.self_attn.q_proj", "vision_model.model.layers.25.self_attn.k_proj", "vision_model.model.layers.25.self_attn.v_proj", "vision_model.model.layers.25.self_attn.o_proj", "vision_model.model.layers.25.mlp.fc1", "vision_model.model.layers.25.mlp.fc2", "vision_model.model.layers.26.self_attn.q_proj", "vision_model.model.layers.26.self_attn.k_proj", "vision_model.model.layers.26.self_attn.v_proj", "vision_model.model.layers.26.self_attn.o_proj", "vision_model.model.layers.26.mlp.fc1", "vision_model.model.layers.26.mlp.fc2", "vision_model.model.layers.27.self_attn.q_proj", "vision_model.model.layers.27.self_attn.k_proj", "vision_model.model.layers.27.self_attn.v_proj", "vision_model.model.layers.27.self_attn.o_proj", "vision_model.model.layers.27.mlp.fc1", "vision_model.model.layers.27.mlp.fc2", "vision_model.model.layers.28.self_attn.q_proj", "vision_model.model.layers.28.self_attn.k_proj", "vision_model.model.layers.28.self_attn.v_proj", "vision_model.model.layers.28.self_attn.o_proj", "vision_model.model.layers.28.mlp.fc1", "vision_model.model.layers.28.mlp.fc2", "vision_model.model.layers.29.self_attn.q_proj", "vision_model.model.layers.29.self_attn.k_proj", "vision_model.model.layers.29.self_attn.v_proj", "vision_model.model.layers.29.self_attn.o_proj", "vision_model.model.layers.29.mlp.fc1", "vision_model.model.layers.29.mlp.fc2", "vision_model.model.layers.30.self_attn.q_proj", "vision_model.model.layers.30.self_attn.k_proj", "vision_model.model.layers.30.self_attn.v_proj", "vision_model.model.layers.30.self_attn.o_proj", "vision_model.model.layers.30.mlp.fc1", "vision_model.model.layers.30.mlp.fc2", "vision_model.model.layers.31.self_attn.q_proj", "vision_model.model.layers.31.self_attn.k_proj", "vision_model.model.layers.31.self_attn.v_proj", "vision_model.model.layers.31.self_attn.o_proj", "vision_model.model.layers.31.mlp.fc1", "vision_model.model.layers.31.mlp.fc2", "vision_model.model.layers.32.self_attn.q_proj", "vision_model.model.layers.32.self_attn.k_proj", "vision_model.model.layers.32.self_attn.v_proj", "vision_model.model.layers.32.self_attn.o_proj", "vision_model.model.layers.32.mlp.fc1", "vision_model.model.layers.32.mlp.fc2", "vision_model.model.layers.33.self_attn.q_proj", "vision_model.model.layers.33.self_attn.k_proj", "vision_model.model.layers.33.self_attn.v_proj", "vision_model.model.layers.33.self_attn.o_proj", "vision_model.model.layers.33.mlp.fc1", "vision_model.model.layers.33.mlp.fc2", "vision_model.vision_adapter.mlp.fc1", "vision_model.vision_adapter.mlp.fc2", "multi_modal_projector.linear_1", "language_model.model.layers.0.self_attn.q_proj", "language_model.model.layers.0.self_attn.k_proj", "language_model.model.layers.0.self_attn.v_proj", "language_model.model.layers.0.self_attn.o_proj", "language_model.model.layers.0.feed_forward.router", "language_model.model.layers.0.feed_forward.shared_expert.gate_proj", "language_model.model.layers.0.feed_forward.shared_expert.up_proj", "language_model.model.layers.0.feed_forward.shared_expert.down_proj", "language_model.model.layers.1.self_attn.q_proj", "language_model.model.layers.1.self_attn.k_proj", "language_model.model.layers.1.self_attn.v_proj", "language_model.model.layers.1.self_attn.o_proj", "language_model.model.layers.1.feed_forward.router", "language_model.model.layers.1.feed_forward.shared_expert.gate_proj", "language_model.model.layers.1.feed_forward.shared_expert.up_proj", "language_model.model.layers.1.feed_forward.shared_expert.down_proj", "language_model.model.layers.2.self_attn.q_proj", "language_model.model.layers.2.self_attn.k_proj", "language_model.model.layers.2.self_attn.v_proj", "language_model.model.layers.2.self_attn.o_proj", "language_model.model.layers.2.feed_forward.router", "language_model.model.layers.2.feed_forward.shared_expert.gate_proj", "language_model.model.layers.2.feed_forward.shared_expert.up_proj", "language_model.model.layers.2.feed_forward.shared_expert.down_proj", "language_model.model.layers.3.self_attn.q_proj", "language_model.model.layers.3.self_attn.k_proj", "language_model.model.layers.3.self_attn.v_proj", "language_model.model.layers.3.self_attn.o_proj", "language_model.model.layers.