optimum 1.8.8
legitimate ML libraries
Applies wraps to nested Python functionBacktick shell command-substitution syntax
SHA-25607a5bd64d3d9dcdbc3926e7a421fbe7fce206fff0d9488a6aad7de1315287449
Evidence
1Metadata-Version: 2.1
2Name: optimum
3Version: 1.8.8
4Summary: Optimum Library is an extension of the Hugging Face Transformers library, providing a framework to integrate third-party libraries from Hardware Partners and interface with their specific functionality.
5Home-page: https://github.com/huggingface/optimum
6Author: HuggingFace Inc. Special Ops Team
7Author-email: [email protected]
8License: Apache
9Keywords: transformers,quantiza …
19:45… :: Artificial Intelligence
20Requires-Python: >=3.7.0
21Description-Content-Type: text/markdown
22Provides-Extra: onnxruntime
23Provides-Extra: onnxruntime-gpu
24Provides-Extra: exporters
25Provides-Extra: exporters-g …
45:113… maximum efficiency to train and run models on targeted hardware, while keeping things easy to use.
46
47## Installation
48
49🤗 Optimum can be installed using `pip` as follows:
50
51```bash
52python -m pip install optimum
53```
54
55If you'd like to use the accelerator-specific features of 🤗 Optimum, you can install the required dependencies according to the table below:
56
57| Accelerator …
143:12… kenizer.decode(predict_answer_tokens, skip_special_tokens=True)
144```
145
146More details on how to run ONNX models with `ORTModelForXXX` classes [here](https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/models).
⋯4 lines
187:2… Habana's Gaudi processors
188- ONNX Runtime (optimized for GPUs)
189
190### Habana
191
192```diff
⋯4 lines
Showing the top 5 files — 6 more files (69 regions) not shown.