{ "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, "attn_scale": 0.1, "attn_temperature_tuning": 4, "bos_token_id": 200000, "eos_token_id": [ 200001, 200007, 200008 ], "floor_scale": 8192, "for_llm_compressor": false, "head_dim": 32, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "interleave_moe_layer_step": 2, "intermediate_size": 64, "intermediate_size_mlp": 128, "max_position_embeddings": 1048576, "model_type": "llama4_text", "moe_layers": [ 1, 3 ], "no_rope_layers": [ 1, 1, 1, 0 ], "num_attention_heads": 1, "num_experts_per_tok": 1, "num_hidden_layers": 4, "num_key_value_heads": 1, "num_local_experts": 8, "output_router_logits": false, "pad_token_id": 200018, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_qk_norm": true, "vocab_size": 202048 }, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.51.0", "vision_config": { "_attn_implementation_autoset": true, "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "image_size": 336, "initializer_range": 0.02, "intermediate_size": 128, "model_type": "llama4_vision_model", "multi_modal_projector_bias": false, "norm_eps": 1e-05, "num_attention_heads": 1, "num_channels": 3, "num_hidden_layers": 2, "patch_size": 14, "pixel_shuffle_ratio": 0.5, "projector_dropout": 0.0, "projector_input_dim": 32, "projector_output_dim": 32, "rope_theta": 10000, "vision_feature_layer": -1, "vision_feature_select_strategy": "default", "vision_output_dim": 32 } }