Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 8 of 8 for Piktus (0.3 sec)

  1. model_cards/facebook/rag-sequence-nq/README.md

    ---
    ## 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) 
    by Patrick Lewis, Ethan Perez, Aleksandara Piktus et al.
    
    The model is a *uncased* model, which means that capital letters are simply converted to lower-case letters.
    
    Plain Text
    - Registered: 2020-10-25 10:36
    - Last Modified: 2020-10-16 14:05
    - 1.7K bytes
    - Viewed (2)
  2. model_cards/facebook/rag-token-nq/README.md

    ---
    ## RAG
    
    This is the RAG-Token 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.
    
    The model is a *uncased* model, which means that capital letters are simply converted to lower-case letters.
    
    Plain Text
    - Registered: 2020-10-25 10:36
    - Last Modified: 2020-10-15 10:53
    - 1.7K bytes
    - Viewed (2)
  3. model_cards/facebook/rag-sequence-base/README.md

    ---
    ## RAG
    
    This is a non-finetuned 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.
    
    Plain Text
    - Registered: 2020-10-25 10:36
    - Last Modified: 2020-10-15 10:53
    - 2.3K bytes
    - Viewed (0)
  4. model_cards/facebook/rag-token-base/README.md

    ---
    ## RAG
    
    This is a non-finetuned version of the RAG-Token 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.
    
    Plain Text
    - Registered: 2020-10-25 10:36
    - Last Modified: 2020-10-15 10:53
    - 2.3K bytes
    - Viewed (0)
  5. docs/source/model_doc/rag.rst

    both retrieval and generation to adapt to downstream tasks.
    
    It is based on the paper `Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
    <https://arxiv.org/abs/2005.11401>`__ by Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir
    Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela.
    
    The abstract from the paper is the following:
    
    Plain Text
    - Registered: 2020-10-25 10:36
    - Last Modified: 2020-10-19 17:42
    - 3.3K bytes
    - Viewed (1)
  6. src/transformers/retrieval_rag.py

            def cat_input_and_doc(doc_title, doc_text, input_string, prefix):
                # TODO(Patrick): if we train more RAG models, I want to put the input first to take advantage of effortless truncation
                # TODO(piktus): better handling of truncation
                if doc_title.startswith('"'):
                    doc_title = doc_title[1:]
                if doc_title.endswith('"'):
                    doc_title = doc_title[:-1]
    Python
    - Registered: 2020-10-25 10:36
    - Last Modified: 2020-10-19 17:42
    - 27.3K bytes
    - Viewed (1)
  7. docs/source/model_summary.rst

       </a>
    
    `Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks <https://arxiv.org/abs/2005.11401>`_,
    Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela
    
    Plain Text
    - Registered: 2020-10-25 10:36
    - Last Modified: 2020-10-20 15:02
    - 41.2K bytes
    - Viewed (1)
  8. src/transformers/modeling_rag.py

        r"""
        RAG models were released with the paper `Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
        <https://arxiv.org/abs/2005.11401>`_ by Patrick Lewis, Ethan Perez, Aleksandra Piktus et al.
    
        RAG is a retriever augmented model and encapsulate three components: a question encoder, a dataset retriever and a
        generator, the encoder and generator are trainable while the retriever is just an indexed dataset.
    Python
    - Registered: 2020-10-25 10:36
    - Last Modified: 2020-10-19 13:15
    - 77.4K bytes
    - Viewed (0)
Back to top