diff --git a/examples/recipes/mixedbread-ai_mxbai-rerank-base-v1/cpu/cpu/text-classification_fp16_config.json b/examples/recipes/mixedbread-ai_mxbai-rerank-base-v1/cpu/cpu/text-classification_fp16_config.json new file mode 100644 index 000000000..7b36e6952 --- /dev/null +++ b/examples/recipes/mixedbread-ai_mxbai-rerank-base-v1/cpu/cpu/text-classification_fp16_config.json @@ -0,0 +1,54 @@ +{ + "export": { + "opset_version": 17, + "batch_size": 1, + "export_params": true, + "do_constant_folding": true, + "verbose": false, + "dynamo": false, + "enable_hierarchy_tags": true, + "clean_onnx": false, + "hierarchy_tag_format": "full", + "input_tensors": [ + { + "name": "input_ids", + "dtype": "int32", + "shape": [ + 1, + 512 + ], + "value_range": [ + 0, + 128100 + ] + }, + { + "name": "attention_mask", + "dtype": "int32", + "shape": [ + 1, + 512 + ], + "value_range": [ + 0, + 2 + ] + } + ], + "output_tensors": [ + { + "name": "logits" + } + ] + }, + "optim": { + "clamp_constant_values": true + }, + "quant": null, + "compile": null, + "loader": { + "task": "text-classification", + "model_class": "AutoModelForSequenceClassification", + "model_type": "deberta-v2" + } +} diff --git a/examples/recipes/mixedbread-ai_mxbai-rerank-base-v1/cpu/cpu/text-classification_fp32_config.json b/examples/recipes/mixedbread-ai_mxbai-rerank-base-v1/cpu/cpu/text-classification_fp32_config.json new file mode 100644 index 000000000..7b36e6952 --- /dev/null +++ b/examples/recipes/mixedbread-ai_mxbai-rerank-base-v1/cpu/cpu/text-classification_fp32_config.json @@ -0,0 +1,54 @@ +{ + "export": { + "opset_version": 17, + "batch_size": 1, + "export_params": true, + "do_constant_folding": true, + "verbose": false, + "dynamo": false, + "enable_hierarchy_tags": true, + "clean_onnx": false, + "hierarchy_tag_format": "full", + "input_tensors": [ + { + "name": "input_ids", + "dtype": "int32", + "shape": [ + 1, + 512 + ], + "value_range": [ + 0, + 128100 + ] + }, + { + "name": "attention_mask", + "dtype": "int32", + "shape": [ + 1, + 512 + ], + "value_range": [ + 0, + 2 + ] + } + ], + "output_tensors": [ + { + "name": "logits" + } + ] + }, + "optim": { + "clamp_constant_values": true + }, + "quant": null, + "compile": null, + "loader": { + "task": "text-classification", + "model_class": "AutoModelForSequenceClassification", + "model_type": "deberta-v2" + } +}