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
| { | |
| "seeded_perturbations": ["misspelling", "reordering", "synonym", "paraphrase"], | |
| "seeds": [1999, 5, 27, 2016, 2026], | |
| "unseeded_perturbations": { | |
| "naturality": "Deterministic transformation (stop-word removal). Produces identical output regardless of seed; represented in the TSV files with seed='deterministic' rather than being duplicated five times." | |
| } | |
| } | |