modeling¶
-
class
BlenderbotModel
(vocab_size, bos_token_id=1, pad_token_id=0, eos_token_id=2, decoder_start_token_id=1, d_model=1280, num_encoder_layers=2, num_decoder_layers=12, encoder_attention_heads=32, decoder_attention_heads=32, encoder_ffn_dim=5120, decoder_ffn_dim=5120, dropout=0.1, activation_function='gelu', attention_dropout=0.0, activation_dropout=0.0, max_position_embeddings=128, init_std=0.02, scale_embedding=True, normalize_before=True)[源代码]¶ 基类:
paddlenlp.transformers.blenderbot.modeling.BlenderbotPretrainedModel
Construct a bare Blenderbot Model.
This model inherits from
PretrainedModel
. Check the superclass documentation for the generic methods and the library implements for all its model.This model is also a Paddle paddle.nn.Layer subclass. Use it as a regular Paddle Layer and refer to the Paddle documentation for all matter related to general usage and behavior.
- 参数
vocab_size (
int
) -- Vocabulary size of the Blenderbot model.bos_token_id (
int
, optional) -- The id for begging of sentences token. Defaults to1
.pad_token_id (
int
, optional) -- The id for padding token. Defaults to0
.eos_token_id (
int
, optional) -- The id for end of sentence token. Defaults to2
.decoder_start_token_id (
int
, optional) -- The id indicating the start of decoding sentence. Defaults to1
.d_model (
int
, optional) -- Dimensionality of the layers and the pooler layer. Defaults to1280
.num_encoder_layers (
int
, optional) -- Number of Transformer encoder layers for BlenderbotEncoder. Defaults to2
.num_decoder_layers (
int
, optional) -- Number of Transformer decoder layers for BlenderbotDecoder. Defaults to12
.encoder_attention_heads (
int
, optional) -- Number of attention heads for each Transformer encoder layer in BlenderbotEncoder. Defaults to32
.decoder_attention_heads (
int
, optional) -- Number of attention heads for each Transformer decoder layer in BlenderbotDecoder. Defaults to32
.encoder_ffn_dim (
int
, optional) -- Dimensionality of the feed-forward layer for each Transformer encoder layer in BlenderbotEncoder. Defaults to5120
.decoder_ffn_dim (
int
, optional) -- Dimensionality of the feed-forward layer for each Transformer dncoder layer in BlenderbotDncoder. Defaults to5120
.dropout (
float
, optional) -- The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. Defaults to0.1
.activation_function (
str
, optional) -- The non-linear activation function (function or string) in the encoder and pooler."gelu"
,"relu"
and any other paddle supported activation functions are supported. Defaults to"gelu"
.attention_dropout (
float
, optional) -- The dropout ratio for the attention probabilities. Defaults to0.0
.activation_dropout (
float
, optional) -- The dropout ratio for activations inside the fully connected layer.max_position_embeddings (
int
, optional) --, The max position index of an input sequence. Defaults to
128
.init_std (
float
, optional) -- The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Defaults to0.02
.scale_embedding (
bool
, optional) -- Indicate whether to scale embeddings by diving by sqrt(d_model). Defaults toTrue
.normalize_before (bool, optional) -- Indicate whether to put layer normalization into preprocessing of MHA and FFN sub-layers. If True, pre-process is layer normalization and post-precess includes dropout, residual connection. Otherwise, no pre-process and post-precess includes dropout, residual connection, layer normalization. Defaults to
True
.
-
forward
(input_ids=None, attention_mask=None, decoder_input_ids=None, decoder_attention_mask=None, encoder_output=None, use_cache=False, cache=None, **kwargs)[源代码]¶ - 参数
input_ids (Tensor) -- Indices of input sequence tokens in the vocabulary. They are numerical representations of tokens that build the input sequence. It's data type should be
int64
and has a shape of [batch_size, sequence_length].attention_mask (Tensor, optional) --
Mask to indicate whether to perform attention on each input token or not. The values should be either 0 or 1. The attention scores will be set to -infinity for any positions in the mask that are 0, and will be unchanged for positions that are 1.
