{ "architectures": [ "Qwen4ExpForConditionalGeneration" ], "image_token_id": 248056, "language_model_only": false, "model_type": "qwen4_exp", "text_config": { "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 248044, "dtype": "bfloat16", "eos_token_id": 248044, "full_attention_interval": 4, "hc_count": 4, "hc_lowrank": 4, "head_dim": 32, "heads_per_ngram": 8, "hidden_act": "silu", "hidden_size": 32, "indexer_budget": 2048, "indexer_compress_ratio": 4, "indexer_head_dim": 128, "indexer_kv_heads": 1, "indexer_n_heads": 4, "initializer_range": 0.02, "layer_types": [ "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention" ], "linear_conv_kernel_dim": 4, "linear_key_head_dim": 32, "linear_num_key_heads": 4, "linear_num_value_heads": 12, "linear_value_head_dim": 32, "make_ngram_vocab_size_divisible_by": 128, "mamba_ssm_dtype": "float32", "max_position_embeddings": 262144, "model_type": "qwen4_exp_text", "moe_intermediate_size": 128, "mtp": { "hybrid": true, "layer_types": [ "full_attention" ], "mtp_use_hidden_state_from_layer": null, "num_hidden_layers": 1, "rope_theta": 10000000 }, "mtp_num_hidden_layers": 1, "mtp_use_dedicated_embeddings": false, "ngram_size": 3, "ngram_vocab_size_base": 512, "num_attention_heads": 12, "num_experts": 32, "num_experts_per_tok": 10, "num_hidden_layers": 8, "num_key_value_heads": 1, "output_gate_type": "sigmoid", "output_router_logits": false, "pad_token_id": null, "partial_rotary_factor": 0.25, "ple_conv_kernel_size": 4, "ple_embed_dim": 16, "ple_layer_ids": [ 2 ], "rms_norm_eps": 1e-06, "rope_parameters": { "mrope_interleaved": true, "mrope_section": [ 2, 1, 1 ], "partial_rotary_factor": 0.25, "rope_theta": 10000000, "rope_type": "default" }, "router_aux_loss_coef": 0.001, "shared_expert_intermediate_size": 128, "split_ngram_parts": 128, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 248320 }, "tie_word_embeddings": false, "transformers_version": "5.8.0.dev0", "video_token_id": 248057, "vision_config": { "deepstack_visual_indexes": [], "depth": 2, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 64, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 128, "model_type": "qwen4_exp", "num_heads": 4, "num_position_embeddings": 2304, "out_hidden_size": 32, "patch_size": 16, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "vision_end_token_id": 248054, "vision_start_token_id": 248053, "quantization_config": { "quant_method": "fp8", "activation_scheme": "dynamic", "weight_per_tensor": false, "act_per_tensor": false, "weight_block_size": [ 32, 32 ], "modules_to_not_convert": [ "lm_head", "model.language_model.embed_tokens", "model.language_model.hyper_connection_mixer.input_mix_weight_down", "model.language_model.hyper_connection_mixer.input_mix_weight_up", "model.language_model.layers.0.attn_hyper_connection.block_inject_weight", "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_down", "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_up", "model.language_model.layers.0.linear_attn.conv1d", "model.language_model.layers.0.linear_attn.in_proj_a", "model.language_model.layers.0.linear_attn.in_proj_b", "model.language_model.layers.0.linear_attn.in_proj_qkv", "model.language_model.layers.0.linear_attn.in_proj_z", "model.language_model.layers.0.linear_attn.out_proj", "model.language_model.layers.0.mlp.gate", "model.language_model.layers.0.mlp.shared_expert.down_proj", "model.language_model.layers.0.mlp.shared_expert.gate_proj", "model.language_model.layers.0.mlp.shared_expert.up_proj", "model.language_model.layers.0.mlp.shared_expert_gate", "model.language_model.layers.0.mlp_hyper_connection.block_inject_weight", "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_down", "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_up", "model.language_model.layers.1.attn_hyper_connection.block_inject_weight", "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_down", "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_up", "model.language_model.layers.1.linear_attn.conv1d", "model.language_model.layers.1.linear_