RAG
Overview
Retrieval-augmented generation (“RAG”) models combine the powers of pretrained dense retrieval (DPR) and sequence-to-sequence models. RAG models retrieve documents, 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 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.
This model was contributed by ola13.
RagConfig
class transformers.RagConfig
< source >( vocab_size = None is_encoder_decoder = True prefix = None bos_token_id = None pad_token_id = None eos_token_id = None decoder_start_token_id = None title_sep = ' / ' doc_sep = ' // ' n_docs = 5 max_combined_length = 300 retrieval_vector_size = 768 retrieval_batch_size = 8 dataset = 'wiki_dpr' dataset_split = 'train' index_name = 'compressed' index_path = None passages_path = None use_dummy_dataset = False reduce_loss = False label_smoothing = 0.0 do_deduplication = True exclude_bos_score = False do_marginalize = False output_retrieved = False use_cache = True forced_eos_token_id = None **kwargs )
Parameters
-
title_sep (
str, optional, defaults to" / ") — Separator inserted between the title and the text of the retrieved document when calling RagRetriever. -
doc_sep (
str, optional, defaults to" // ") — Separator inserted between the text of the retrieved document and the original input when calling RagRetriever. -
n_docs (
int, optional, defaults to 5) — Number of documents to retrieve. -
max_combined_length (
int, optional, defaults to 300) — Max length of contextualized input returned by__call__(). -
retrieval_vector_size (
int, optional, defaults to 768) — Dimensionality of the document embeddings indexed by RagRetriever. -
retrieval_batch_size (
int, optional, defaults to 8) — Retrieval batch size, defined as the number of queries issues concurrently to the faiss index encapsulated RagRetriever. -
dataset (
str, optional, defaults to"wiki_dpr") — A dataset identifier of the indexed dataset in HuggingFace Datasets (list all available datasets and ids usingdatasets.list_datasets()). -
dataset_split (
str, optional, defaults to"train") — Which split of thedatasetto load. -
index_name (
str, optional, defaults to"compressed") — The index name of the index associated with thedataset. One can choose between"legacy","exact"and"compressed". -
index_path (
str, optional) — The path to the serialized faiss index on disk. -
passages_path (
str, optional) — A path to text passages compatible with the faiss index. Required if usingLegacyIndex -
use_dummy_dataset (
bool, optional, defaults toFalse) — Whether to load a “dummy” variant of the dataset specified bydataset. -
label_smoothing (
float, optional, defaults to 0.0) — Only relevant ifreturn_lossis set toTrue. Controls theepsilonparameter value for label smoothing in the loss calculation. If set to 0, no label smoothing is performed. -
do_marginalize (
bool, optional, defaults toFalse) — IfTrue, the logits are marginalized over all documents by making use oftorch.nn.functional.log_softmax. -
reduce_loss (
bool, optional, defaults toFalse) — Whether or not to reduce the NLL loss using thetorch.Tensor.sumoperation. -
do_deduplication (
bool, optional, defaults toTrue) — Whether or not to deduplicate the generations from different context documents for a given input. Has to be set toFalseif used while training with distributed backend. -
exclude_bos_score (
bool, optional, defaults toFalse) — Whether or not to disregard the BOS token when computing the loss. -
output_retrieved(
bool, optional, defaults toFalse) — If set toTrue,retrieved_doc_embeds,retrieved_doc_ids,context_input_idsandcontext_attention_maskare returned. See returned tensors for more detail. -
use_cache (
bool, optional, defaults toTrue) — Whether or not the model should return the last key/values attentions (not used by all models). -
forced_eos_token_id (
int, optional) — The id of the token to force as the last generated token whenmax_lengthis reached. Usually set toeos_token_id.
RagConfig stores the configuration of a RagModel. Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
from_question_encoder_generator_configs
< source >( question_encoder_config: PretrainedConfig generator_config: PretrainedConfig **kwargs ) → EncoderDecoderConfig
Instantiate a EncoderDecoderConfig (or a derived class) from a pre-trained encoder model configuration and decoder model configuration.
to_dict
< source >(
)
→
Dict[str, any]
Returns
Dict[str, any]
Dictionary of all the attributes that make up this configuration instance,
Serializes this instance to a Python dictionary. Override the default to_dict().
RagTokenizer
Rag specific outputs
class transformers.models.rag.modeling_rag.RetrievAugLMMarginOutput
< source >( loss: typing.Optional[torch.FloatTensor] = None logits: FloatTensor = None doc_scores: FloatTensor = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None retrieved_doc_embeds: typing.Optional[torch.FloatTensor] = None retrieved_doc_ids: typing.Optional[torch.LongTensor] = None context_input_ids: typing.Optional[torch.LongTensor] = None context_attention_mask: typing.Optional[torch.LongTensor] = None question_encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None question_enc_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None question_enc_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_enc_last_hidden_state: typing.Optional[torch.FloatTensor] = None generator_enc_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_enc_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_dec_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_dec_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None )
Parameters
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. -
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head. The score is possibly marginalized over all documents for each vocabulary token. -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. -
past_key_values (
List[torch.FloatTensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftorch.FloatTensorof lengthconfig.n_layers, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)).Contains precomputed hidden-states (key and values in the attention blocks) of the decoder that can be used (see
past_key_valuesinput) to speed up sequential decoding. -
retrieved_doc_embeds (
torch.FloatTensorof shape(batch_size, config.n_docs, hidden_size), optional, returned when output_retrieved=True) — Embedded documents retrieved by the retriever. Is used withquestion_encoder_last_hidden_stateto compute thedoc_scores. -
retrieved_doc_ids (
torch.LongTensorof shape(batch_size, config.n_docs), optional, returned when output_retrieved=True) — The indexes of the embedded documents retrieved by the retriever. -
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input ids post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever. -
question_encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden states at the output of the last layer of the question encoder pooled output of the model. -
question_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the question encoder at the output of each layer plus the initial embedding outputs.
-
question_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the question encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_enc_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the generator encoder of the model. -
generator_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator encoder at the output of each layer plus the initial embedding outputs.
-
generator_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_dec_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator decoder at the output of each layer plus the initial embedding outputs.
-
generator_dec_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_cross_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Cross-attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the cross-attention heads.
Base class for retriever augmented marginalized models outputs.
class transformers.models.rag.modeling_rag.RetrievAugLMOutput
< source >( logits: FloatTensor = None doc_scores: FloatTensor = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None retrieved_doc_embeds: typing.Optional[torch.FloatTensor] = None retrieved_doc_ids: typing.Optional[torch.LongTensor] = None context_input_ids: typing.Optional[torch.LongTensor] = None context_attention_mask: typing.Optional[torch.LongTensor] = None question_encoder_last_hidden_state: typing.Optional[torch.FloatTensor] = None question_enc_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None question_enc_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_enc_last_hidden_state: typing.Optional[torch.FloatTensor] = None generator_enc_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_enc_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_dec_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_dec_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None generator_cross_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None )
Parameters
-
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head. The score is possibly marginalized over all documents for each vocabulary token. -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. -
past_key_values (
List[torch.FloatTensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftorch.FloatTensorof lengthconfig.n_layers, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)).Contains precomputed hidden-states (key and values in the attention blocks) of the decoder that can be used (see
past_key_valuesinput) to speed up sequential decoding. -
retrieved_doc_embeds (
torch.FloatTensorof shape(batch_size, config.n_docs, hidden_size), optional, returned when output_retrieved=True) — Embedded documents retrieved by the retriever. Is used withquestion_encoder_last_hidden_stateto compute thedoc_scores. -
retrieved_doc_ids (
torch.LongTensorof shape(batch_size, config.n_docs), optional, returned when output_retrieved=True) — The indexes of the embedded documents retrieved by the retriever. -
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input ids post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever. -
question_encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden states at the output of the last layer of the question encoder pooled output of the model. -
question_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the question encoder at the output of each layer plus the initial embedding outputs.
-
question_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the question encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_enc_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the generator encoder of the model. -
generator_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator encoder at the output of each layer plus the initial embedding outputs.
-
generator_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_dec_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator decoder at the output of each layer plus the initial embedding outputs.
-
generator_dec_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_cross_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Cross-attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the cross-attention heads.
RagRetriever
class transformers.RagRetriever
< source >( config question_encoder_tokenizer generator_tokenizer index = None init_retrieval = True )
Parameters
-
config (RagConfig) —
The configuration of the RAG model this Retriever is used with. Contains parameters indicating which
Indexto build. You can load your own custom dataset withconfig.index_name="custom"or use a canonical one (default) from the datasets library withconfig.index_name="wiki_dpr"for example. - question_encoder_tokenizer (PreTrainedTokenizer) — The tokenizer that was used to tokenize the question. It is used to decode the question and then use the generator_tokenizer.
- generator_tokenizer (PreTrainedTokenizer) — The tokenizer used for the generator part of the RagModel.
-
index (
Index, optional, defaults to the one defined by the configuration) — If specified, use this index instead of the one built using the configuration
Retriever used to get documents from vector queries. It retrieves the documents embeddings as well as the documents contents, and it formats them to be used with a RagModel.
