Instructions to use microsoft/MiniLM-L12-H384-uncased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/MiniLM-L12-H384-uncased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="microsoft/MiniLM-L12-H384-uncased")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("microsoft/MiniLM-L12-H384-uncased", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download convert_model.py from microsoft/MiniLM-L12-H384-uncased: direct link, hf CLI and curl.
- Browser
- Download file 473 Bytes
-
https://huggingface.co/microsoft/MiniLM-L12-H384-uncased/resolve/main/convert_model.py
- Command line
-
hf download hf://microsoft/MiniLM-L12-H384-uncased/convert_model.py
-
curl -L -o convert_model.py https://huggingface.co/microsoft/MiniLM-L12-H384-uncased/resolve/main/convert_model.py
473 Bytes
| #!/usr/bin/env python3 | |
| import logging | |
| from transformers import BertModel, BertTokenizer, TFBertModel | |
| logging.basicConfig(level=logging.INFO, filename="log.txt") | |
| model = BertModel.from_pretrained("../../MiniLM-L12-H384-uncased/") | |
| tf_model = TFBertModel.from_pretrained("../../MiniLM-L12-H384-uncased/", from_pt=True) | |
| model.save_pretrained("./") | |
| tf_model.save_pretrained("./") | |
| tok = BertTokenizer.from_pretrained("../../MiniLM-L12-H384-uncased/") | |
| tok.save_pretrained("./") | |