Constricted model types and software specifications
Constricted software specifications are only supported in an upgraded instance. They are not supported in new installations, imported space assets, and patch operations.
Constricted model types and software specifications
Support for the following software specifications is constricted:
| Framework | Versions | Model Type | Default software specification | Supported platforms |
|---|---|---|---|---|
| PyTorch | 1.10 | pytorch-onnx_1.10 pytorch-onnx_rt22.1 |
runtime-22.1-py3.9 pytorch-onnx_rt22.1-py3.9 pytorch-onnx_rt22.1-py3.9-edt |
x86 |
| PyTorch | 1.12 | pytorch-onnx_1.12 pytorch-onnx_rt22.2 |
runtime-22.2-py3.10 (F)pytorch-onnx_rt22.2-py3.10 (F)pytorch-onnx_rt22.2-py3.10-edt (F) | x86. PPC, s390x |
| PyTorch | 1.12 | pytorch-onnx_1.12 pytorch-onnx_rt22.2 |
pytorch-onnx_rt22.2-py3.10-dist(x86) (F) | x86 |
| PyTorch | 2.0 | pytorch-onnx_2.0 pytorch-onnx_rt23.1 |
runtime-23.1-py3.10 pytorch-onnx_rt23.1-py3.10 pytorch-onnx_rt23.1-py3.10-edt pytorch-onnx_rt23.1-py3.10-dist |
x86, s390x, PPC |
| Python functions | NA | NA | runtime-22.1-py3.9 | x86 |
| Python functions | NA | NA | runtime-22.2-py3.10 (F) runtime-23.1-py3.10 |
x86, PPC, s390x |
| Python Functions | NA | NA | runtime-23.1-py3.10-cuda | x86 |
| Python Scripts | NA | NA | runtime-22.1-py3.9 | x86 |
| Python Scripts | NA | NA | runtime-23.1-py3.10 | x86, s390x, PPC |
| Python scripts | NA | NA | runtime-22.2-py3.10 (F) | x86, PPC, s390x |
| R Scripts | NA | NA | default_r3.6 runtime-22.1-r3.6 runtime-22.2-r4.2 (F) |
x86 |
| R Scripts | NA | NA | runtime-23.1-r4.2 | x86, PPC |
| R Shiny applications | NA | NA | shiny-r3.6 | x86, PPC |
| R Shiny applications | NA | NA | rstudio_r4.2 | x86 |
| R Shiny applications | NA | NA | rstudio-23.1-r4.2 | x86, PPC |
| Scikit-learn | 1.0 | scikit-learn_1.0 | runtime-22.1-py3.9 | x86 |
| Scikit-learn | 1.1 | scikit-learn_1.1 | runtime-22.2-py3.10 (F) runtime-23.1-py3.10 |
x86, PPC, s390x |
| Spark | 3.3 | mllib_3.3 | spark-mllib_3.3 | x86, PPC |
| Tensorflow | 2.7 | tensorflow_2.7 tensorflow_rt22.1 |
runtime-22.1-py3.9 tensorflow_rt22.1-py3.9 |
x86 |
| Tensorflow | 2.9 | tensorflow_2.9 tensorflow_rt22.2 |
runtime-22.2-py3.10 (F) tensorflow_rt22.2-py3.10 (F) |
x86, PPC, s390x |
| Tensorflow | 2.9 | tensorflow_2.9 4.8.4tensorflow_rt22.2 |
tensorflow_rt22.2-py3.10-dist(x86) (F) tensorflow_rt22.2-py3.10-edt(x86) (F) |
x86, s390x, PPC |
| Tensorflow | 2.12 | tensorflow_2.12 tensorflow_rt23.1 |
runtime-23.1-py3.10 tensorflow_rt23.1-py3.10-dist tensorflow_rt23.1-py3.10-edt tensorflow_rt23.1-py3.10 |
x86, s390x, PPC |
| Tensorflow | 2.12 | tensorflow_2.12 tensorflow_rt23.1 |
runtime-23.1-py3.10-cuda | x86 |
| XGBoost | 1.5 | xgboost_1.5 or scikit-learn_1.0 (see notes) | runtime-22.1-py3.9 | x86 |
| XGBoost | 1.6 | xgboost_1.6 or scikit-learn_1.1 | runtime-22.2-py3.10 (F) | x86, s390x, PPC |
| XGBoost | 1.6 | xgboost_1.6 or scikit-learn_1.1 (see notes) | runtime-23.1-py3.10 | x86, s390x, PPC |
Important:
For XGBoost, if model is trained with sklearn wrapper (XGBClassifier or XGBRegressor), use the scikit-learn_1.1 model type in Python 3.10.
Constricted model types and software specifications for hybrid models
| Framework | Versions | Model Type | Default Software specification |
Pipeline software specification | Supported platform |
|---|---|---|---|---|---|
| Hybrid | 0.1 | wml-hybrid_0.1 | hybrid_0.1 | autoai-kb_rt22.1-py3.9 autoai-ts_rt22.1-py3.9 |
x86 |
| Hybrid | 0.1 | wml-hybrid_0.1 | hybrid_0.1 | autoai-kb_rt22.2-py3.10 (F) autoai-ts_rt22.2-py3.10 (F) autoai-kb_rt23.1-py3.10 autoai-ts_rt23.1-py3.10 autoai-tsad_rt23.1-py3.10 |
x86. PPC, s390x |
Parent topic: Frameworks and software specifications in Watson Machine Learning