Instructions to use Mathnub/ruDistilBert-base-sberquad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mathnub/ruDistilBert-base-sberquad 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="Mathnub/ruDistilBert-base-sberquad")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Mathnub/ruDistilBert-base-sberquad") model = AutoModelForQuestionAnswering.from_pretrained("Mathnub/ruDistilBert-base-sberquad", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from Mathnub/ruDistilBert-base-sberquad: direct link, hf CLI and curl.
- Browser
- Download file 3.52 kB
-
https://huggingface.co/Mathnub/ruDistilBert-base-sberquad/resolve/main/training_args.bin
- Command line
-
hf download hf://Mathnub/ruDistilBert-base-sberquad/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/Mathnub/ruDistilBert-base-sberquad/resolve/main/training_args.bin
3.52 kB
- Xet hash:
- 4d95bbbc27c9388c73c846422aa654f83ad3f120db3c4994d1c5f5de754bab41
- Size of remote file:
- 3.52 kB
- SHA256:
- 1c58e651f1f57e2339def9f28f39bf212c9d4b943c11dda3b91ba2884995ee82
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.