SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Patrick von Platen
2020-09-18 16:37:14 +02:00
committed by GitHub
parent 4c14669a78
commit 31516c776a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
model_cards/facebook/rag-sequence-nq/README.md
View File

@@ -1,7 +1,7 @@
## RAG ## RAG
This is the RAG-Sequence Model of the the paper [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/pdf/2005.11401.pdf) This is the RAG-Sequence Model of the the paper [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/pdf/2005.11401.pdf)
by Aleksandra Piktus et al. by Patrick Lewis, Ethan Perez, Aleksandara Piktus et al.
## Usage: ## Usage:
@@ -18,7 +18,7 @@ outputs = model(input_ids=input_dict["input_ids"], labels=input_dict["labels"])
# outputs.loss should give 76.2978 # outputs.loss should give 76.2978
generated = model.generate(input_ids=input_dict["input_ids"], num_beams=4) generated = model.generate(input_ids=input_dict["input_ids"])
generated_string = tokenizer.batch_decode(generated, skip_special_tokens=True) generated_string = tokenizer.batch_decode(generated, skip_special_tokens=True)
# generated_string should give 270,000,000 -> not quite correct the answer, but it also only uses a dummy index # generated_string should give 270,000,000 -> not quite correct the answer, but it also only uses a dummy index