saymrwulf/transformers
1
0
Fork 0
mirror of https://github.com/saymrwulf/transformers.git synced 2026-05-14 20:58:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Create README.md

Browse source
This commit is contained in:
Patrick von Platen 2020-09-18 16:52:00 +02:00 committed by GitHub
parent 7eeca4d399
commit 9397436ea5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 22 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
model_cards/facebook/rag-sequence-base/README.md Normal file
View file

@ -0,0 +1,22 @@
## RAG
This is a "base" version of the RAG-Sequence Model of the the paper [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/pdf/2005.11401.pdf)
by Patrick Lewis, Ethan Perez, Aleksandara Piktus et al.
## Usage:
```python
from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
tokenizer = RagTokenizer.from_pretrained("facebook/rag-sequence-base")
retriever = RagRetriever.from_pretrained("facebook/rag-sequence-base", index_name="exact", use_dummy_dataset=True)
model = RagSequenceForGeneration.from_pretrained("facebook/rag-sequence-base", retriever=retriever)
input_ids = tokenizer("What is the largest country in the world?", return_tensors="pt").input_ids
generated = model.generate(input_ids=input_ids)
generated_string = tokenizer.batch_decode(generated, skip_special_tokens=True)
# => should give ["Asia ended in 2010 when China overtook Japan to become the world's second largest economy."]
# Interesting answer. Definitely on topic, but might factual probably not fully correct.
```