Instructions to use harshil10/tiny_bert_flax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use harshil10/tiny_bert_flax 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="harshil10/tiny_bert_flax")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("harshil10/tiny_bert_flax") model = AutoModelForQuestionAnswering.from_pretrained("harshil10/tiny_bert_flax", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.zip from harshil10/tiny_bert_flax: direct link, hf CLI and curl.
- Browser
- Download file 1.07 kB
-
https://huggingface.co/harshil10/tiny_bert_flax/resolve/main/training_args.zip
- Command line
-
hf download hf://harshil10/tiny_bert_flax/training_args.zip
-
curl -L -o training_args.zip https://huggingface.co/harshil10/tiny_bert_flax/resolve/main/training_args.zip
1.07 kB
- Xet hash:
- 7cbda3cb05d40968ace4facb7353af739b2be646bf3143d217f22055674c93e9
- Size of remote file:
- 1.07 kB
- SHA256:
- 10bd9a1d54114ef0ffed0f4fce87e26e2893d94deb467851675ad19ea211ac7f
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.