Examples:
>>> # To load the default "wiki_dpr" dataset with 21M passages from wikipedia (index name is 'compressed' or 'exact')
>>> from transformers import RagRetriever
>>> retriever = RagRetriever.from_pretrained(
... "facebook/dpr-ctx_encoder-single-nq-base", dataset="wiki_dpr", index_name="compressed"
... )
>>> # To load your own indexed dataset built with the datasets library. More info on how to build the indexed dataset in examples/rag/use_own_knowledge_dataset.py
>>> from transformers import RagRetriever
>>> dataset = (
... ...
... ) # dataset must be a datasets.Datasets object with columns "title", "text" and "embeddings", and it must have a faiss index
>>> retriever = RagRetriever.from_pretrained("facebook/dpr-ctx_encoder-single-nq-base", indexed_dataset=dataset)
>>> # To load your own indexed dataset built with the datasets library that was saved on disk. More info in examples/rag/use_own_knowledge_dataset.py
>>> from transformers import RagRetriever
>>> dataset_path = "path/to/my/dataset" # dataset saved via *dataset.save_to_disk(...)*
>>> index_path = "path/to/my/index.faiss" # faiss index saved via *dataset.get_index("embeddings").save(...)*
>>> retriever = RagRetriever.from_pretrained(
... "facebook/dpr-ctx_encoder-single-nq-base",
... index_name="custom",
... passages_path=dataset_path,
... index_path=index_path,
... )
>>> # To load the legacy index built originally for Rag's paper
>>> from transformers import RagRetriever
>>> retriever = RagRetriever.from_pretrained("facebook/dpr-ctx_encoder-single-nq-base", index_name="legacy")Retriever initialization function. It loads the index into memory.
postprocess_docs
< source >(
docs
input_strings
prefix
n_docs
return_tensors = None
)
→
tuple(tensors)
Parameters
-
docs (
dict) — Retrieved documents. -
input_strings (
str) — Input strings decoded bypreprocess_query. -
prefix (
str) — Prefix added at the beginning of each input, typically used with T5-based models.
Returns
tuple(tensors)
a tuple consisting of two elements: contextualized input_ids and a compatible
attention_mask.
Postprocessing retrieved docs and combining them with input_strings.
retrieve
< source >(
question_hidden_states: ndarray
n_docs: int
)
→
Tuple[np.ndarray, np.ndarray, List[dict]]
Parameters
-
question_hidden_states (
np.ndarrayof shape(batch_size, vector_size)) — A batch of query vectors to retrieve with. -
n_docs (
int) — The number of docs retrieved per query.
Returns
Tuple[np.ndarray, np.ndarray, List[dict]]
A tuple with the following objects:
- retrieved_doc_embeds (
np.ndarrayof shape(batch_size, n_docs, dim)) — The retrieval embeddings of the retrieved docs per query. - doc_ids (
np.ndarrayof shape(batch_size, n_docs)) — The ids of the documents in the index - doc_dicts (
List[dict]): Theretrieved_doc_embedsexamples per query.
Retrieves documents for specified question_hidden_states.
RagModel
class transformers.RagModel
< source >( config: typing.Optional[transformers.configuration_utils.PretrainedConfig] = None question_encoder: typing.Optional[transformers.modeling_utils.PreTrainedModel] = None generator: typing.Optional[transformers.modeling_utils.PreTrainedModel] = None retriever: typing.Optional[transformers.models.rag.retrieval_rag.RagRetriever] = None **kwargs )
Parameters
- config (RagConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
-
question_encoder (PreTrainedModel) —
An encoder model compatible with the faiss index encapsulated by the
retriever. - generator (PreTrainedModel) — A seq2seq model used as the generator in the RAG architecture.
- retriever (RagRetriever) — A retriever class encapsulating a faiss index queried to obtain context documents for current inputs.
The RagModel forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
RAG is a seq2seq model which encapsulates two core components: a question encoder and a generator. During a forward pass, we encode the input with the question encoder and pass it to the retriever to extract relevant context documents. The documents are then prepended to the input. Such contextualized inputs is passed to the generator.
The question encoder can be any autoencoding model, preferably DPRQuestionEncoder, and the generator can be any seq2seq model, preferably BartForConditionalGeneration.
The model can be initialized with a RagRetriever for end-to-end generation or used in combination with the
outputs of a retriever in multiple steps---see examples for more details. The model is compatible any
autoencoding model as the question_encoder and any seq2seq model with language model head as the generator.
It has been tested with DPRQuestionEncoder as the question_encoder and BartForConditionalGeneration or
T5ForConditionalGeneration as the generator.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
attention_mask: typing.Optional[torch.Tensor] = None
encoder_outputs: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None
decoder_input_ids: typing.Optional[torch.LongTensor] = None
decoder_attention_mask: typing.Optional[torch.BoolTensor] = None
past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None
doc_scores: typing.Optional[torch.FloatTensor] = None
context_input_ids: typing.Optional[torch.LongTensor] = None
context_attention_mask = None
use_cache: typing.Optional[bool] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
output_retrieved: typing.Optional[bool] = None
n_docs: typing.Optional[int] = None
)
→
transformers.models.rag.modeling_rag.RetrievAugLMOutput or tuple(torch.FloatTensor)
Parameters
-
input_ids (
torch.LongTensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. RagConfig, used to initialize the model, specifies which generator to use, it also specifies a compatible generator tokenizer. Use that tokenizer class to obtain the indices. -
attention_mask (
torch.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
encoder_outputs (
tuple(tuple(torch.FloatTensor), optional) — Tuple consists of (generator_enc_last_hidden_state, optional:generator_enc_hidden_states, optional:generator_enc_attentions).generator_enc_last_hidden_stateof shape(batch_size, n_docs * sequence_length, hidden_size)is a sequence of hidden-states at the output of the last layer of the generator’s encoder.Used by the (RagModel) model during decoding.
-
decoder_input_ids (
torch.LongTensorof shape(batch_size, target_sequence_length), optional) — Provide for generation tasks.Noneby default, construct as per instructions for the generator model you’re using with your RAG instance. -
decoder_attention_mask (
torch.BoolTensorof shape(batch_size, target_sequence_length), optional) — Default behavior: generate a tensor that ignores pad tokens indecoder_input_ids. Causal mask will also be used by default. -
past_key_values (
tuple(tuple(torch.FloatTensor))) — Tuple consists of two elements:encoder_outputsof the RAG model (seeencoder_outputs) andpast_key_valuesof the underlying generator. Can be used to speed up decoding.past_key_valuesare used in the (RagTokenForGeneration) model during decoding. -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. If the model has is not initialized with aretrieverdoc_scoreshas to be provided to the forward pass.doc_scorescan be computed viaquestion_encoder_last_hidden_stateandretrieved_doc_embeds, see examples for more information. -
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever`context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). context_attention_mask (torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True): Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retrievercontext_attention_maskhas to be provided to the forward pass.context_attention_maskare returned by__call__(). -
use_cache (
bool, optional, defaults toTrue) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). -
output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. -
output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. -
output_retrieved(
bool, optional) — Whether or not to return theretrieved_doc_embeds,retrieved_doc_ids,context_input_idsandcontext_attention_mask. See returned tensors for more detail. -
n_docs (
int, optional, defaults to `config.n_docs“) — Number of documents to retrieve and/or number of documents for which to generate an answer.
Returns
transformers.models.rag.modeling_rag.RetrievAugLMOutput or tuple(torch.FloatTensor)
A transformers.models.rag.modeling_rag.RetrievAugLMOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (RagConfig) and inputs.
-
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head. The score is possibly marginalized over all documents for each vocabulary token. -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. -
past_key_values (
List[torch.FloatTensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftorch.FloatTensorof lengthconfig.n_layers, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)).Contains precomputed hidden-states (key and values in the attention blocks) of the decoder that can be used (see
past_key_valuesinput) to speed up sequential decoding. -
retrieved_doc_embeds (
torch.FloatTensorof shape(batch_size, config.n_docs, hidden_size), optional, returned when output_retrieved=True) — Embedded documents retrieved by the retriever. Is used withquestion_encoder_last_hidden_stateto compute thedoc_scores. -
retrieved_doc_ids (
torch.LongTensorof shape(batch_size, config.n_docs), optional, returned when output_retrieved=True) — The indexes of the embedded documents retrieved by the retriever. -
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input ids post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever. -
question_encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden states at the output of the last layer of the question encoder pooled output of the model. -
question_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the question encoder at the output of each layer plus the initial embedding outputs.
-
question_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the question encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_enc_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the generator encoder of the model. -
generator_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator encoder at the output of each layer plus the initial embedding outputs.
-
generator_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_dec_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator decoder at the output of each layer plus the initial embedding outputs.
-
generator_dec_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_cross_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Cross-attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the cross-attention heads.
The RagModel forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import RagTokenizer, RagRetriever, RagModel
>>> import torch
>>> tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-base")
>>> retriever = RagRetriever.from_pretrained(
... "facebook/rag-token-base", index_name="exact", use_dummy_dataset=True
... )
>>> # initialize with RagRetriever to do everything in one forward call
>>> model = RagModel.from_pretrained("facebook/rag-token-base", retriever=retriever)
>>> inputs = tokenizer("How many people live in Paris?", return_tensors="pt")
>>> outputs = model(input_ids=inputs["input_ids"])RagSequenceForGeneration
class transformers.RagSequenceForGeneration
< source >( config: typing.Optional[transformers.configuration_utils.PretrainedConfig] = None question_encoder: typing.Optional[transformers.modeling_utils.PreTrainedModel] = None generator: typing.Optional[transformers.modeling_utils.PreTrainedModel] = None retriever: typing.Optional[transformers.models.rag.retrieval_rag.RagRetriever] = None **kwargs )
Parameters
- config (RagConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
-
question_encoder (PreTrainedModel) —
An encoder model compatible with the faiss index encapsulated by the
retriever. - generator (PreTrainedModel) — A seq2seq model used as the generator in the RAG architecture.
