Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
Paper • 2007.01282 • Published
Text Generation
Transformers
PyTorch
Safetensors
English
t5
Eval Results (legacy)
text-generation-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Intel/fid_t5_large_nq")
model = AutoModelForSeq2SeqLM.from_pretrained("Intel/fid_t5_large_nq")Quick Links
Fusion-In-Decoder Base on Natural Questions
This trained model is based on the Fusion-In-Decoder model, and trained on the Natural Questions dataset.
Model Details
Model is based on Fusion-In-Decoder, which in turn is based on the t5-large checkpoint as the base model. For training, we utilized text retrieval for each query, which provides a collection of relevant passages for it.
We note that the passages were retrieved using a corpus based on Wikipedia.
Evaluation
See model performance on Evaluation Results tab on the right side.
- Downloads last month
- 936
Dataset used to train Intel/fid_t5_large_nq
Paper for Intel/fid_t5_large_nq
Evaluation results
- Exact Macth on NQ KILTself-reported59.010
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Intel/fid_t5_large_nq")