1 for tokens that are not masked,
0 for tokens that are masked.
It's data type should be
float32
and has a shape of [batch_size, sequence_length]. Defaults toNone
.decoder_input_ids (Tensor, optional) -- If not provided,
decoder_input_ids
will be automatically generated based ondecoder_start_token_id
andinput_ids
.decoder_attention_mask (Tensor, optional) -- If not provided, the default
decoder_attention_mask
will be a tensor with upper triangular part being-np.inf
. the shape will be(decoder_length, decoder_length)
encoder_output (Tensor, optional) -- The output of encoder. If not provided, a
encoder_output
will be generated from BlenderbotEncoder. Defaults toNone
.use_cache (bool, optional) -- Indicates whether to use cache to speed up decoding. Defaults to
False
cache (list, optional) -- It is a list, and each element in the list is a tuple(
(incremental_cache, static_cache)
). Seepaddle.nn.TransformerDecoder.gen_cache
for more details. It is only used for inference and should be None for training. Default None.
- 返回
If
use_cache=False
, the return will be the last hidden state of decoder with shape of [batch_size, seq_lens, hidden_size].seq_lens
corresponds to the length of input sequence. Otherwise, the return will be a tuple of(decoder_output, cache)
. Please refer to classpaddle.nn.TransformerDecoder
for more information regardingcache
.- 返回类型
Tensor|tuple
示例
import paddle from paddlenlp.transformers import BlenderbotTokenizer, BlenderbotModel # "blenderbot-400M-distill" is the pretrained weight of BlenderbotForConditionalGeneration, # Therefore some weight of additional layers in BlenderbotForConditionalGeneration # might not be loaded and used regarding the following sample code. pretrained_model_name = "blenderbot-400M-distill" tokenizer = BlenderbotTokenizer.from_pretrained(pretrained_model_name) model = BlenderbotModel.from_pretrained(pretrained_model_name) sample_text = "My friends are cool but they eat too many carbs." inputs = tokenizer(sample_text, return_attention_mask=True, return_token_type_ids=False) inputs = {k:paddle.to_tensor([v]) for (k, v) in inputs.items()} decoder_output = model(**inputs)
-
class
BlenderbotPretrainedModel
(*args, **kwargs)[源代码]¶ 基类:
paddlenlp.transformers.model_utils.PretrainedModel
An abstract class for pretrained Blenderbot models. It provides Blenderbot related
model_config_file
,resource_files_names
,pretrained_resource_files_map
,pretrained_init_configuration
,base_model_prefix
for downloading and loading pretrained models. Refer toPretrainedModel
for more details.-
base_model_class
¶ alias of
paddlenlp.transformers.blenderbot.modeling.BlenderbotModel
-
-
class
BlenderbotEncoder
(vocab_size, embed_tokens=None, pad_token_id=0, d_model=1280, num_encoder_layers=2, encoder_attention_heads=32, encoder_ffn_dim=5120, dropout=0.1, activation_function='gelu', attention_dropout=0.0, activation_dropout=0.0, max_position_embeddings=128, init_std=0.02, scale_embedding=True, normalize_before=True)[源代码]¶ 基类:
paddlenlp.transformers.blenderbot.modeling.BlenderbotPretrainedModel
The encoder of Blenderbot Model. Please refer to
PretrainedModel
orBlenderbotModel
for more information regarding methods and arguments.
-
class
BlenderbotDecoder
(vocab_size, embed_tokens=None, pad_token_id=0, d_model=1280, num_decoder_layers=12, decoder_attention_heads=32, decoder_ffn_dim=5120, dropout=0.1, activation_function='gelu', attention_dropout=0.0, activation_dropout=0.0, max_position_embeddings=128, init_std=0.02, scale_embedding=True, normalize_before=True)[源代码]¶ 基类:
paddlenlp.transformers.blenderbot.modeling.BlenderbotPretrainedModel
The decoder of Blenderbot Model. Please refer to
PretrainedModel
andBlenderbotModel
for more information regarding methods and arguments.
