Instructions to use dosai/bert-sud with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dosai/bert-sud with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="dosai/bert-sud")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("dosai/bert-sud") model = AutoModelForQuestionAnswering.from_pretrained("dosai/bert-sud", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tf_model.h5 from dosai/bert-sud: direct link, hf CLI and curl.
- Browser
- Download file 667 MB
-
https://huggingface.co/dosai/bert-sud/resolve/main/tf_model.h5
- Command line
-
hf download hf://dosai/bert-sud/tf_model.h5
-
curl -L -o tf_model.h5 https://huggingface.co/dosai/bert-sud/resolve/main/tf_model.h5
667 MB
- Xet hash:
- c8462390202e7e5d90dea17e5569d194f8926122855890125e4856dd3b823d4b
- Size of remote file:
- 667 MB
- SHA256:
- 29448ed5795ee875c0d38ed9c6ad732567119d7646af127e860dc703f1352bbd
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.