{ "architectures": [ "Phi4ForCausalLMV" ], "auto_map": { "AutoConfig": "modeling_phi4_visionr.Phi4VisionR", "AutoModelForCausalLM": "modeling_phi4_visionr.Phi4ForCausalLMV", "AutoProcessor": "processing_phi4_visionr.Phi4VisionRProcessor" }, "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 100257, "dtype": "bfloat16", "embd_pdrop": 0.0, "eos_token_id": 100265, "freeze_mm_mlp_adapter": false, "hidden_act": "silu", "hidden_size": 5120, "image_aspect_ratio": "square", "initializer_range": 0.02, "intermediate_size": 17920, "max_num_patches": 3600, "max_position_embeddings": 32768, "min_num_patches": 256, "mm_hidden_size": 1152, "mm_projector_lr": null, "mm_projector_type": "mlp2x_gelu", "mm_vision_tower": "google/siglip2-so400m-patch16-naflex", "model_type": "phi4-siglip", "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 10, "original_max_position_embeddings": 32768, "pad_token_id": 100349, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000, "sliding_window": null, "tie_word_embeddings": false, "tokenizer_model_max_length": 16384, "tokenizer_padding_side": "right", "transformers_version": "4.56.1", "tune_mm_mlp_adapter": false, "unfreeze_vision_tower": true, "use_cache": true, "use_mm_proj": true, "use_s2": false, "vocab_size": 100352, "vision_config": { "hidden_size": 1152, "intermediate_size": 4304, "model_type": "siglip2_vision_model", "num_attention_heads": 16, "num_hidden_layers": 27 } }