3.feed_forward.router", "language_model.model.layers.3.feed_forward.shared_expert.gate_proj", "language_model.model.layers.3.feed_forward.shared_expert.up_proj", "language_model.model.layers.3.feed_forward.shared_expert.down_proj", "language_model.model.layers.4.self_attn.q_proj", "language_model.model.layers.4.self_attn.k_proj", "language_model.model.layers.4.self_attn.v_proj", "language_model.model.layers.4.self_attn.o_proj", "language_model.model.layers.4.feed_forward.router", "language_model.model.layers.4.feed_forward.shared_expert.gate_proj", "language_model.model.layers.4.feed_forward.shared_expert.up_proj", "language_model.model.layers.4.feed_forward.shared_expert.down_proj", "language_model.model.layers.5.self_attn.q_proj", "language_model.model.layers.5.self_attn.k_proj", "language_model.model.layers.5.self_attn.v_proj", "language_model.model.layers.5.self_attn.o_proj", "language_model.model.layers.5.feed_forward.router", "language_model.model.layers.5.feed_forward.shared_expert.gate_proj", "language_model.model.layers.5.feed_forward.shared_expert.up_proj", "language_model.model.layers.5.feed_forward.shared_expert.down_proj", "language_model.model.layers.6.self_attn.q_proj", "language_model.model.layers.6.self_attn.k_proj", "language_model.model.layers.6.self_attn.v_proj", "language_model.model.layers.6.self_attn.o_proj", "language_model.model.layers.6.feed_forward.router", "language_model.model.layers.6.feed_forward.shared_expert.gate_proj", "language_model.model.layers.6.feed_forward.shared_expert.up_proj", "language_model.model.layers.6.feed_forward.shared_expert.down_proj", "language_model.model.layers.7.self_attn.q_proj", "language_model.model.layers.7.self_attn.k_proj", "language_model.model.layers.7.self_attn.v_proj", "language_model.model.layers.7.self_attn.o_proj", "language_model.model.layers.7.feed_forward.router", "language_model.model.layers.7.feed_forward.shared_expert.gate_proj", "language_model.model.layers.7.feed_forward.shared_expert.up_proj", "language_model.model.layers.7.feed_forward.shared_expert.down_proj", "language_model.model.layers.8.self_attn.q_proj", "language_model.model.layers.8.self_attn.k_proj", "language_model.model.layers.8.self_attn.v_proj", "language_model.model.layers.8.self_attn.o_proj", "language_model.model.layers.8.feed_forward.router", "language_model.model.layers.8.feed_forward.shared_expert.gate_proj", "language_model.model.layers.8.feed_forward.shared_expert.up_proj", "language_model.model.layers.8.feed_forward.shared_expert.down_proj", "language_model.model.layers.9.self_attn.q_proj", "language_model.model.layers.9.self_attn.k_proj", "language_model.model.layers.9.self_attn.v_proj", "language_model.model.layers.9.self_attn.o_proj", "language_model.model.layers.9.feed_forward.router", "language_model.model.layers.9.feed_forward.shared_expert.gate_proj", "language_model.model.layers.9.feed_forward.shared_expert.up_proj", "language_model.model.layers.9.feed_forward.shared_expert.down_proj", "language_model.model.layers.10.self_attn.q_proj", "language_model.model.layers.10.self_attn.k_proj", "language_model.model.layers.10.self_attn.v_proj", "language_model.model.layers.10.self_attn.o_proj", "language_model.model.layers.10.feed_forward.router", "language_model.model.layers.10.feed_forward.shared_expert.gate_proj", "language_model.model.layers.10.feed_forward.shared_expert.up_proj", "language_model.model.layers.10.feed_forward.shared_expert.down_proj", "language_model.model.layers.11.self_attn.q_proj", "language_model.model.layers.11.self_attn.k_proj", "language_model.model.layers.11.self_attn.v_proj", "language_model.model.layers.11.self_attn.o_proj", "language_model.model.layers.11.feed_forward.router", "language_model.model.layers.11.feed_forward.shared_expert.gate_proj", "language_model.model.layers.11.feed_forward.shared_expert.up_proj", "language_model.model.layers.11.feed_forward.shared_expert.down_proj", "language_model.model.layers.12.self_attn.q_proj", "language_model.model.layers.12.self_attn.k_proj", "language_model.model.layers.12.self_attn.v_proj", "language_model.model.layers.12.self_attn.o_proj", "language_model.model.layers.12.feed_forward.router", "language_model.model.layers.12.feed_forward.shared_expert.gate_proj", "language_model.model.layers.12.feed_forward.shared_expert.up_proj", "language_model.model.layers.12.feed_forward.shared_expert.down_proj", "language_model.model.layers.13.self_attn.q_proj", "language_model.model.layers.13.self_attn.k_proj", "language_model.model.layers.13.self_attn.v_proj", "language_model.model.layers.13.self_attn.o_proj", "language_model.model.layers.13.feed_forward.router", "language_model.model.layers.13.feed_forward.shared_expert.gate_proj", "language_model.model.layers.13.feed_forward.shared_expert.up_proj", "language_model.model.layers.13.feed_forward.shared_expert.down_proj", "language_model.model.layers.14.self_attn.q_proj", "language_model.model.layers.14.self_attn.k_proj", "language_model.model.layers.14.self_attn.v_proj", "language_model.model.layers.14.self_attn.o_proj", "language_model.model.layers.14.feed_forward.router", "language_model.model.layers.14.feed_forward.shared_expert.gate_proj", "language_model.model.layers.14.feed_forward.shared_expert.up_proj", "language_model.model.layers.14.feed_forward.shared_expert.down_proj", "language_model.model.layers.15.self_attn.q_proj", "language_model.model.layers.15.self_attn.k_proj", "language_model.model.layers.15.self_attn.v_proj", "language_model.model.layers.15.self_attn.o_proj", "language_model.model.layers.15.feed_forward.router", "language_model.model.layers.15.feed_forward.shared_expert.gate_proj", "language_model.model.layers.15.feed_forward.shared_expert.up_proj", "language_model.model.layers.15.feed_forward.shared_expert.down_proj", "language_model.model.layers.16.self_attn.q_proj", "language_model.model.layers.16.self_attn.k_proj", "language_model.model.layers.16.self_attn.v_proj", "language_model.model.layers.16.self_attn.o_proj", "language_model.model.layers.16.feed_forward.router", "language_model.model.layers.16.feed_forward.shared_expert.gate_proj", "language_model.model.layers.16.feed_forward.shared_expert.up_proj", "language_model.model.layers.16.feed_forward.shared_expert.down_proj", "language_model.model.layers.17.self_attn.q_proj", "language_model.model.layers.17.self_attn.k_proj", "language_model.model.layers.17.self_attn.v_proj", "language_model.model.layers.17.self_attn.o_proj", "language_model.model.layers.17.feed_forward.router", "language_model.model.layers.17.feed_forward.shared_expert.gate_proj", "language_model.model.layers.17.feed_forward.shared_expert.up_proj", "language_model.model.layers.17.feed_forward.shared_expert.down_proj", "language_model.model.layers.18.self_attn.q_proj", "language_model.model.layers.18.self_attn.k_proj", "language_model.model.layers.18.self_attn.v_proj", "language_model.model.layers.18.self_attn.o_proj", "language_model.model.layers.18.feed_forward.router", "language_model.model.layers.18.feed_forward.shared_expert.gate_proj", "language_model.model.layers.18.feed_forward.shared_expert.up_proj", "language_model.model.layers.18.feed_forward.shared_expert.down_proj", "language_model.model.layers.19.self_attn.q_proj", "language_model.model.layers.19.self_attn.k_proj", "language_model.model.layers.19.self_attn.v_proj", "language_model.model.layers.19.self_attn.o_proj", "language_model.model.layers.19.feed_forward.router", "language_model.model.layers.19.feed_forward.shared_expert.gate_proj", "language_model.model.layers.19.feed_forward.shared_expert.up_proj", "language_model.model.layers.19.feed_forward.shared_expert.down_proj", "language_model.model.layers.20.self_attn.q_proj", "language_model.model.layers.20.self_attn.k_proj", "language_model.model.layers.20.self_attn.v_proj", "language_model.model.layers.20.self_attn.o_proj", "language_model.model.layers.20.feed_forward.router", "language_model.model.layers.20.feed_forward.shared_expert.gate_proj", "language_model.model.layers.20.feed_forward.shared_expert.up_proj", "language_model.model.layers.20.feed_forward.shared_expert.down_proj", "language_model.model.layers.21.self_attn.q_proj", "language_model.model.layers.21.self_attn.k_proj", "language_model.model.layers.21.self_attn.v_proj", "language_model.model.layers.21.self_attn.o_proj", "language_model.model.layers.21.feed_forward.router", "language_model.model.layers.21.feed_forward.shared_expert.gate_proj", "language_model.model.layers.21.feed_forward.shared_expert.up_proj", "language_model.model.layers.21.feed_forward.shared_expert.down_proj", "language_model.model.layers.22.self_attn.q_proj", "language_model.model.layers.22.self_attn.k_proj", "language_model.model.layers.22.self_attn.v_proj", "language_model.model.layers.22.self_attn.o_proj", "language_model.model.layers.22.feed_forward.router", "language_model.model.layers.22.feed_forward.shared_expert.gate_proj", "language_model.model.layers.22.feed_forward.shared_expert.up_proj", "language_model.model.layers.22.feed_forward.shared_expert.down_proj", "language_model.model.layers.23.self_attn.q_proj", "language_model.model.layers.23.self_attn.k_proj", "language_model.model.layers.23.self_attn.v_proj", "language_model.model.layers.23.self_attn.o_proj", "language_model.model.layers.23.feed_forward.router", "language_model.model.layers.23.feed_forward.shared_expert.gate_proj", "language_model.model.layers.23.feed_forward.shared_expert.up_proj", "language_model.model.layers.23.feed_forward.shared_expert.down_proj", "language_model.model.layers.24.self_attn.q_proj", "language_model.model.layers.24.self_attn.k_proj", "language_model.model.layers.24.self_attn.v_proj", "language_model.model.layers.24.self_attn.o_proj", "language_model.model.layers.24.feed_forward.router", "language_model.model.layers.24.feed_forward.shared_expert.gate_proj", "language_model.model.layers.24.feed_forward.shared_expert.up_proj", "language_model.model.layers.24.feed_forward.shared_expert.down_proj", "language_model.model.layers.25.self_attn.q_proj", "language_model.model.layers.25.self_attn.k_proj", "language_model.model.layers.25.self_attn.v_proj", "language_model.model.layers.25.self_attn.o_proj", "language_model.model.layers.25.feed_forward.router", "language_model.model.layers.25.feed_forward.shared_expert.gate_proj", "language_model.model.layers.25.feed_forward.shared_expert.up_proj", "language_model.model.layers.25.feed_forward.shared_expert.down_proj", "language_model.model.layers.26.self_attn.q_proj", "language_model.model.layers.26.self_attn.k_proj", "language_model.model.layers.26.self_attn.v_proj", "language_model.model.layers.26.self_attn.o_proj", "language_model.model.layers.26.feed_forward.router", "language_model.model.layers.26.feed_forward.shared_expert.gate_proj", "language_model.model.layers.26.feed_forward.shared_expert.up_proj", "language_model.model.layers.26.feed_forward.shared_expert.down_proj", "language_model.model.layers.27.self_attn.q_proj", "language_model.model.layers.27.self_attn.k_proj", "language_model.model.layers.27.self_attn.v_proj", "language_model.model.layers.27.self_attn.o_proj", "language_model.model.layers.27.feed_forward.router", "language_model.model.layers.27.feed_forward.shared_expert.gate_proj", "language_model.model.layers.27.feed_forward.shared_expert.up_proj", "language_model.model.layers.27.feed_forward.shared_expert.down_proj", "language_model.model.layers.28.self_attn.q_proj", "language_model.model.layers.28.self_attn.k_proj", "language_model.model.layers.28.self_attn.v_proj", "language_model.model.layers.28.self_attn.o_proj", "language_model.model.layers.28.feed_forward.router", "language_model.model.layers.28.feed_forward.shared_expert.gate_proj", "language_model.model.layers.28.feed_forward.shared_expert.up_proj", "language_model.model.layers.28.feed_forward.shared_expert.down_proj", "language_model.model.layers.29.self_attn.q_proj", "language_model.model.layers.29.self_attn.k_proj", "language_model.model.layers.29.self_attn.v_proj", "language_model.model.layers.29.self_attn.o_proj", "language_model.model.layers.29.feed_forward.router", "language_model.model.layers.29.feed_forward.shared_expert.gate_proj", "language_model.model.layers.29.feed_forward.shared_expert.up_proj", "language_model.model.layers.29.feed_forward.shared_expert.down_proj", "language_model.model.layers.30.self_attn.q_proj", "language_model.model.layers.30.self_attn.k_proj", "language_model.model.layers.30.self_attn.v_proj", "language