Transformers
PyTorch
TensorFlow
JAX
English
t5
text2text-generation
deep-narrow
text-generation-inference
Instructions to use google/t5-efficient-base-kv256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/t5-efficient-base-kv256 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/t5-efficient-base-kv256") model = AutoModelForSeq2SeqLM.from_pretrained("google/t5-efficient-base-kv256", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download flax_model.msgpack from google/t5-efficient-base-kv256: direct link, hf CLI and curl.
- Browser
- Download file 1.91 GB
-
https://huggingface.co/google/t5-efficient-base-kv256/resolve/main/flax_model.msgpack
- Command line
-
hf download hf://google/t5-efficient-base-kv256/flax_model.msgpack
-
curl -L -o flax_model.msgpack https://huggingface.co/google/t5-efficient-base-kv256/resolve/main/flax_model.msgpack
1.91 GB
- Xet hash:
- 705956a078bf6ef711302fa5d31aed58fab4d4d1bbe0a9c34ea9ca1f83e40a5d
- Size of remote file:
- 1.91 GB
- SHA256:
- 41320fbf6954cf617da9a6e3cd57f42b7f848aafcc96806e81bff4baaba8460f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.