- retriever (RagRetriever) — A retriever class encapsulating a faiss index queried to obtain context documents for current inputs.
The RagSequenceForGeneration forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
A RAG-sequence model implementation. It performs RAG-sequence specific marginalization in the forward pass.
RAG is a seq2seq model which encapsulates two core components: a question encoder and a generator. During a forward pass, we encode the input with the question encoder and pass it to the retriever to extract relevant context documents. The documents are then prepended to the input. Such contextualized inputs is passed to the generator.
The question encoder can be any autoencoding model, preferably DPRQuestionEncoder, and the generator can be any seq2seq model, preferably BartForConditionalGeneration.
The model can be initialized with a RagRetriever for end-to-end generation or used in combination with the
outputs of a retriever in multiple steps---see examples for more details. The model is compatible any
autoencoding model as the question_encoder and any seq2seq model with language model head as the generator.
It has been tested with DPRQuestionEncoder as the question_encoder and BartForConditionalGeneration or
T5ForConditionalGeneration as the generator.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
attention_mask: typing.Optional[torch.Tensor] = None
encoder_outputs: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None
decoder_input_ids: typing.Optional[torch.LongTensor] = None
decoder_attention_mask: typing.Optional[torch.BoolTensor] = None
past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None
context_input_ids: typing.Optional[torch.LongTensor] = None
context_attention_mask: typing.Optional[torch.LongTensor] = None
doc_scores: typing.Optional[torch.FloatTensor] = None
use_cache: typing.Optional[bool] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
output_retrieved: typing.Optional[bool] = None
exclude_bos_score: typing.Optional[bool] = None
reduce_loss: typing.Optional[bool] = None
labels: typing.Optional[torch.LongTensor] = None
n_docs: typing.Optional[int] = None
**kwargs
)
→
transformers.models.rag.modeling_rag.RetrievAugLMMarginOutput or tuple(torch.FloatTensor)
Parameters
-
input_ids (
torch.LongTensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. RagConfig, used to initialize the model, specifies which generator to use, it also specifies a compatible generator tokenizer. Use that tokenizer class to obtain the indices. -
attention_mask (
torch.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
encoder_outputs (
tuple(tuple(torch.FloatTensor), optional) — Tuple consists of (generator_enc_last_hidden_state, optional:generator_enc_hidden_states, optional:generator_enc_attentions).generator_enc_last_hidden_stateof shape(batch_size, n_docs * sequence_length, hidden_size)is a sequence of hidden-states at the output of the last layer of the generator’s encoder.Used by the (RagModel) model during decoding.
-
decoder_input_ids (
torch.LongTensorof shape(batch_size, target_sequence_length), optional) — Provide for generation tasks.Noneby default, construct as per instructions for the generator model you’re using with your RAG instance. -
decoder_attention_mask (
torch.BoolTensorof shape(batch_size, target_sequence_length), optional) — Default behavior: generate a tensor that ignores pad tokens indecoder_input_ids. Causal mask will also be used by default. -
past_key_values (
tuple(tuple(torch.FloatTensor))) — Tuple consists of two elements:encoder_outputsof the RAG model (seeencoder_outputs) andpast_key_valuesof the underlying generator. Can be used to speed up decoding.past_key_valuesare used in the (RagTokenForGeneration) model during decoding. -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. If the model has is not initialized with aretrieverdoc_scoreshas to be provided to the forward pass.doc_scorescan be computed viaquestion_encoder_last_hidden_stateandretrieved_doc_embeds, see examples for more information. -
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever`context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). context_attention_mask (torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True): Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retrievercontext_attention_maskhas to be provided to the forward pass.context_attention_maskare returned by__call__(). -
use_cache (
bool, optional, defaults toTrue) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). -
output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. -
output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. -
output_retrieved(
bool, optional) — Whether or not to return theretrieved_doc_embeds,retrieved_doc_ids,context_input_idsandcontext_attention_mask. See returned tensors for more detail. -
n_docs (
int, optional, defaults to `config.n_docs“) — Number of documents to retrieve and/or number of documents for which to generate an answer. -
exclude_bos_score (
bool, optional) — Only relevant iflabelsis passed. IfTrue, the score of the BOS token is disregarded when computing the loss. -
reduce_loss (
bool, optional) — Only relevant iflabelsis passed. IfTrue, the NLL loss is reduced using thetorch.Tensor.sumoperation. -
kwargs (
Dict[str, any], optional, defaults to {}) — Legacy dictionary, which is required so that model can use generate() function.
Returns
transformers.models.rag.modeling_rag.RetrievAugLMMarginOutput or tuple(torch.FloatTensor)
A transformers.models.rag.modeling_rag.RetrievAugLMMarginOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (RagConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. -
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head. The score is possibly marginalized over all documents for each vocabulary token. -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. -
past_key_values (
List[torch.FloatTensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftorch.FloatTensorof lengthconfig.n_layers, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)).Contains precomputed hidden-states (key and values in the attention blocks) of the decoder that can be used (see
past_key_valuesinput) to speed up sequential decoding. -
retrieved_doc_embeds (
torch.FloatTensorof shape(batch_size, config.n_docs, hidden_size), optional, returned when output_retrieved=True) — Embedded documents retrieved by the retriever. Is used withquestion_encoder_last_hidden_stateto compute thedoc_scores. -
retrieved_doc_ids (
torch.LongTensorof shape(batch_size, config.n_docs), optional, returned when output_retrieved=True) — The indexes of the embedded documents retrieved by the retriever. -
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input ids post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever. -
question_encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden states at the output of the last layer of the question encoder pooled output of the model. -
question_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the question encoder at the output of each layer plus the initial embedding outputs.
-
question_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the question encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_enc_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the generator encoder of the model. -
generator_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator encoder at the output of each layer plus the initial embedding outputs.
-
generator_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_dec_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator decoder at the output of each layer plus the initial embedding outputs.
-
generator_dec_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_cross_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Cross-attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the cross-attention heads.
The RagSequenceForGeneration forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
>>> import torch
>>> tokenizer = RagTokenizer.from_pretrained("facebook/rag-sequence-nq")
>>> retriever = RagRetriever.from_pretrained(
... "facebook/rag-sequence-nq", index_name="exact", use_dummy_dataset=True
... )
>>> # initialize with RagRetriever to do everything in one forward call
>>> model = RagSequenceForGeneration.from_pretrained("facebook/rag-token-nq", retriever=retriever)
>>> inputs = tokenizer("How many people live in Paris?", return_tensors="pt")
>>> targets = tokenizer(text_target="In Paris, there are 10 million people.", return_tensors="pt")
>>> input_ids = inputs["input_ids"]
>>> labels = targets["input_ids"]
>>> outputs = model(input_ids=input_ids, labels=labels)
>>> # or use retriever separately
>>> model = RagSequenceForGeneration.from_pretrained("facebook/rag-sequence-nq", use_dummy_dataset=True)
>>> # 1. Encode
>>> question_hidden_states = model.question_encoder(input_ids)[0]
>>> # 2. Retrieve
>>> docs_dict = retriever(input_ids.numpy(), question_hidden_states.detach().numpy(), return_tensors="pt")
>>> doc_scores = torch.bmm(
... question_hidden_states.unsqueeze(1), docs_dict["retrieved_doc_embeds"].float().transpose(1, 2)
... ).squeeze(1)
>>> # 3. Forward to generator
>>> outputs = model(
... context_input_ids=docs_dict["context_input_ids"],
... context_attention_mask=docs_dict["context_attention_mask"],
... doc_scores=doc_scores,
... decoder_input_ids=labels,
... )generate
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
attention_mask: typing.Optional[torch.LongTensor] = None
context_input_ids: typing.Optional[torch.LongTensor] = None
context_attention_mask: typing.Optional[torch.LongTensor] = None
doc_scores: typing.Optional[torch.FloatTensor] = None
do_deduplication: typing.Optional[bool] = None
num_return_sequences: typing.Optional[int] = None
num_beams: typing.Optional[int] = None
n_docs: typing.Optional[int] = None
**model_kwargs
)
→
torch.LongTensor of shape (batch_size * num_return_sequences, sequence_length)
Parameters
-
input_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — The sequence used as a prompt for the generation. Ifinput_idsis not passed, thencontext_input_idshas to be provided. -
attention_mask (
torch.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model is not initialized with a
retrieverorinput_idsis not given,context_input_idsandcontext_attention_maskhave to be provided to the forward pass. They are returned by__call__(). -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state.If the model is not initialized with a
retrieverorinput_idsis not given,doc_scoreshas to be provided to the forward pass.doc_scoresare returned by__call__(). -
do_deduplication (
bool, optional) — Whether or not to deduplicate the generations from different context documents for a given input. Has to be set toFalseif used while training with distributed backend. -
num_return_sequences(
int, optional, defaults to 1) — The number of independently computed returned sequences for each element in the batch. Note that this is not the value we pass to thegenerator’s[generate()](/docs/transformers/v4.22.1/en/main_classes/text_generation#transformers.generation_utils.GenerationMixin.generate)function, where we setnum_return_sequencestonum_beams. -
num_beams (
int, optional, defaults to 1) — Number of beams for beam search. 1 means no beam search. -
n_docs (
int, optional, defaults toconfig.n_docs) — Number of documents to retrieve and/or number of documents for which to generate an answer. kwargs — Additional kwargs will be passed to generate().
