Instructions to use Felladrin/onnx-Intel-dynamic_tinybert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Felladrin/onnx-Intel-dynamic_tinybert 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="Felladrin/onnx-Intel-dynamic_tinybert")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Felladrin/onnx-Intel-dynamic_tinybert") model = AutoModelForQuestionAnswering.from_pretrained("Felladrin/onnx-Intel-dynamic_tinybert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download onnx/decoder_model_merged_quantized.onnx from Felladrin/onnx-Intel-dynamic_tinybert: direct link, hf CLI and curl.
- Browser
- Download file 67 MB
-
https://huggingface.co/Felladrin/onnx-Intel-dynamic_tinybert/resolve/main/onnx/decoder_model_merged_quantized.onnx
- Command line
-
hf download hf://Felladrin/onnx-Intel-dynamic_tinybert/onnx/decoder_model_merged_quantized.onnx
-
curl -L -o decoder_model_merged_quantized.onnx https://huggingface.co/Felladrin/onnx-Intel-dynamic_tinybert/resolve/main/onnx/decoder_model_merged_quantized.onnx
67 MB
- Xet hash:
- 8d9aeb288b6229657e20a068dbd6f9335a58d15e504e435ef89baa227f282ea6
- Size of remote file:
- 67 MB
- SHA256:
- 9a088c25cec105afd07e4f9bc18e43482aa006acb67b2358c66d1e3c75a78b01
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.