{ "architectures": [ "Qwen3_5ForConditionalGeneration" ], "image_token_id": 248056, "language_model_only": false, "model_type": "qwen3_5", "text_config": { "attention_bias": false, "attention_dropout": 0.0, "attn_output_gate": true, "bos_token_id": 248044, "dtype": "bfloat16", "eos_token_id": 248044, "full_attention_interval": 4, "head_dim": 128, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 512, "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": 128, "linear_num_key_heads": 2, "linear_num_value_heads": 6, "linear_value_head_dim": 128, "mamba_ssm_dtype": "float32", "max_position_embeddings": 262144, "model_type": "qwen3_5_text", "mtp_num_hidden_layers": 1, "mtp_use_dedicated_embeddings": false, "num_attention_heads": 12, "num_hidden_layers": 8, "num_key_value_heads": 2, "output_gate_type": "swish", "pad_token_id": null, "partial_rotary_factor": 0.25, "rms_norm_eps": 1e-06, "rope_parameters": { "mrope_interleaved": true, "mrope_section": [ 6, 5, 5 ], "partial_rotary_factor": 0.25, "rope_theta": 10000000, "rope_type": "default" }, "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": "qwen3_5", "num_heads": 2, "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": { "activation_scheme": "dynamic", "fmt": "e4m3", "quant_method": "fp8", "modules_to_not_convert": [ "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.merger.norm", "model.visual.patch_embed.proj", "model.visual.pos_embed", "model.visual", "lm_head", "model.language_model.layers.0.input_layernorm", "model.language_model.layers.0.post_attention_layernorm", "model.language_model.layers.0.linear_attn.A_log", "model.language_model.layers.0.linear_attn.conv1d", "model.language_model.layers.0.linear_attn.dt_bias", "model.language_model.layers.0.linear_attn.in_proj_b", "model.language_model.layers.0.linear_attn.in_proj_a", "model.language_model.layers.0.linear_attn.norm", "model.language_model.layers.1.input_layernorm", "model.language_model.layers.1.post_attention_layernorm", "model.language_model.layers.1.linear_attn.A_log", "model.language_model.layers.1.linear_attn.conv1d", "model.language_model.layers.1.linear_attn.dt_bias", "model.language_model.layers.1.linear_attn.in_proj_b", "model.language_model.layers.1.linear_attn.in_proj_a", "model.language_model.layers.1.linear_attn.norm", "model.language_model.layers.2.input_layernorm", "model.language_model.layers.2.post_attention_layernorm", "model.language_model.layers.2.linear_attn.A_log", "model.language_model.layers.2.linear_attn.conv1d", "model.language_model.layers.2.linear_attn.dt_bias", "model.language_model.layers.2.linear_attn.in_proj_b", "model.language_model.layers.2.linear_attn.in_proj_a", "model.language_model.layers.2.linear_attn.norm", "model.language_model.layers.3.input_layernorm", "model.language_model.layers.3.post_attention_layernorm", "model.language_model.layers.3.self_attn.k_norm", "model.language_model.layers.3.self_attn.q_norm", "model.language_model.layers.4.input_layernorm", "model.language_model.layers.4.post_attention_layernorm", "model.language_model.layers.4.linear_attn.A_log", "model.language_model.layers.4.linear_attn.conv1d", "model.language_model.layers.4.linear_attn.dt_bias", "model.language_model.layers.4.linear_attn.in_proj_b", "model.language_model.layers.4.linear_attn.in_proj_a", "model.language_model.layers.4.linear_attn.norm", "model.language_model.layers.5.input_layernorm", "model.language_model.layers.5.post_attention_layernorm", "model.language_model.layers.5.linear_attn.A_log", "model.language_model.layers.5.linear_attn.conv1d", "model.language_model.layers.5.linear_attn.dt_bias", "model.language_model.layers.5.linear_attn.in_proj_b", "model.language_model.layers.5.linear_attn.in_proj_a", "model.language_model.layers.5.linear_attn.norm", "model.language_model.layers.6.input_layernorm", "model.language_model.layers.6.post_attention_layernorm", "model.language_model.layers.6.linear_attn.A_log", "model.language_model.layers.6.linear_attn.conv1d", "model.language_model.layers.6.linear_attn.dt_bias", "model.language_model.layers.6.linear_attn.in_proj_b", "model.language_model.layers.6.linear_attn.in_proj_a", "model.language_model.layers.6.linear_attn.norm", "model.language_model.layers.7.input_layernorm", "model.language_model.layers.7.post_attention_layernorm", "model.language_model.layers.7.self_attn.k_norm", "model.language_model.layers.7.self_attn.q_norm", "mtp.layers.0.input_layernorm", "mtp.layers.0.post_attention_layernorm", "mtp.layers.0.self_attn.k_norm", "mtp.layers.0.self_attn.q_norm", "mtp.fc", "mtp.norm", "mtp.pre_fc_norm_embedding", "mtp.pre_fc_norm_hidden" ], "weight_block_size": [ 32, 32 ] } }