Returns
torch.LongTensor of shape (batch_size * num_return_sequences, sequence_length)
The generated
sequences. The second dimension (sequence length) is either equal to max_length or shorter if all batches
finished early due to the eos_token_id.
Implements RAG sequence “thorough” decoding. Read the generate()` documentation for more information on how to set other generate input parameters.
RagTokenForGeneration
class transformers.RagTokenForGeneration
< source >( config: typing.Optional[transformers.configuration_utils.PretrainedConfig] = None question_encoder: typing.Optional[transformers.modeling_utils.PreTrainedModel] = None generator: typing.Optional[transformers.modeling_utils.PreTrainedModel] = None retriever: typing.Optional[transformers.models.rag.retrieval_rag.RagRetriever] = None **kwargs )
Parameters
- config (RagConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
-
question_encoder (PreTrainedModel) —
An encoder model compatible with the faiss index encapsulated by the
retriever. - generator (PreTrainedModel) — A seq2seq model used as the generator in the RAG architecture.
- retriever (RagRetriever) — A retriever class encapsulating a faiss index queried to obtain context documents for current inputs.
The RagTokenForGeneration forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
A RAG-token model implementation. It performs RAG-token specific marginalization in the forward pass.
RAG is a seq2seq model which encapsulates two core components: a question encoder and a generator. During a forward pass, we encode the input with the question encoder and pass it to the retriever to extract relevant context documents. The documents are then prepended to the input. Such contextualized inputs is passed to the generator.
The question encoder can be any autoencoding model, preferably DPRQuestionEncoder, and the generator can be any seq2seq model, preferably BartForConditionalGeneration.
The model can be initialized with a RagRetriever for end-to-end generation or used in combination with the
outputs of a retriever in multiple steps---see examples for more details. The model is compatible any
autoencoding model as the question_encoder and any seq2seq model with language model head as the generator.
It has been tested with DPRQuestionEncoder as the question_encoder and BartForConditionalGeneration or
T5ForConditionalGeneration as the generator.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
attention_mask: typing.Optional[torch.FloatTensor] = None
encoder_outputs: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None
decoder_input_ids: typing.Optional[torch.LongTensor] = None
decoder_attention_mask: typing.Optional[torch.BoolTensor] = None
past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None
context_input_ids: typing.Optional[torch.LongTensor] = None
context_attention_mask: typing.Optional[torch.LongTensor] = None
doc_scores: typing.Optional[torch.FloatTensor] = None
use_cache: typing.Optional[bool] = None
output_attentions: typing.Optional[bool] = None
output_hidden_states: typing.Optional[bool] = None
output_retrieved: typing.Optional[bool] = None
do_marginalize: typing.Optional[bool] = None
reduce_loss: typing.Optional[bool] = None
labels: typing.Optional[torch.LongTensor] = None
n_docs: typing.Optional[int] = None
**kwargs
)
→
transformers.models.rag.modeling_rag.RetrievAugLMMarginOutput or tuple(torch.FloatTensor)
Parameters
-
input_ids (
torch.LongTensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. RagConfig, used to initialize the model, specifies which generator to use, it also specifies a compatible generator tokenizer. Use that tokenizer class to obtain the indices. -
attention_mask (
torch.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
encoder_outputs (
tuple(tuple(torch.FloatTensor), optional) — Tuple consists of (generator_enc_last_hidden_state, optional:generator_enc_hidden_states, optional:generator_enc_attentions).generator_enc_last_hidden_stateof shape(batch_size, n_docs * sequence_length, hidden_size)is a sequence of hidden-states at the output of the last layer of the generator’s encoder.Used by the (RagModel) model during decoding.
-
decoder_input_ids (
torch.LongTensorof shape(batch_size, target_sequence_length), optional) — Provide for generation tasks.Noneby default, construct as per instructions for the generator model you’re using with your RAG instance. -
decoder_attention_mask (
torch.BoolTensorof shape(batch_size, target_sequence_length), optional) — Default behavior: generate a tensor that ignores pad tokens indecoder_input_ids. Causal mask will also be used by default. -
past_key_values (
tuple(tuple(torch.FloatTensor))) — Tuple consists of two elements:encoder_outputsof the RAG model (seeencoder_outputs) andpast_key_valuesof the underlying generator. Can be used to speed up decoding.past_key_valuesare used in the (RagTokenForGeneration) model during decoding. -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. If the model has is not initialized with aretrieverdoc_scoreshas to be provided to the forward pass.doc_scorescan be computed viaquestion_encoder_last_hidden_stateandretrieved_doc_embeds, see examples for more information. -
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever`context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). context_attention_mask (torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True): Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retrievercontext_attention_maskhas to be provided to the forward pass.context_attention_maskare returned by__call__(). -
use_cache (
bool, optional, defaults toTrue) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). -
output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. -
output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. -
output_retrieved(
bool, optional) — Whether or not to return theretrieved_doc_embeds,retrieved_doc_ids,context_input_idsandcontext_attention_mask. See returned tensors for more detail. -
n_docs (
int, optional, defaults to `config.n_docs“) — Number of documents to retrieve and/or number of documents for which to generate an answer. -
do_marginalize (
bool, optional) — IfTrue, the logits are marginalized over all documents by making use oftorch.nn.functional.log_softmax. -
reduce_loss (
bool, optional) — Only relevant iflabelsis passed. IfTrue, the NLL loss is reduced using thetorch.Tensor.sumoperation. -
kwargs (
Dict[str, any], optional, defaults to {}) — Legacy dictionary, which is required so that model can use generate() function.
Returns
transformers.models.rag.modeling_rag.RetrievAugLMMarginOutput or tuple(torch.FloatTensor)
A transformers.models.rag.modeling_rag.RetrievAugLMMarginOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (RagConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. -
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head. The score is possibly marginalized over all documents for each vocabulary token. -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. -
past_key_values (
List[torch.FloatTensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftorch.FloatTensorof lengthconfig.n_layers, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)).Contains precomputed hidden-states (key and values in the attention blocks) of the decoder that can be used (see
past_key_valuesinput) to speed up sequential decoding. -
retrieved_doc_embeds (
torch.FloatTensorof shape(batch_size, config.n_docs, hidden_size), optional, returned when output_retrieved=True) — Embedded documents retrieved by the retriever. Is used withquestion_encoder_last_hidden_stateto compute thedoc_scores. -
retrieved_doc_ids (
torch.LongTensorof shape(batch_size, config.n_docs), optional, returned when output_retrieved=True) — The indexes of the embedded documents retrieved by the retriever. -
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input ids post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever. -
question_encoder_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden states at the output of the last layer of the question encoder pooled output of the model. -
question_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the question encoder at the output of each layer plus the initial embedding outputs.
-
question_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the question encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_enc_last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the generator encoder of the model. -
generator_enc_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator encoder at the output of each layer plus the initial embedding outputs.
-
generator_enc_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_dec_hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator decoder at the output of each layer plus the initial embedding outputs.
-
generator_dec_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_cross_attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Cross-attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the cross-attention heads.
The RagTokenForGeneration forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import RagTokenizer, RagRetriever, RagTokenForGeneration
>>> import torch
>>> tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq")
>>> retriever = RagRetriever.from_pretrained(
... "facebook/rag-token-nq", index_name="exact", use_dummy_dataset=True
... )
>>> # initialize with RagRetriever to do everything in one forward call
>>> model = RagTokenForGeneration.from_pretrained("facebook/rag-token-nq", retriever=retriever)
>>> inputs = tokenizer("How many people live in Paris?", return_tensors="pt")
>>> targets = tokenizer(text_target="In Paris, there are 10 million people.", return_tensors="pt")
>>> input_ids = inputs["input_ids"]
>>> labels = targets["input_ids"]
>>> outputs = model(input_ids=input_ids, labels=labels)
>>> # or use retriever separately
>>> model = RagTokenForGeneration.from_pretrained("facebook/rag-token-nq", use_dummy_dataset=True)
>>> # 1. Encode
>>> question_hidden_states = model.question_encoder(input_ids)[0]
>>> # 2. Retrieve
>>> docs_dict = retriever(input_ids.numpy(), question_hidden_states.detach().numpy(), return_tensors="pt")
>>> doc_scores = torch.bmm(
... question_hidden_states.unsqueeze(1), docs_dict["retrieved_doc_embeds"].float().transpose(1, 2)
... ).squeeze(1)
>>> # 3. Forward to generator
>>> outputs = model(
... context_input_ids=docs_dict["context_input_ids"],
... context_attention_mask=docs_dict["context_attention_mask"],
... doc_scores=doc_scores,
... decoder_input_ids=labels,
... )
>>> # or directly generate
>>> generated = model.generate(
... context_input_ids=docs_dict["context_input_ids"],
... context_attention_mask=docs_dict["context_attention_mask"],
... doc_scores=doc_scores,
... )
>>> generated_string = tokenizer.batch_decode(generated, skip_special_tokens=True)generate
< source >(
input_ids: typing.Optional[torch.LongTensor] = None
attention_mask: typing.Optional[torch.LongTensor] = None
context_input_ids: typing.Optional[torch.LongTensor] = None
context_attention_mask: typing.Optional[torch.LongTensor] = None
doc_scores: typing.Optional[torch.FloatTensor] = None
max_length: typing.Optional[int] = None
min_length: typing.Optional[int] = None
early_stopping: typing.Optional[bool] = None
use_cache: typing.Optional[bool] = None
num_beams: typing.Optional[int] = None
num_beam_groups: typing.Optional[int] = None
diversity_penalty: typing.Optional[float] = None
bos_token_id: typing.Optional[int] = None
pad_token_id: typing.Optional[int] = None
eos_token_id: typing.Optional[int] = None
length_penalty: typing.Optional[float] = None
no_repeat_ngram_size: typing.Optional[int] = None
encoder_no_repeat_ngram_size: typing.Optional[int] = None
repetition_penalty: typing.Optional[float] = None
bad_words_ids: typing.Optional[typing.List[typing.List[int]]] = None
num_return_sequences: typing.Optional[int] = None
decoder_start_token_id: typing.Optional[int] = None
n_docs: typing.Optional[int] = None
prefix_allowed_tokens_fn: typing.Callable[[int, torch.Tensor], typing.List[int]] = None
logits_processor: typing.Optional[transformers.generation_logits_process.LogitsProcessorList] = []
renormalize_logits: typing.Optional[bool] = None
stopping_criteria: typing.Optional[transformers.generation_stopping_criteria.StoppingCriteriaList] = []
forced_bos_token_id: typing.Optional[int] = None
forced_eos_token_id: typing.Optional[int] = None
remove_invalid_values: typing.Optional[bool] = None
exponential_decay_length_penalty: typing.Union[typing.Tuple[typing.Union[int, float]], NoneType] = None
**model_kwargs
)
→
torch.LongTensor of shape (batch_size * num_return_sequences, sequence_length)
Parameters
-
input_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — The sequence used as a prompt for the generation. Ifinput_idsis not passed, thencontext_input_idshas to be provided. -
attention_mask (
torch.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
context_input_ids (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever,context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). -
context_attention_mask (
torch.LongTensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever,context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). -
doc_scores (
torch.FloatTensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state.If the model has is not initialized with a
retriever,context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). -
max_length (
int, optional, defaults to 20) — The maximum length of the sequence to be generated. -
min_length (
int, optional, defaults to 10) — The minimum length of the sequence to be generated. -
early_stopping (
bool, optional, defaults toFalse) — Whether or not to stop the beam search when at leastnum_beamssentences are finished per batch or not. use_cache — (bool, optional, defaults toTrue): Whether or not the model should use the past last key/values attentions (if applicable to the model) to speed up decoding. -
pad_token_id (
int, optional) — The id of the padding token. -
bos_token_id (
int, optional) — The id of the beginning-of-sequence token. -
eos_token_id (
int, optional) — The id of the end-of-sequence token. -
length_penalty (
float, optional, defaults to 1.0) — Exponential penalty to the length. 1.0 means no penalty.Set to values < 1.0 in order to encourage the model to generate shorter sequences, to a value > 1.0 in order to encourage the model to produce longer sequences.
-
no_repeat_ngram_size (
int, optional, defaults to 0) — If set to int > 0, all ngrams of that size can only occur once. -
encoder_no_repeat_ngram_size (
int, optional, defaults to 0) — If set to int > 0, all ngrams of that size that occur in theencoder_input_idscannot occur in thedecoder_input_ids. -
bad_words_ids(
List[int], optional) — List of token ids that are not allowed to be generated. In order to get the tokens of the words that should not appear in the generated text, usetokenizer.encode(bad_word, add_prefix_space=True). -
num_beams (
int, optional, defaults to 1) — Number of beams for beam search. 1 means no beam search. -
num_beam_groups (
int, optional, defaults to 1) — Number of groups to dividenum_beamsinto in order to ensure diversity among different groups of beams. this paper for more details. -
diversity_penalty (
float, optional, defaults to 0.0) — This value is subtracted from a beam’s score if it generates a token same as any beam from other group at a particular time. Note thatdiversity_penaltyis only effective ifgroup beam searchis enabled. -
num_return_sequences(
int, optional, defaults to 1) — The number of independently computed returned sequences for each element in the batch. Note that this is not the value we pass to thegenerator’s[generate()](/docs/transformers/v4.22.1/en/main_classes/text_generation#transformers.generation_utils.GenerationMixin.generate) function, where we setnum_return_sequencestonum_beams. decoder_start_token_id (int`, optional): If an encoder-decoder model starts decoding with a different token than bos, the id of that token. -
n_docs (
int, optional, defaults toconfig.n_docs) — Number of documents to retrieve and/or number of documents for which to generate an answer. prefix_allowed_tokens_fn — (Callable[[int, torch.Tensor], List[int]], optional): If provided, this function constraints the beam search to allowed tokens only at each step. If not provided no constraint is applied. This function takes 2 argumentsinputs_idsand the batch IDbatch_id. It has to return a list with the allowed tokens for the next generation step conditioned on the previously generated tokensinputs_idsand the batch IDbatch_id. This argument is useful for constrained generation conditioned on the prefix, as described in Autoregressive Entity Retrieval. -
logits_processor (
LogitsProcessorList, optional) — Custom logits processors that complement the default logits processors built from arguments and a model’s config. If a logit processor is passed that is already created with the arguments or a model’s config an error is thrown. -
stopping_criteria (
StoppingCriteriaList, optional) — Custom stopping criteria that complement the default stopping criteria built from arguments and a model’s config. If a stopping criteria is passed that is already created with the arguments or a model’s config an error is thrown. -
forced_bos_token_id (
int, optional) — The id of the token to force as the first generated token after thedecoder_start_token_id. Useful for multilingual models like mBART where the first generated token needs to be the target language token. -
forced_eos_token_id (
int, optional) — The id of the token to force as the last generated token whenmax_lengthis reached. -
remove_invalid_values (
bool, optional) — Whether to remove possible nan and inf outputs of the model to prevent the generation method to crash. Note that usingremove_invalid_valuescan slow down generation.
Returns
torch.LongTensor of shape (batch_size * num_return_sequences, sequence_length)
The generated
sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches
finished early due to the eos_token_id.
Implements RAG token decoding.
TFRagModel
class transformers.TFRagModel
< source >( *args **kwargs )
Parameters
- config (RagConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
-
question_encoder (TFPreTrainedModel) —
An encoder model compatible with the faiss index encapsulated by the
retriever. - generator (TFPreTrainedModel) — A seq2seq model used as the generator in the RAG architecture.
- retriever (RagRetriever) — A retriever class encapsulating a faiss index queried to obtain context documents for current inputs.
The TFRagModel forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
RAG is a sequence-to-sequence model which encapsulates two core components: a question encoder and a generator. During a forward pass, we encode the input with the question encoder and pass it to the retriever to extract relevant context documents. The documents are then prepended to the input. Such contextualized inputs is passed to the generator.
The question encoder can be any autoencoding model, preferably TFDPRQuestionEncoder, and the generator can be any seq2seq model, preferably TFBartForConditionalGeneration.
The model can be initialized with a RagRetriever for end-to-end generation or used in combination with the
outputs of a retriever in multiple steps---see examples for more details. The model is compatible any
autoencoding model as the question_encoder and any seq2seq model with language model head as the generator.
It has been tested with TFDPRQuestionEncoder as the question_encoder and TFBartForConditionalGeneration
as the generator.
This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a Tensorflow tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
The model is in a developing state as it is now fully supports in eager-mode only, and may not be exported in SavedModel format.
call
< source >(
input_ids = None
attention_mask = None
encoder_outputs = None
decoder_input_ids = None
decoder_attention_mask = None
past_key_values = None
doc_scores = None
context_input_ids = None
context_attention_mask = None
use_cache = None
output_attentions = None
output_hidden_states = None
output_retrieved = None
n_docs = None
return_dict = None
training = False
**kwargs
)
→
transformers.models.rag.modeling_tf_rag.TFRetrievAugLMOutput or tuple(tf.Tensor)
Parameters
-
input_ids (
tf.Tensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. RagConfig, used to initialize the model, specifies which generator to use, it also specifies a compatible generator tokenizer. Use that tokenizer class to obtain the indices. -
attention_mask (
tf.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
encoder_outputs (
tuple(tuple(tf.Tensor), optional) — Tuple consists of (generator_enc_last_hidden_state, optional:generator_enc_hidden_states, optional:generator_enc_attentions).generator_enc_last_hidden_stateof shape(batch_size, n_docs * sequence_length, hidden_size)is a sequence of hidden-states at the output of the last layer of the generator’s encoder.Used by the (TFRagModel) model during decoding.
