| { | |
| "external_data": "model.onnx.data", | |
| "geometry": { | |
| "dynamic_batch": true, | |
| "dynamic_sequence": true, | |
| "local_attention_window": 257, | |
| "max_batch": 32, | |
| "max_sequence": 1024, | |
| "passage_max_sequence": 1024, | |
| "query_max_sequence": 128 | |
| }, | |
| "graph": "model.onnx", | |
| "inputs": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "output": "embeddings", | |
| "precision": "float32", | |
| "provider_chain": [ | |
| "CUDAExecutionProvider", | |
| "CPUExecutionProvider" | |
| ], | |
| "role": "dense-retriever", | |
| "schema": "daecore.retrieval-onnx-serving.v1", | |
| "sha256": "8c088b1635875d5406e148782b303cfc5a961138600783fb4842b413b98a98c3", | |
| "source_model_tree_sha256": "30a7b9f1c42b1fcee29a6729742685d5b744e8fa87d13cefab2fd2d49ea9150e", | |
| "torch_required_at_runtime": false | |
| } | |