{ "architectures": [ "Llama4ForConditionalGeneration" ], "boi_token_index": 200080, "dtype": "float32", "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, "attn_scale": 0.1, "attn_temperature_tuning": true, "bos_token_id": 200000, "dtype": "float32", "eos_token_id": [ 200001, 200007, 200008 ], "floor_scale": 8192, "for_llm_compressor": false, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "interleave_moe_layer_step": 1, "intermediate_size": 3072, "intermediate_size_mlp": 6144, "layer_types": [ "chunked_attention", "chunked_attention", "chunked_attention", "full_attention", "chunked_attention", "chunked_attention", "chunked_attention", "full_attention" ], "max_position_embeddings": 10485760, "model_type": "llama4_text", "moe_layers": [ 0, 1, 2, 3, 4, 5, 6, 7 ], "no_rope_layer_interval": 4, "no_rope_layers": [ 1, 1, 1, 0, 1, 1, 1, 0 ], "num_attention_heads": 16, "num_experts_per_tok": 1, "num_hidden_layers": 8, "num_key_value_heads": 4, "num_local_experts": 4, "output_router_logits": false, "pad_token_id": 200018, "rms_norm_eps": 1e-05, "rope_parameters": { "factor": 16.0, "high_freq_factor": 1.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_theta": 500000.0, "rope_type": "llama3" }, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "tie_word_embeddings": false, "use_cache": true, "use_qk_norm": true, "vocab_size": 202048 }, "tie_word_embeddings": false, "transformers_version": "5.10.1", "use_cache": false, "vision_config": { "_attn_implementation_autoset": true, "attention_dropout": 0.0, "dtype": "float32", "hidden_act": "gelu", "hidden_size": 768, "image_size": 336, "initializer_range": 0.02, "intermediate_size": 3072, "model_type": "llama4_vision_model", "multi_modal_projector_bias": false, "norm_eps": 1e-05, "num_attention_heads": 12, "num_channels": 3, "num_hidden_layers": 6, "patch_size": 14, "pixel_shuffle_ratio": 0.5, "projector_dropout": 0.0, "projector_input_dim": 2048, "projector_output_dim": 2048, "rope_parameters": { "rope_theta": 10000, "rope_type": "default" }, "vision_feature_layer": -1, "vision_feature_select_strategy": "default", "vision_output_dim": 2048 } }