Instructions to use Intel/tiny-random-bert_ipex_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Intel/tiny-random-bert_ipex_model 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="Intel/tiny-random-bert_ipex_model")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Intel/tiny-random-bert_ipex_model") model = AutoModelForQuestionAnswering.from_pretrained("Intel/tiny-random-bert_ipex_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model Card for Model ID
This is a tiny random bert model. It was uploaded by IPEXModelForQuestionAnswering.
from optimum.intel import IPEXModelForQuestionAnswering
model = IPEXModelForQuestionAnswering.from_pretrained("Intel/tiny-random-bert")
model.push_to_hub("Intel/tiny-random-bert_ipex_model")
This is useful for functional testing (not quality generation, since its weights are random) on optimum-intel
- Downloads last month
- 41