Transformers
PyTorch
t5
generative-retrieval
information-retrieval
msmarco
robustness
reproducibility
text-generation-inference
Instructions to use kiyam/lost-in-decoding-pag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kiyam/lost-in-decoding-pag with Transformers:
# Load model directly from transformers import AutoTokenizer, T5ForLexicalSemanticGeneration tokenizer = AutoTokenizer.from_pretrained("kiyam/lost-in-decoding-pag") model = T5ForLexicalSemanticGeneration.from_pretrained("kiyam/lost-in-decoding-pag", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 80f58d73b891a0a3c5a6f090e37f746605249aa3c57c20954bb197179cfe54c2
- Size of remote file:
- 2.97 GB
- SHA256:
- 29e6b3b0cb74db6dcbc34f5f7e9cb6c928e60e0a381bd460da5de5a7d7a624b2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.