attn.in_proj_a", "model.language_model.layers.1.linear_attn.in_proj_b", "model.language_model.layers.1.linear_attn.in_proj_qkv", "model.language_model.layers.1.linear_attn.in_proj_z", "model.language_model.layers.1.linear_attn.out_proj", "model.language_model.layers.1.mlp.gate", "model.language_model.layers.1.mlp.shared_expert.down_proj", "model.language_model.layers.1.mlp.shared_expert.gate_proj", "model.language_model.layers.1.mlp.shared_expert.up_proj", "model.language_model.layers.1.mlp.shared_expert_gate", "model.language_model.layers.1.mlp_hyper_connection.block_inject_weight", "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_down", "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_up", "model.language_model.layers.1.ple.conv1d", "model.language_model.layers.1.ple.key_proj", "model.language_model.layers.1.ple.value_proj", "model.language_model.layers.2.attn_hyper_connection.block_inject_weight", "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_down", "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_up", "model.language_model.layers.2.linear_attn.conv1d", "model.language_model.layers.2.linear_attn.in_proj_a", "model.language_model.layers.2.linear_attn.in_proj_b", "model.language_model.layers.2.linear_attn.in_proj_qkv", "model.language_model.layers.2.linear_attn.in_proj_z", "model.language_model.layers.2.linear_attn.out_proj", "model.language_model.layers.2.mlp.gate", "model.language_model.layers.2.mlp.shared_expert.down_proj", "model.language_model.layers.2.mlp.shared_expert.gate_proj", "model.language_model.layers.2.mlp.shared_expert.up_proj", "model.language_model.layers.2.mlp.shared_expert_gate", "model.language_model.layers.2.mlp_hyper_connection.block_inject_weight", "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_down", "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_up", "model.language_model.layers.3.attn_hyper_connection.block_inject_weight", "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_down", "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_up", "model.language_model.layers.3.mlp.gate", "model.language_model.layers.3.mlp.shared_expert.down_proj", "model.language_model.layers.3.mlp.shared_expert.gate_proj", "model.language_model.layers.3.mlp.shared_expert.up_proj", "model.language_model.layers.3.mlp.shared_expert_gate", "model.language_model.layers.3.mlp_hyper_connection.block_inject_weight", "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_down", "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_up", "model.language_model.layers.3.self_attn.indexer.index_qk_proj", "model.language_model.layers.3.self_attn.k_proj", "model.language_model.layers.3.self_attn.o_proj", "model.language_model.layers.3.self_attn.q_proj", "model.language_model.layers.3.self_attn.v_proj", "model.language_model.layers.4.attn_hyper_connection.block_inject_weight", "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_down", "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_up", "model.language_model.layers.4.linear_attn.conv1d", "model.language_model.layers.4.linear_attn.in_proj_a", "model.language_model.layers.4.linear_attn.in_proj_b", "model.language_model.layers.4.linear_attn.in_proj_qkv", "model.language_model.layers.4.linear_attn.in_proj_z", "model.language_model.layers.4.linear_attn.out_proj", "model.language_model.layers.4.mlp.gate", "model.language_model.layers.4.mlp.shared_expert.down_proj", "model.language_model.layers.4.mlp.shared_expert.gate_proj", "model.language_model.layers.4.mlp.shared_expert.up_proj", "model.language_model.layers.4.mlp.shared_expert_gate", "model.language_model.layers.4.mlp_hyper_connection.block_inject_weight", "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_down", "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_up", "model.language_model.layers.5.attn_hyper_connection.block_inject_weight", "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_down", "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_up", "model.language_model.layers.5.linear_attn.conv1d", "model