RAG (#6813)
* added rag WIP * path fix * Formatting / renaming prior to actual work * added rag WIP * path fix * Formatting / renaming prior to actual work * added rag WIP * path fix * Formatting / renaming prior to actual work * added rag WIP * Formatting / renaming prior to actual work * First commit * improve comments * Retrieval evaluation scripts * refactor to include modeling outputs + MPI retriever * Fix rag-token model + refactor * Various fixes + finetuning logic * use_bos fix * Retrieval refactor * Finetuning refactoring and cleanup * Add documentation and cleanup * Remove set_up_rag_env.sh file * Fix retrieval wit HF index * Fix import errors * Fix quality errors * Refactor as per suggestions in https://github.com/huggingface/transformers/pull/6813#issuecomment-687208867 * fix quality * Fix RAG Sequence generation * minor cleanup plus initial tests * fix test * fix tests 2 * Comments fix * post-merge fixes * Improve readme + post-rebase refactor * Extra dependencied for tests * Fix tests * Fix tests 2 * Refactor test requirements * Fix tests 3 * Post-rebase refactor * rename nlp->datasets * RAG integration tests * add tokenizer to slow integration test and allow retriever to run on cpu * add tests; fix position ids warning * change structure * change structure * add from encoder generator * save working solution * make all integration tests pass * add RagTokenizer.save/from_pretrained and RagRetriever.save/from_pretrained * don't save paths * delete unnecessary imports * pass config to AutoTokenizer.from_pretrained for Rag tokenizers * init wiki_dpr only once * hardcode legacy index and passages paths (todo: add the right urls) * finalize config * finalize retriver api and config api * LegacyIndex index download refactor * add dpr to autotokenizer * make from pretrained more flexible * fix ragfortokengeneration * small name changes in tokenizer * add labels to models * change default index name * add retrieval tests * finish token generate * align test with previous version and make all tests pass * add tests * finalize tests * implement thoms suggestions * add first version of test * make first tests work * make retriever platform agnostic * naming * style * add legacy index URL * docstrings + simple retrieval test for distributed * clean model api * add doc_ids to retriever's outputs * fix retrieval tests * finish model outputs * finalize model api * fix generate problem for rag * fix generate for other modles * fix some tests * save intermediate * set generate to default * big refactor generate * delete rag_api * correct pip faiss install * fix auto tokenization test * fix faiss install * fix test * move the distributed logic to examples * model page * docs * finish tests * fix dependencies * fix import in __init__ * Refactor eval_rag and finetune scripts * start docstring * add psutil to test * fix tf test * move require torch to top * fix retrieval test * align naming * finish automodel * fix repo consistency * test ragtokenizer save/load * add rag model output docs * fix ragtokenizer save/load from pretrained * fix tokenizer dir * remove torch in retrieval * fix docs * fixe finetune scripts * finish model docs * finish docs * remove auto model for now * add require torch * remove solved todos * integrate sylvains suggestions * sams comments * correct mistake on purpose * improve README * Add generation test cases * fix rag token * clean token generate * fix test * add note to test * fix attention mask * add t5 test for rag * Fix handling prefix in finetune.py * don't overwrite index_name Co-authored-by: Patrick Lewis <plewis@fb.com> Co-authored-by: Aleksandra Piktus <piktus@devfair0141.h2.fair> Co-authored-by: Aleksandra Piktus <piktus@learnfair5102.h2.fair> Co-authored-by: Aleksandra Piktus <piktus@learnfair5067.h2.fair> Co-authored-by: Your Name <you@example.com> Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Quentin Lhoest <lhoest.q@gmail.com>
This commit is contained in:
Ola Piktus
@@ -231,6 +231,7 @@ conversion utilities for the following models:
|
||||
model_doc/lxmert
|
||||
model_doc/bertgeneration
|
||||
model_doc/layoutlm
|
||||
model_doc/rag
|
||||
internal/modeling_utils
|
||||
internal/tokenization_utils
|
||||
internal/pipelines_utils
|
||||
|
||||
88
docs/source/model_doc/rag.rst
Normal file
88
docs/source/model_doc/rag.rst
Normal file
@@ -0,0 +1,88 @@
|
||||
RAG
|
||||
----------------------------------------------------
|
||||
|
||||
Overview
|
||||
~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
Retrieval-augmented generation ("RAG") models combine the powers of pretrained dense retrieval (DPR) and Seq2Seq models.
|
||||
RAG models retrieve docs, pass them to a seq2seq model, then marginalize to generate outputs.
