{ "model": { "bos_token_id": 199999, "context_length": 131072, "decoder": { "session_options": { "log_id": "onnxruntime-genai", "provider_options": [] }, "filename": "phi-4-mm-text.onnx", "head_size": 128, "hidden_size": 3072, "inputs": { "inputs_embeds": "inputs_embeds", "attention_mask": "attention_mask", "past_key_names": "past_key_values.%d.key", "past_value_names": "past_key_values.%d.value" }, "outputs": { "logits": "logits", "present_key_names": "present.%d.key", "present_value_names": "present.%d.value" }, "num_attention_heads": 24, "num_hidden_layers": 32, "num_key_value_heads": 8 }, "vision": { "filename": "phi-4-mm-vision.onnx", "config_filename": "vision_processor.json", "adapter_filename": "phi-4-mm-vision.onnx_adapter", "inputs": { "pixel_values": "pixel_values", "attention_mask": "image_attention_mask", "image_sizes": "image_sizes" }, "outputs": { "image_features": "image_features" } }, "speech": { "filename": "phi-4-mm-speech.onnx", "config_filename": "speech_processor.json", "adapter_filename": "phi-4-mm-speech.onnx_adapter", "inputs": { "audio_embeds": "audio_embeds", "attention_mask": "audio_attention_mask", "audio_sizes": "audio_sizes", "audio_projection_mode": "audio_projection_mode" }, "outputs": { "audio_features": "audio_features" } }, "embedding": { "filename": "phi-4-mm-embedding.onnx", "inputs": { "input_ids": "input_ids", "image_features": "image_features", "audio_features": "audio_features" }, "outputs": { "inputs_embeds": "inputs_embeds" } }, "eos_token_id": [ 200020, 199999 ], "pad_token_id": 199999, "type": "phi4mm", "vocab_size": 200064 }, "search": { "diversity_penalty": 0.0, "do_sample": false, "early_stopping": true, "length_penalty": 1.0, "max_length": 131072, "min_length": 0, "no_repeat_ngram_size": 0, "num_beams": 1, "num_return_sequences": 1, "past_present_share_buffer": true, "repetition_penalty": 1.0, "temperature": 1.0, "top_k": 1, "top_p": 1.0 } }