.language_model.layers.5.linear_attn.in_proj_a", "model.language_model.layers.5.linear_attn.in_proj_b", "model.language_model.layers.5.linear_attn.in_proj_qkv", "model.language_model.layers.5.linear_attn.in_proj_z", "model.language_model.layers.5.linear_attn.out_proj", "model.language_model.layers.5.mlp.gate", "model.language_model.layers.5.mlp.shared_expert.down_proj", "model.language_model.layers.5.mlp.shared_expert.gate_proj", "model.language_model.layers.5.mlp.shared_expert.up_proj", "model.language_model.layers.5.mlp.shared_expert_gate", "model.language_model.layers.5.mlp_hyper_connection.block_inject_weight", "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_down", "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_up", "model.language_model.layers.6.attn_hyper_connection.block_inject_weight", "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_down", "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_up", "model.language_model.layers.6.linear_attn.conv1d", "model.language_model.layers.6.linear_attn.in_proj_a", "model.language_model.layers.6.linear_attn.in_proj_b", "model.language_model.layers.6.linear_attn.in_proj_qkv", "model.language_model.layers.6.linear_attn.in_proj_z", "model.language_model.layers.6.linear_attn.out_proj", "model.language_model.layers.6.mlp.gate", "model.language_model.layers.6.mlp.shared_expert.down_proj", "model.language_model.layers.6.mlp.shared_expert.gate_proj", "model.language_model.layers.6.mlp.shared_expert.up_proj", "model.language_model.layers.6.mlp.shared_expert_gate", "model.language_model.layers.6.mlp_hyper_connection.block_inject_weight", "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_down", "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_up", "model.language_model.layers.7.attn_hyper_connection.block_inject_weight", "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_down", "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_up", "model.language_model.layers.7.mlp.gate", "model.language_model.layers.7.mlp.shared_expert.down_proj", "model.language_model.layers.7.mlp.shared_expert.gate_proj", "model.language_model.layers.7.mlp.shared_expert.up_proj", "model.language_model.layers.7.mlp.shared_expert_gate", "model.language_model.layers.7.mlp_hyper_connection.block_inject_weight", "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_down", "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_up", "model.language_model.layers.7.self_attn.indexer.index_qk_proj", "model.language_model.layers.7.self_attn.k_proj", "model.language_model.layers.7.self_attn.o_proj", "model.language_model.layers.7.self_attn.q_proj", "model.language_model.layers.7.self_attn.v_proj", "model.visual.blocks.0.attn.proj", "model.visual.blocks.0.attn.qkv", "model.visual.blocks.0.mlp.linear_fc1", "model.visual.blocks.0.mlp.linear_fc2", "model.visual.blocks.1.attn.proj", "model.visual.blocks.1.attn.qkv", "model.visual.blocks.1.mlp.linear_fc1", "model.visual.blocks.1.mlp.linear_fc2", "model.visual.merger.linear_fc1", "model.visual.merger.linear_fc2", "model.visual.patch_embed.proj", "model.visual.pos_embed", "mtp.fc_embedding", "mtp.fc_hidden", "mtp.hyper_connection_mixer.input_mix_weight_down", "mtp.hyper_connection_mixer.input_mix_weight_up", "mtp.layers.0.attn_hyper_connection.block_inject_weight", "mtp.layers.0.attn_hyper_connection.input_mix_weight_down", "mtp.layers.0.attn_hyper_connection.input_mix_weight_up", "mtp.layers.0.mlp.gate", "mtp.layers.0.mlp.shared_expert.down_proj", "mtp.layers.0.mlp.shared_expert.gate_proj", "mtp.layers.0.mlp.shared_expert.up_proj", "mtp.layers.0.mlp.shared_expert_gate", "mtp.layers.0.mlp_hyper_connection.block_inject_weight", "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down", "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up", "mtp.layers.0.self_attn.indexer.index_qk_proj", "mtp.layers.0.self_attn.k_proj", "mtp.layers.0.self_attn.o_proj", "mtp.layers.0.self_attn.q_proj", "mtp.layers.0.self_attn.v_proj" ], "modules_to_convert": [ "ple.ple_embedding.ngram_embedding" ] } }