-
decoder_input_ids (
tf.Tensorof shape(batch_size, target_sequence_length), optional) — Provide for generation tasks.Noneby default, construct as per instructions for the generator model you’re using with your RAG instance. -
decoder_attention_mask (
torch.BoolTensorof shape(batch_size, target_sequence_length), optional) — Default behavior: generate a tensor that ignores pad tokens indecoder_input_ids. Causal mask will also be used by default. -
past_key_values (
tuple(tuple(tf.Tensor))) — Tuple consists of two elements:encoder_outputsof the RAG model (seeencoder_outputs) andpast_key_valuesof the underlying generator. Can be used to speed up decoding.past_key_valuesare used in the (RagTokenForGeneration) model during decoding. -
doc_scores (
tf.Tensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. If the model has is not initialized with aretrieverdoc_scoreshas to be provided to the forward pass.doc_scorescan be computed viaquestion_encoder_last_hidden_stateandretrieved_doc_embeds, see examples for more information. -
context_input_ids (
tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever`context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). context_attention_mask (tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True): Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retrievercontext_attention_maskhas to be provided to the forward pass.context_attention_maskare returned by__call__(). -
use_cache (
bool, optional, defaults toTrue) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). -
output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. -
output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. -
output_retrieved(
bool, optional) — Whether or not to return theretrieved_doc_embeds,retrieved_doc_ids,context_input_idsandcontext_attention_mask. See returned tensors for more detail. -
return_dict (
bool, optional) — Whether or not to return aTFRetrievAugLMOutputinstead of a plain tuple. -
n_docs (
int, optional, defaults to `config.n_docs“) — Number of documents to retrieve and/or number of documents for which to generate an answer.
Returns
transformers.models.rag.modeling_tf_rag.TFRetrievAugLMOutput or tuple(tf.Tensor)
A transformers.models.rag.modeling_tf_rag.TFRetrievAugLMOutput or a tuple of tf.Tensor (if
return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the
configuration (RagConfig) and inputs.
-
logits (
tf.Tensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head. The score is possibly marginalized over all documents for each vocabulary token. -
past_key_values (
List[tf.Tensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftf.Tensorof lengthconfig.n_layers, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)).Contains precomputed hidden-states (key and values in the attention blocks) of the decoder that can be used (see
past_key_valuesinput) to speed up sequential decoding. -
doc_scores (
tf.Tensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. -
retrieved_doc_embeds (
tf.Tensorof shape(batch_size, config.n_docs, hidden_size), optional, returned when output_retrieved=True) — Embedded documents retrieved by the retriever. Is used withquestion_encoder_last_hidden_stateto compute thedoc_scores. -
retrieved_doc_ids (
tf.Tensorof shape(batch_size, config.n_docs), optional, returned when output_retrieved=True) — The indexes of the embedded documents retrieved by the retriever. -
context_input_ids (
tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input ids post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever. -
question_encoder_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden states at the output of the last layer of the question encoder pooled output of the model. -
question_enc_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the question encoder at the output of each layer plus the initial embedding outputs.
-
question_enc_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the question encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_enc_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the generator encoder of the model. -
generator_enc_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator encoder at the output of each layer plus the initial embedding outputs.
-
generator_enc_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_dec_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator decoder at the output of each layer plus the initial embedding outputs.
-
generator_dec_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
The TFRagModel forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import RagTokenizer, RagRetriever, TFRagModel
>>> import torch
>>> tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-base")
>>> retriever = RagRetriever.from_pretrained(
... "facebook/rag-token-base", index_name="exact", use_dummy_dataset=True
... )
>>> # initialize with RagRetriever to do everything in one forward call
>>> model = TFRagModel.from_pretrained("facebook/rag-token-base", retriever=retriever, from_pt=True)
>>> input_dict = tokenizer.prepare_seq2seq_batch(
... "How many people live in Paris?", "In Paris, there are 10 million people.", return_tensors="tf"
... )
>>> input_ids = input_dict["input_ids"]
>>> outputs = model(input_ids)TFRagSequenceForGeneration
class transformers.TFRagSequenceForGeneration
< source >( *args **kwargs )
Parameters
- config (RagConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
-
question_encoder (TFPreTrainedModel) —
An encoder model compatible with the faiss index encapsulated by the
retriever. - generator (TFPreTrainedModel) — A seq2seq model used as the generator in the RAG architecture.
- retriever (RagRetriever) — A retriever class encapsulating a faiss index queried to obtain context documents for current inputs.
The TFRagSequenceForGeneration forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
A TF RAG-sequence model implementation. It performs RAG-sequence specific marginalization in the forward pass.
RAG is a sequence-to-sequence model which encapsulates two core components: a question encoder and a generator. During a forward pass, we encode the input with the question encoder and pass it to the retriever to extract relevant context documents. The documents are then prepended to the input. Such contextualized inputs is passed to the generator.
The question encoder can be any autoencoding model, preferably TFDPRQuestionEncoder, and the generator can be any seq2seq model, preferably TFBartForConditionalGeneration.
The model can be initialized with a RagRetriever for end-to-end generation or used in combination with the
outputs of a retriever in multiple steps---see examples for more details. The model is compatible any
autoencoding model as the question_encoder and any seq2seq model with language model head as the generator.
It has been tested with TFDPRQuestionEncoder as the question_encoder and TFBartForConditionalGeneration
as the generator.
This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a Tensorflow tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
The model is in a developing state as it is now fully supports in eager-mode only, and may not be exported in SavedModel format.
call
< source >(
input_ids = None
attention_mask = None
decoder_input_ids = None
decoder_attention_mask = None
encoder_outputs = None
past_key_values = None
doc_scores = None
context_input_ids = None
context_attention_mask = None
use_cache = None
output_attentions = None
output_hidden_states = None
output_retrieved = None
n_docs = None
exclude_bos_score = None
labels = None
reduce_loss = None
return_dict = None
training = False
**kwargs
)
→
transformers.models.rag.modeling_tf_rag.TFRetrievAugLMMarginOutput or tuple(tf.Tensor)
Parameters
-
input_ids (
tf.Tensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. RagConfig, used to initialize the model, specifies which generator to use, it also specifies a compatible generator tokenizer. Use that tokenizer class to obtain the indices. -
attention_mask (
tf.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
encoder_outputs (
tuple(tuple(tf.Tensor), optional) — Tuple consists of (generator_enc_last_hidden_state, optional:generator_enc_hidden_states, optional:generator_enc_attentions).generator_enc_last_hidden_stateof shape(batch_size, n_docs * sequence_length, hidden_size)is a sequence of hidden-states at the output of the last layer of the generator’s encoder.Used by the (TFRagModel) model during decoding.
-
decoder_input_ids (
tf.Tensorof shape(batch_size, target_sequence_length), optional) — Provide for generation tasks.Noneby default, construct as per instructions for the generator model you’re using with your RAG instance. -
decoder_attention_mask (
torch.BoolTensorof shape(batch_size, target_sequence_length), optional) — Default behavior: generate a tensor that ignores pad tokens indecoder_input_ids. Causal mask will also be used by default. -
past_key_values (
tuple(tuple(tf.Tensor))) — Tuple consists of two elements:encoder_outputsof the RAG model (seeencoder_outputs) andpast_key_valuesof the underlying generator. Can be used to speed up decoding.past_key_valuesare used in the (RagTokenForGeneration) model during decoding. -
doc_scores (
tf.Tensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. If the model has is not initialized with aretrieverdoc_scoreshas to be provided to the forward pass.doc_scorescan be computed viaquestion_encoder_last_hidden_stateandretrieved_doc_embeds, see examples for more information. -
context_input_ids (
tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever`context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). context_attention_mask (tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True): Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retrievercontext_attention_maskhas to be provided to the forward pass.context_attention_maskare returned by__call__(). -
use_cache (
bool, optional, defaults toTrue) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). -
output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. -
output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. -
output_retrieved(
bool, optional) — Whether or not to return theretrieved_doc_embeds,retrieved_doc_ids,context_input_idsandcontext_attention_mask. See returned tensors for more detail. -
return_dict (
bool, optional) — Whether or not to return aTFRetrievAugLMOutputinstead of a plain tuple. -
n_docs (
int, optional, defaults to `config.n_docs“) — Number of documents to retrieve and/or number of documents for which to generate an answer. -
exclude_bos_score (
bool, optional) — Only relevant iflabelsis passed. IfTrue, the score of the BOS token is disregarded when computing the loss. -
labels (
tf.Tensorornp.ndarrayof shape(batch_size, sequence_length), optional) — Labels for computing the cross entropy classification loss according to Rag-Sequence model formulation See https://arxiv.org/pdf/2005.11401.pdf Section 2.1 for details about Rag-Sequence formulation. Indices should be in[0, ..., config.vocab_size - 1]. -
reduce_loss (
bool, optional) — Only relevant iflabelsis passed. IfTrue, the NLL loss is reduced using thetf.Tensor.sumoperation. -
kwargs (
Dict[str, any], optional, defaults to {}) — Legacy dictionary, which is required so that model can use generate() function.
Returns
transformers.models.rag.modeling_tf_rag.TFRetrievAugLMMarginOutput or tuple(tf.Tensor)
A transformers.models.rag.modeling_tf_rag.TFRetrievAugLMMarginOutput or a tuple of tf.Tensor (if
return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the
configuration (RagConfig) and inputs.
