Instructions to use CatSnowdrop/universal_onnxruntime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use CatSnowdrop/universal_onnxruntime with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download onnxruntime/transformers/constants.py from CatSnowdrop/universal_onnxruntime: direct link, hf CLI and curl.
- Browser
- Download file 1.08 kB
-
https://huggingface.co/CatSnowdrop/universal_onnxruntime/resolve/main/onnxruntime/transformers/constants.py
- Command line
-
hf download hf://CatSnowdrop/universal_onnxruntime/onnxruntime/transformers/constants.py
-
curl -L -o constants.py https://huggingface.co/CatSnowdrop/universal_onnxruntime/resolve/main/onnxruntime/transformers/constants.py
1.08 kB
| # ------------------------------------------------------------------------- | |
| # Copyright (c) Microsoft Corporation. All rights reserved. | |
| # Licensed under the MIT License. | |
| # -------------------------------------------------------------------------- | |
| class Operators: | |
| ATTENTION = "Attention" | |
| LAYERNORM = "LayerNormalization" | |
| MULTI_HEAD_ATTENTION = "MultiHeadAttention" | |
| PACKEDATTENTION = "PackedAttention" | |
| PACKED_MULTI_HEAD_ATTENTION = "PackedMultiHeadAttention" | |
| REMOVEPADDING = "RemovePadding" | |
| RESTOREPADDING = "RestorePadding" | |
| SKIPLAYERNORM = "SkipLayerNormalization" | |
| class AttentionInputIDs: | |
| INPUT = 0 | |
| WEIGHTS = 1 | |
| BIAS = 2 | |
| MASK_INDEX = 3 | |
| PAST = 4 | |
| ATTENTION_BIAS = 5 | |
| PAST_SEQUENCE_LENGTH = 6 | |
| class AttentionOutputIDs: | |
| OUTPUT = 0 | |
| PRESENT = 1 | |
| class MultiHeadAttentionInputIDs: | |
| QUERY = 0 | |
| KEY = 1 | |
| VALUE = 2 | |
| BIAS = 3 | |
| KEY_PADDING_MASK = 4 | |
| ATTENTION_BIAS = 5 | |
| PAST_KEY = 6 | |
| PAST_VALUE = 7 | |
| class MultiHeadAttentionOutputIDs: | |
| OUTPUT = 0 | |
| PRESENT_KEY = 1 | |
| PRESENT_VALUE = 2 | |