_model.model.layers.30.self_attn.o_proj", "language_model.model.layers.30.feed_forward.router", "language_model.model.layers.30.feed_forward.shared_expert.gate_proj", "language_model.model.layers.30.feed_forward.shared_expert.up_proj", "language_model.model.layers.30.feed_forward.shared_expert.down_proj", "language_model.model.layers.31.self_attn.q_proj", "language_model.model.layers.31.self_attn.k_proj", "language_model.model.layers.31.self_attn.v_proj", "language_model.model.layers.31.self_attn.o_proj", "language_model.model.layers.31.feed_forward.router", "language_model.model.layers.31.feed_forward.shared_expert.gate_proj", "language_model.model.layers.31.feed_forward.shared_expert.up_proj", "language_model.model.layers.31.feed_forward.shared_expert.down_proj", "language_model.model.layers.32.self_attn.q_proj", "language_model.model.layers.32.self_attn.k_proj", "language_model.model.layers.32.self_attn.v_proj", "language_model.model.layers.32.self_attn.o_proj", "language_model.model.layers.32.feed_forward.router", "language_model.model.layers.32.feed_forward.shared_expert.gate_proj", "language_model.model.layers.32.feed_forward.shared_expert.up_proj", "language_model.model.layers.32.feed_forward.shared_expert.down_proj", "language_model.model.layers.33.self_attn.q_proj", "language_model.model.layers.33.self_attn.k_proj", "language_model.model.layers.33.self_attn.v_proj", "language_model.model.layers.33.self_attn.o_proj", "language_model.model.layers.33.feed_forward.router", "language_model.model.layers.33.feed_forward.shared_expert.gate_proj", "language_model.model.layers.33.feed_forward.shared_expert.up_proj", "language_model.model.layers.33.feed_forward.shared_expert.down_proj", "language_model.model.layers.34.self_attn.q_proj", "language_model.model.layers.34.self_attn.k_proj", "language_model.model.layers.34.self_attn.v_proj", "language_model.model.layers.34.self_attn.o_proj", "language_model.model.layers.34.feed_forward.router", "language_model.model.layers.34.feed_forward.shared_expert.gate_proj", "language_model.model.layers.34.feed_forward.shared_expert.up_proj", "language_model.model.layers.34.feed_forward.shared_expert.down_proj", "language_model.model.layers.35.self_attn.q_proj", "language_model.model.layers.35.self_attn.k_proj", "language_model.model.layers.35.self_attn.v_proj", "language_model.model.layers.35.self_attn.o_proj", "language_model.model.layers.35.feed_forward.router", "language_model.model.layers.35.feed_forward.shared_expert.gate_proj", "language_model.model.layers.35.feed_forward.shared_expert.up_proj", "language_model.model.layers.35.feed_forward.shared_expert.down_proj", "language_model.model.layers.36.self_attn.q_proj", "language_model.model.layers.36.self_attn.k_proj", "language_model.model.layers.36.self_attn.v_proj", "language_model.model.layers.36.self_attn.o_proj", "language_model.model.layers.36.feed_forward.router", "language_model.model.layers.36.feed_forward.shared_expert.gate_proj", "language_model.model.layers.36.feed_forward.shared_expert.up_proj", "language_model.model.layers.36.feed_forward.shared_expert.down_proj", "language_model.model.layers.37.self_attn.q_proj", "language_model.model.layers.37.self_attn.k_proj", "language_model.model.layers.37.self_attn.v_proj", "language_model.model.layers.37.self_attn.o_proj", "language_model.model.layers.37.feed_forward.router", "language_model.model.layers.37.feed_forward.shared_expert.gate_proj", "language_model.model.layers.37.feed_forward.shared_expert.up_proj", "language_model.model.layers.37.feed_forward.shared_expert.down_proj", "language_model.model.layers.38.self_attn.q_proj", "language_model.model.layers.38.self_attn.k_proj", "language_model.model.layers.38.self_attn.v_proj", "language_model.model.layers.38.self_attn.o_proj", "language_model.model.layers.38.feed_forward.router", "language_model.model.layers.38.feed_forward.shared_expert.gate_proj", "language_model.model.layers.38.feed_forward.shared_expert.up_proj", "language_model.model.layers.38.feed_forward.shared_expert.down_proj", "language_model.model.layers.39.self_attn.q_proj", "language_model.model.layers.39.self_attn.k_proj", "language_model.model