-
loss (
tf.Tensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. -
logits (
tf.Tensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head. The score is possibly marginalized over all documents for each vocabulary token. -
past_key_values (
List[tf.Tensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftf.Tensorof lengthconfig.n_layers, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)).Contains precomputed hidden-states (key and values in the attention blocks) of the decoder that can be used (see
past_key_valuesinput) to speed up sequential decoding. -
doc_scores (
tf.Tensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. -
retrieved_doc_embeds (
tf.Tensorof shape(batch_size, config.n_docs, hidden_size), optional, returned when output_retrieved=True) — Embedded documents retrieved by the retriever. Is used withquestion_encoder_last_hidden_stateto compute thedoc_scores. -
retrieved_doc_ids (
tf.Tensor(int32) of shape(batch_size, config.n_docs), optional, returned when output_retrieved=True) — The indexes of the embedded documents retrieved by the retriever. -
context_input_ids (
tf.Tensor(int32) of shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input ids post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
tf.Tensor(int32) of shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever. -
question_encoder_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden states at the output of the last layer of the question encoder pooled output of the model. -
question_enc_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the question encoder at the output of each layer plus the initial embedding outputs.
-
question_enc_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the question encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_enc_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the generator encoder of the model. -
generator_enc_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator encoder at the output of each layer plus the initial embedding outputs.
-
generator_enc_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_dec_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator decoder at the output of each layer plus the initial embedding outputs.
-
generator_dec_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
The TFRagSequenceForGeneration forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import RagTokenizer, RagRetriever, TFRagSequenceForGeneration
>>> tokenizer = RagTokenizer.from_pretrained("facebook/rag-sequence-nq")
>>> retriever = RagRetriever.from_pretrained(
... "facebook/rag-sequence-nq", index_name="exact", use_dummy_dataset=True
... )
>>> # initialize with RagRetriever to do everything in one forward call
>>> model = TFRagSequenceForGeneration.from_pretrained(
... "facebook/rag-sequence-nq", retriever=retriever, from_pt=True
... )
>>> input_dict = tokenizer.prepare_seq2seq_batch(
... "How many people live in Paris?", "In Paris, there are 10 million people.", return_tensors="tf"
... )
>>> outputs = model(input_dict, output_retrieved=True)
>>> # or use retriever separately
>>> # 1. Encode
>>> input_ids = input_dict["input_ids"]
>>> question_hidden_states = model.question_encoder(input_ids)[0]
>>> # 2. Retrieve
>>> docs_dict = retriever(input_ids.numpy(), question_hidden_states.numpy(), return_tensors="tf")
>>> doc_scores = tf.squeeze(
... tf.matmul(
... tf.expand_dims(question_hidden_states, axis=1), docs_dict["retrieved_doc_embeds"], transpose_b=True
... ),
... axis=1,
... )
>>> # 3. Forward to generator
>>> outputs = model(
... inputs=None,
... context_input_ids=docs_dict["context_input_ids"],
... context_attention_mask=docs_dict["context_attention_mask"],
... doc_scores=doc_scores,
... decoder_input_ids=input_dict["labels"],
... )
>>> # or directly generate
>>> generated = model.generate(
... context_input_ids=docs_dict["context_input_ids"],
... context_attention_mask=docs_dict["context_attention_mask"],
... doc_scores=doc_scores,
... )
>>> generated_string = tokenizer.batch_decode(generated, skip_special_tokens=True)generate
< source >(
input_ids: typing.Optional[tensorflow.python.framework.ops.Tensor] = None
attention_mask: typing.Optional[tensorflow.python.framework.ops.Tensor] = None
context_input_ids = None
context_attention_mask = None
doc_scores = None
do_deduplication = None
num_return_sequences = None
num_beams = None
n_docs = None
**model_kwargs
)
→
tf.Tensor of shape (batch_size * num_return_sequences, sequence_length)
Parameters
-
input_ids (
tf.Tensorof shape(batch_size, sequence_length), optional) — The sequence used as a prompt for the generation. Ifinput_idsis not passed, thencontext_input_idshas to be provided. -
attention_mask (
tf.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]: - 1 for tokens that are not masked, - 0 for tokens that are masked. What are attention masks? -
context_input_ids (
tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever. If the model has is not initialized with aretrieverorinput_idsis not given,context_input_idsandcontext_attention_maskhave to be provided to the forward pass. They are returned by__call__(). -
doc_scores (
tf.Tensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. If the model has is not initialized with aretrieverorinput_idsis not given,doc_scoreshas to be provided to the forward pass.doc_scoresare returned by__call__(). -
do_deduplication (
bool, optional) — Whether or not to deduplicate the generations from different context documents for a given input. Has to be set toFalseif used while training with distributed backend. -
num_return_sequences(
int, optional, defaults to 1) — The number of independently computed returned sequences for each element in the batch. Note that this is not the value we pass to thegenerator’s[generate()](/docs/transformers/v4.22.1/en/main_classes/text_generation#transformers.generation_utils.GenerationMixin.generate)function, where we setnum_return_sequencestonum_beams. -
num_beams (
int, optional, defaults to 1) — Number of beams for beam search. 1 means no beam search. -
n_docs (
int, optional, defaults toconfig.n_docs) — Number of documents to retrieve and/or number of documents for which to generate an answer. kwargs — Additional kwargs will be passed to generate()
Returns
tf.Tensor of shape (batch_size * num_return_sequences, sequence_length)
The generated sequences. The
second dimension (sequence length) is either equal to max_length or shorter if all batches finished early
due to the eos_token_id.
Implements RAG sequence “thorough” decoding. Read the generate()` documentation for more information on how to set other generate input parameters
TFRagTokenForGeneration
class transformers.TFRagTokenForGeneration
< source >( *args **kwargs )
Parameters
- config (RagConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
-
question_encoder (TFPreTrainedModel) —
An encoder model compatible with the faiss index encapsulated by the
retriever. - generator (TFPreTrainedModel) — A seq2seq model used as the generator in the RAG architecture.
- retriever (RagRetriever) — A retriever class encapsulating a faiss index queried to obtain context documents for current inputs.
The TFRagTokenForGeneration forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
A TF RAG-token model implementation. It performs RAG-token specific marginalization in the forward pass.
RAG is a sequence-to-sequence model which encapsulates two core components: a question encoder and a generator. During a forward pass, we encode the input with the question encoder and pass it to the retriever to extract relevant context documents. The documents are then prepended to the input. Such contextualized inputs is passed to the generator.
The question encoder can be any autoencoding model, preferably TFDPRQuestionEncoder, and the generator can be any seq2seq model, preferably TFBartForConditionalGeneration.
The model can be initialized with a RagRetriever for end-to-end generation or used in combination with the
outputs of a retriever in multiple steps---see examples for more details. The model is compatible any
autoencoding model as the question_encoder and any seq2seq model with language model head as the generator.
It has been tested with TFDPRQuestionEncoder as the question_encoder and TFBartForConditionalGeneration
as the generator.
This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a Tensorflow tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
The model is in a developing state as it is now fully supports in eager-mode only, and may not be exported in SavedModel format.
call
< source >(
input_ids = None
attention_mask = None
decoder_input_ids = None
decoder_attention_mask = None
encoder_outputs = None
past_key_values = None
doc_scores = None
context_input_ids = None
context_attention_mask = None
use_cache = None
output_attentions = None
output_hidden_states = None
output_retrieved = None
n_docs = None
do_marginalize = None
labels = None
reduce_loss = None
return_dict = None
training = False
**kwargs
)
→
transformers.models.rag.modeling_tf_rag.TFRetrievAugLMMarginOutput or tuple(tf.Tensor)
Parameters
-
input_ids (
tf.Tensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. RagConfig, used to initialize the model, specifies which generator to use, it also specifies a compatible generator tokenizer. Use that tokenizer class to obtain the indices. -
attention_mask (
tf.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
encoder_outputs (
tuple(tuple(tf.Tensor), optional) — Tuple consists of (generator_enc_last_hidden_state, optional:generator_enc_hidden_states, optional:generator_enc_attentions).generator_enc_last_hidden_stateof shape(batch_size, n_docs * sequence_length, hidden_size)is a sequence of hidden-states at the output of the last layer of the generator’s encoder.Used by the (TFRagModel) model during decoding.
-
decoder_input_ids (
tf.Tensorof shape(batch_size, target_sequence_length), optional) — Provide for generation tasks.Noneby default, construct as per instructions for the generator model you’re using with your RAG instance. -
decoder_attention_mask (
torch.BoolTensorof shape(batch_size, target_sequence_length), optional) — Default behavior: generate a tensor that ignores pad tokens indecoder_input_ids. Causal mask will also be used by default. -
past_key_values (
tuple(tuple(tf.Tensor))) — Tuple consists of two elements:encoder_outputsof the RAG model (seeencoder_outputs) andpast_key_valuesof the underlying generator. Can be used to speed up decoding.past_key_valuesare used in the (RagTokenForGeneration) model during decoding. -
doc_scores (
tf.Tensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. If the model has is not initialized with aretrieverdoc_scoreshas to be provided to the forward pass.doc_scorescan be computed viaquestion_encoder_last_hidden_stateandretrieved_doc_embeds, see examples for more information. -
context_input_ids (
tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever`context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). context_attention_mask (tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True): Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retrievercontext_attention_maskhas to be provided to the forward pass.context_attention_maskare returned by__call__(). -
use_cache (
bool, optional, defaults toTrue) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). -
output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. -
output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. -
output_retrieved(
bool, optional) — Whether or not to return theretrieved_doc_embeds,retrieved_doc_ids,context_input_idsandcontext_attention_mask. See returned tensors for more detail. -
return_dict (
bool, optional) — Whether or not to return aTFRetrievAugLMOutputinstead of a plain tuple. -
n_docs (
int, optional, defaults to `config.n_docs“) — Number of documents to retrieve and/or number of documents for which to generate an answer. -
do_marginalize (
bool, optional) — IfTrue, the logits are marginalized over all documents by making use oftorch.nn.functional.log_softmax. -
labels (
tf.Tensorornp.ndarrayof shape(batch_size, sequence_length), optional) — Labels for computing the cross entropy classification loss according to Rag-Token model formulation See https://arxiv.org/pdf/2005.11401.pdf Section 2.1 for details about Rag-Token formulation. Indices should be in[0, ..., config.vocab_size - 1]. -
reduce_loss (
bool, optional) — Only relevant iflabelsis passed. IfTrue, the NLL loss is reduced using thetf.Tensor.sumoperation. -
kwargs (
Dict[str, any], optional, defaults to {}) — Legacy dictionary, which is required so that model can use generate() function.