-
class
BlenderbotForConditionalGeneration
(blenderbot)[源代码]¶ 基类:
paddlenlp.transformers.blenderbot.modeling.BlenderbotPretrainedModel
-
forward
(input_ids=None, attention_mask=None, decoder_input_ids=None, decoder_attention_mask=None, encoder_output=None, use_cache=False, cache=None, **kwargs)[源代码]¶ Please refer to
BlenderbotModel
for more information regarding arguments. :returns:- If
use_cache=False
, the return will be a tensor with shape of [batch_size, seq_lens, hidden_size]. Otherwise, the return will be a tuple of
(decoder_output, cache)
.
- 返回类型
Tensor|tuple
示例
import paddle from paddlenlp.transformers import BlenderbotTokenizer, BlenderbotForConditionalGeneration
pretrained_model_name = "blenderbot-400M-distill" tokenizer = BlenderbotTokenizer.from_pretrained(pretrained_model_name) model = BlenderbotForConditionalGeneration.from_pretrained(pretrained_model_name)
sample_text = "My friends are cool but they eat too many carbs." inputs = tokenizer(sample_text, return_attention_mask=True, return_token_type_ids=False) inputs = {k: paddle.to_tensor([v]) for (k, v) in inputs.items()}
# Generate response using beam search result_ids, scores = model.generate(input_ids=inputs['input_ids'],
max_length=60, min_length=20, decode_strategy='beam_search', num_beams=10, length_penalty=0.65)
- for sequence_ids in result_ids.numpy().tolist():
print("User: ", sample_text) print("bot: ", tokenizer.convert_ids_to_string(sequence_ids)) # "bot: That's unfortunate. Are they trying to lose weight?"
- If
-
-
class
BlenderbotForCausalLM
(blenderbot)[源代码]¶ 基类:
paddlenlp.transformers.blenderbot.modeling.BlenderbotPretrainedModel
Constructs BLenderbot For Causal Language Model. This model is equivalent to the blenderbot decoder without cross-attention.
-
forward
(input_ids=None, attention_mask=None, use_cache=False, cache=None, **kwargs)[源代码]¶ - 参数
input_ids (Tensor) -- Indices of input sequence tokens in the vocabulary. They are numerical representations of tokens that build the input sequence. It's data type should be
int64
and has a shape of [batch_size, sequence_length].attention_mask (Tensor, optional) --
Mask to indicate whether to perform attention on each input token or not. The values should be either 0 or 1. The attention scores will be set to -infinity for any positions in the mask that are 0, and will be unchanged for positions that are 1.
1 for tokens that are not masked,
0 for tokens that are masked.
It's data type should be
float32
and has a shape of [batch_size, sequence_length]. Defaults toNone
.use_cache (bool, optional) -- Indicates whether to use cache to speed up decoding. Defaults to
False
cache (list, optional) -- It is a list, and each element in the list is a tuple(
(incremental_cache, static_cache)
). Seepaddle.nn.TransformerDecoder.gen_cache
for more details. It is only used for inference and should be None for training. Default None.
- 返回
- If
use_cache=False
, the return will be a tensor with shape of [batch_size, seq_lens, hidden_size]. Otherwise, the return will be a tuple of
(lm_logits, cache)
.
- If
- 返回类型
Tensor|tuple
示例
import paddle from paddlenlp.transformers import BlenderbotTokenizer, BlenderbotForCausalLM use_cache = False text = "My friends are cool but they eat too many carbs." model_name = "blenderbot-400M-distill" tokenizer = BlenderbotTokenizer.from_pretrained(model_name) model = BlenderbotForCausalLM.from_pretrained(model_name) model.eval() inputs = tokenizer(text) inputs = {k: paddle.to_tensor([v]) for (k, v) in inputs.items()}
- with paddle.no_grad():
outputs = model(**inputs, use_cache=use_cache) # outputs is a tuple of (lm_logits, cache) if
use_cache=True
.
-