Instructions to use echarlaix/t5-small-int8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use echarlaix/t5-small-int8-dynamic with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" 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("translation", model="echarlaix/t5-small-int8-dynamic")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("echarlaix/t5-small-int8-dynamic") model = AutoModelWithLMHead.from_pretrained("echarlaix/t5-small-int8-dynamic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download decoder_model.onnx from echarlaix/t5-small-int8-dynamic: direct link, hf CLI and curl.
- Browser
- Download file 58.3 MB
-
https://huggingface.co/echarlaix/t5-small-int8-dynamic/resolve/main/decoder_model.onnx
- Command line
-
hf download hf://echarlaix/t5-small-int8-dynamic/decoder_model.onnx
-
curl -L -o decoder_model.onnx https://huggingface.co/echarlaix/t5-small-int8-dynamic/resolve/main/decoder_model.onnx
58.3 MB
- Xet hash:
- 0d3db6ba1916a80d571a420547c70ad589004ab4b05e5fe0023cd42e44914f8e
- Size of remote file:
- 58.3 MB
- SHA256:
- 8a08e2c556fc3c0929c040a53a68cc3e8e0027ecb42056925577cc52d9f06cdb
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.