Returns
transformers.models.rag.modeling_tf_rag.TFRetrievAugLMMarginOutput or tuple(tf.Tensor)
A transformers.models.rag.modeling_tf_rag.TFRetrievAugLMMarginOutput or a tuple of tf.Tensor (if
return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the
configuration (RagConfig) and inputs.
-
loss (
tf.Tensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss. -
logits (
tf.Tensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head. The score is possibly marginalized over all documents for each vocabulary token. -
past_key_values (
List[tf.Tensor], optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — List oftf.Tensorof lengthconfig.n_layers, with each tensor of shape(2, batch_size, num_heads, sequence_length, embed_size_per_head)).Contains precomputed hidden-states (key and values in the attention blocks) of the decoder that can be used (see
past_key_valuesinput) to speed up sequential decoding. -
doc_scores (
tf.Tensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state. -
retrieved_doc_embeds (
tf.Tensorof shape(batch_size, config.n_docs, hidden_size), optional, returned when output_retrieved=True) — Embedded documents retrieved by the retriever. Is used withquestion_encoder_last_hidden_stateto compute thedoc_scores. -
retrieved_doc_ids (
tf.Tensor(int32) of shape(batch_size, config.n_docs), optional, returned when output_retrieved=True) — The indexes of the embedded documents retrieved by the retriever. -
context_input_ids (
tf.Tensor(int32) of shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input ids post-processed from the retrieved documents and the question encoder input_ids by the retriever. -
context_attention_mask (
tf.Tensor(int32) of shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever. -
question_encoder_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden states at the output of the last layer of the question encoder pooled output of the model. -
question_enc_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the question encoder at the output of each layer plus the initial embedding outputs.
-
question_enc_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the question encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_enc_last_hidden_state (
tf.Tensorof shape(batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the generator encoder of the model. -
generator_enc_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator encoder at the output of each layer plus the initial embedding outputs.
-
generator_enc_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
-
generator_dec_hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(one for the output of the embeddings and one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden states of the generator decoder at the output of each layer plus the initial embedding outputs.
-
generator_dec_attentions (
tuple(tf.Tensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftf.Tensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights of the generator decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
The TFRagTokenForGeneration forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> import tensorflow as tf
>>> from transformers import RagTokenizer, RagRetriever, TFRagTokenForGeneration
>>> tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq")
>>> retriever = RagRetriever.from_pretrained(
... "facebook/rag-token-nq", index_name="exact", use_dummy_dataset=True
... )
>>> # initialize with RagRetriever to do everything in one forward call
>>> model = TFRagTokenForGeneration.from_pretrained("facebook/rag-token-nq", retriever=retriever, from_pt=True)
>>> input_dict = tokenizer.prepare_seq2seq_batch(
... "How many people live in Paris?", "In Paris, there are 10 million people.", return_tensors="tf"
... )
>>> outputs = model(input_dict, output_retrieved=True)
>>> # or use retriever separately
>>> # 1. Encode
>>> input_ids = input_dict["input_ids"]
>>> question_hidden_states = model.question_encoder(input_ids)[0]
>>> # 2. Retrieve
>>> docs_dict = retriever(input_ids.numpy(), question_hidden_states.numpy(), return_tensors="tf")
>>> doc_scores = tf.squeeze(
... tf.matmul(
... tf.expand_dims(question_hidden_states, axis=1), docs_dict["retrieved_doc_embeds"], transpose_b=True
... ),
... axis=1,
... )
>>> # 3. Forward to generator
>>> outputs = model(
... inputs=None,
... context_input_ids=docs_dict["context_input_ids"],
... context_attention_mask=docs_dict["context_attention_mask"],
... doc_scores=doc_scores,
... decoder_input_ids=input_dict["labels"],
... )
>>> # or directly generate
>>> generated = model.generate(
... context_input_ids=docs_dict["context_input_ids"],
... context_attention_mask=docs_dict["context_attention_mask"],
... doc_scores=doc_scores,
... )
>>> generated_string = tokenizer.batch_decode(generated, skip_special_tokens=True)generate
< source >(
input_ids: typing.Optional[tensorflow.python.framework.ops.Tensor] = None
attention_mask: typing.Optional[tensorflow.python.framework.ops.Tensor] = None
context_input_ids = None
context_attention_mask = None
doc_scores = None
max_length = None
min_length = None
early_stopping = None
use_cache = None
num_beams = None
bos_token_id = None
pad_token_id = None
eos_token_id = None
length_penalty = None
no_repeat_ngram_size = None
bad_words_ids = None
num_return_sequences = None
decoder_start_token_id = None
n_docs = None
output_scores = None
output_attentions = None
output_hidden_states = None
return_dict_in_generate = None
**model_kwargs
)
→
tf.Tensor of shape (batch_size * num_return_sequences, sequence_length)
Parameters
-
input_ids (
tf.Tensorof shape(batch_size, sequence_length), optional) — The sequence used as a prompt for the generation. Ifinput_idsis not passed, thencontext_input_idshas to be provided. -
attention_mask (
tf.Tensorof shape(batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
-
context_input_ids (
tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Input IDs post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever,context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). -
context_attention_mask (
tf.Tensorof shape(batch_size * config.n_docs, config.max_combined_length), optional, returned when output_retrieved=True) — Attention mask post-processed from the retrieved documents and the question encoderinput_idsby the retriever.If the model has is not initialized with a
retriever,context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). -
doc_scores (
tf.Tensorof shape(batch_size, config.n_docs)) — Score between each retrieved document embeddings (seeretrieved_doc_embeds) andquestion_encoder_last_hidden_state.If the model has is not initialized with a
retriever,context_input_idshas to be provided to the forward pass.context_input_idsare returned by__call__(). -
max_length (
int, optional, defaults to 20) — The maximum length of the sequence to be generated. -
min_length (
int, optional, defaults to 10) — The minimum length of the sequence to be generated. -
early_stopping (
bool, optional, defaults toFalse) — Whether or not to stop the beam search when at leastnum_beamssentences are finished per batch or not. use_cache — (bool, optional, defaults toTrue): Whether or not the model should use the past last key/values attentions (if applicable to the model) to speed up decoding. -
pad_token_id (
int, optional) — The id of the padding token. -
bos_token_id (
int, optional) — The id of the beginning-of-sequence token. -
eos_token_id (
int, optional) — The id of the end-of-sequence token. -
length_penalty (
float, optional, defaults to 1.0) — Exponential penalty to the length. 1.0 means no penalty.Set to values < 1.0 in order to encourage the model to generate shorter sequences, to a value > 1.0 in order to encourage the model to produce longer sequences.
-
no_repeat_ngram_size (
int, optional, defaults to 0) — If set to int > 0, all ngrams of that size can only occur once. -
bad_words_ids(
List[int], optional) — List of token ids that are not allowed to be generated. In order to get the tokens of the words that should not appear in the generated text, usetokenizer.encode(bad_word, add_prefix_space=True). -
num_beams (
int, optional, defaults to 1) — Number of beams for beam search. 1 means no beam search. -
num_return_sequences(
int, optional, defaults to 1) — The number of independently computed returned sequences for each element in the batch. Note that this is not the value we pass to thegenerator’s[generate()](/docs/transformers/v4.22.1/en/main_classes/text_generation#transformers.generation_utils.GenerationMixin.generate) function, where we setnum_return_sequencestonum_beams. decoder_start_token_id (int`, optional): If an encoder-decoder model starts decoding with a different token than bos, the id of that token. -
n_docs (
int, optional, defaults toconfig.n_docs) — Number of documents to retrieve and/or number of documents for which to generate an answer. -
output_attentions (
bool, optional, defaults toFalse) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more details. -
output_hidden_states (
bool, optional, defaults toFalse) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more details. -
output_scores (
bool, optional, defaults toFalse) — Whether or not to return the prediction scores. Seescoresunder returned tensors for more details. -
return_dict_in_generate (
bool, optional, defaults toFalse) — Whether or not to return a ModelOutput instead of a plain tuple. model_specific_kwargs — Additional model specific kwargs will be forwarded to theforwardfunction of the model.
Returns
tf.Tensor of shape (batch_size * num_return_sequences, sequence_length)
The generated sequences. The
second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early
due to the eos_token_id.
Implements TFRAG token decoding.