|
||||
The retriever and seq2seq modules are initialized from pretrained models, and fine-tuned jointly, allowing 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:
|
||||
|
||||
*Large pre-trained language models have been shown to store factual knowledge
|
||||
in their parameters, and achieve state-of-the-art results when fine-tuned on
|
||||
downstream NLP tasks. However, their ability to access and precisely manipulate
|
||||
knowledge is still limited, and hence on knowledge-intensive tasks, their
|
||||
performance lags behind task-specific architectures. Additionally, providing
|
||||
provenance for their decisions and updating their world knowledge remain open
|
||||
research problems. Pre-trained models with a differentiable access mechanism to
|
||||
explicit nonparametric memory can overcome this issue, but have so far been only
|
||||
investigated for extractive downstream tasks. We explore a general-purpose
|
||||
fine-tuning recipe for retrieval-augmented generation (RAG) — models which combine
|
||||
pre-trained parametric and non-parametric memory for language generation. We
|
||||
introduce RAG models where the parametric memory is a pre-trained seq2seq model and
|
||||
the non-parametric memory is a dense vector index of Wikipedia, accessed with
|
||||
a pre-trained neural retriever. We compare two RAG formulations, one which
|
||||
conditions on the same retrieved passages across the whole generated sequence, the
|
||||
other can use different passages per token. We fine-tune and evaluate our models
|
||||
on a wide range of knowledge-intensive NLP tasks and set the state-of-the-art
|
||||
on three open domain QA tasks, outperforming parametric seq2seq models and
|
||||
task-specific retrieve-and-extract architectures. For language generation tasks, we
|
||||
find that RAG models generate more specific, diverse and factual language than a
|
||||
state-of-the-art parametric-only seq2seq baseline.*
|
||||
|
||||
|
||||
|
||||
RagConfig
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. autoclass:: transformers.RagConfig
|
||||
:members:
|
||||
|
||||
|
||||
RagTokenizer
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. autoclass:: transformers.RagTokenizer
|
||||
:members:
|
||||
|
||||
|
||||
Rag specific outputs
|
||||
~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. autoclass:: transformers.modeling_rag.RetrievAugLMMarginOutput
|
||||
:members:
|
||||
|
||||
.. autoclass:: transformers.modeling_rag.RetrievAugLMOutput
|
||||
:members:
|
||||
|
||||
|
||||
RAGRetriever
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. autoclass:: transformers.RagRetriever
|
||||
:members:
|
||||
|
||||
|
||||
RagModel
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. autoclass:: transformers.RagModel
|
||||
:members: forward
|
||||
|
||||
|
||||
RagSequenceForGeneration
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. autoclass:: transformers.RagSequenceForGeneration
|
||||
:members: forward, generate
|
||||
|
||||
|
||||
RagTokenForGeneration
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. autoclass:: transformers.RagTokenForGeneration
|
||||
:members: forward, generate
|
||||
@@ -654,7 +654,7 @@ DPR
|
||||
<a href="https://huggingface.co/models?filter=dpr">
|
||||
<img alt="Models" src="https://img.shields.io/badge/All_model_pages-dpr-blueviolet">
|
||||
</a>
|
||||
<a href="model_doc/ctrl.dpr">
|
||||
<a href="model_doc/dpr.html">
|
||||
<img alt="Doc" src="https://img.shields.io/badge/Model_documentation-dpr-blueviolet">
|
||||
</a>
|
||||
|
||||
@@ -672,6 +672,27 @@ DPR consists in three models:
|
||||
|
||||
DPR's pipeline (not implemented yet) uses a retrieval step to find the top k contexts given a certain question, and then it calls the reader with the question and the retrieved documents to get the answer.
|
||||
|
||||
RAG
|
||||
----------------------------------------------
|
||||
|
||||
.. raw:: html
|
||||
|
||||
<a href="https://huggingface.co/models?filter=rag">
|
||||
<img alt="Models" src="https://img.shields.io/badge/All_model_pages-rag-blueviolet">
|
||||
</a>
|
||||
<a href="model_doc/rag.html">
|
||||
<img alt="Doc" src="https://img.shields.io/badge/Model_documentation-rag-blueviolet">
|
||||
</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
|
||||
|
||||
Retrieval-augmented generation ("RAG") models combine the powers of pretrained dense retrieval (DPR) and Seq2Seq models.
|
||||
RAG models retrieve docs, pass them to a seq2seq model, then marginalize to generate outputs.
|
||||
The retriever and seq2seq modules are initialized from pretrained models, and fine-tuned jointly, allowing both retrieval and generation to adapt to downstream tasks.
|
||||
|
||||
The two models RAG-Token and RAG-Sequence are available for generation.
|
||||
|
||||
More technical aspects
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
|
||||
Reference in New Issue
Block a user