.layers.39.self_attn.v_proj", "language_model.model.layers.39.self_attn.o_proj", "language_model.model.layers.39.feed_forward.router", "language_model.model.layers.39.feed_forward.shared_expert.gate_proj", "language_model.model.layers.39.feed_forward.shared_expert.up_proj", "language_model.model.layers.39.feed_forward.shared_expert.down_proj", "language_model.model.layers.40.self_attn.q_proj", "language_model.model.layers.40.self_attn.k_proj", "language_model.model.layers.40.self_attn.v_proj", "language_model.model.layers.40.self_attn.o_proj", "language_model.model.layers.40.feed_forward.router", "language_model.model.layers.40.feed_forward.shared_expert.gate_proj", "language_model.model.layers.40.feed_forward.shared_expert.up_proj", "language_model.model.layers.40.feed_forward.shared_expert.down_proj", "language_model.model.layers.41.self_attn.q_proj", "language_model.model.layers.41.self_attn.k_proj", "language_model.model.layers.41.self_attn.v_proj", "language_model.model.layers.41.self_attn.o_proj", "language_model.model.layers.41.feed_forward.router", "language_model.model.layers.41.feed_forward.shared_expert.gate_proj", "language_model.model.layers.41.feed_forward.shared_expert.up_proj", "language_model.model.layers.41.feed_forward.shared_expert.down_proj", "language_model.model.layers.42.self_attn.q_proj", "language_model.model.layers.42.self_attn.k_proj", "language_model.model.layers.42.self_attn.v_proj", "language_model.model.layers.42.self_attn.o_proj", "language_model.model.layers.42.feed_forward.router", "language_model.model.layers.42.feed_forward.shared_expert.gate_proj", "language_model.model.layers.42.feed_forward.shared_expert.up_proj", "language_model.model.layers.42.feed_forward.shared_expert.down_proj", "language_model.model.layers.43.self_attn.q_proj", "language_model.model.layers.43.self_attn.k_proj", "language_model.model.layers.43.self_attn.v_proj", "language_model.model.layers.43.self_attn.o_proj", "language_model.model.layers.43.feed_forward.router", "language_model.model.layers.43.feed_forward.shared_expert.gate_proj", "language_model.model.layers.43.feed_forward.shared_expert.up_proj", "language_model.model.layers.43.feed_forward.shared_expert.down_proj", "language_model.model.layers.44.self_attn.q_proj", "language_model.model.layers.44.self_attn.k_proj", "language_model.model.layers.44.self_attn.v_proj", "language_model.model.layers.44.self_attn.o_proj", "language_model.model.layers.44.feed_forward.router", "language_model.model.layers.44.feed_forward.shared_expert.gate_proj", "language_model.model.layers.44.feed_forward.shared_expert.up_proj", "language_model.model.layers.44.feed_forward.shared_expert.down_proj", "language_model.model.layers.45.self_attn.q_proj", "language_model.model.layers.45.self_attn.k_proj", "language_model.model.layers.45.self_attn.v_proj", "language_model.model.layers.45.self_attn.o_proj", "language_model.model.layers.45.feed_forward.router", "language_model.model.layers.45.feed_forward.shared_expert.gate_proj", "language_model.model.layers.45.feed_forward.shared_expert.up_proj", "language_model.model.layers.45.feed_forward.shared_expert.down_proj", "language_model.model.layers.46.self_attn.q_proj", "language_model.model.layers.46.self_attn.k_proj", "language_model.model.layers.46.self_attn.v_proj", "language_model.model.layers.46.self_attn.o_proj", "language_model.model.layers.46.feed_forward.router", "language_model.model.layers.46.feed_forward.shared_expert.gate_proj", "language_model.model.layers.46.feed_forward.shared_expert.up_proj", "language_model.model.layers.46.feed_forward.shared_expert.down_proj", "language_model.model.layers.47.self_attn.q_proj", "language_model.model.layers.47.self_attn.k_proj", "language_model.model.layers.47.self_attn.v_proj", "language_model.model.layers.47.self_attn.o_proj", "language_model.model.layers.47.feed_forward.router", "language_model.model.layers.47.feed_forward.shared_expert.gate_proj", "language_model.model.layers.47.feed_forward.shared_expert.up_proj", "language_model.model.layers.47.feed_forward.shared_expert.down_proj", "language_model.lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed" } }