1gluonnlp.model
2==============
3
4GluonNLP Toolkit supplies models for common NLP tasks with pre-trained weights. By default,
5all requested pre-trained weights are downloaded from public repo and stored in ~/.mxnet/models/.
6
7.. currentmodule:: gluonnlp.model
8
9Model Registry
10--------------
11
12The model registry provides an easy interface to obtain pre-defined and pre-trained models.
13
14.. autosummary::
15    :nosignatures:
16
17    get_model
18
19The `get_model` function returns a pre-defined model given the name of a
20registered model. The following sections of this page present a list of
21registered names for each model category.
22
23Information about pretrained models
24-----------------------------------
25
26.. autosummary::
27    :nosignatures:
28
29    list_models
30
31Language Modeling
32-----------------
33
34Components
35
36.. autosummary::
37    :nosignatures:
38
39    AWDRNN
40    BiLMEncoder
41    LSTMPCellWithClip
42    StandardRNN
43    BigRNN
44
45Pre-defined models
46
47.. autosummary::
48    :nosignatures:
49
50    awd_lstm_lm_1150
51    awd_lstm_lm_600
52    standard_lstm_lm_200
53    standard_lstm_lm_650
54    standard_lstm_lm_1500
55    big_rnn_lm_2048_512
56
57Machine Translation
58-------------------
59
60.. autosummary::
61    :nosignatures:
62
63    Seq2SeqEncoder
64    TransformerEncoder
65    TransformerEncoderCell
66    PositionwiseFFN
67
68.. autosummary::
69    :nosignatures:
70
71    transformer_en_de_512
72
73Bidirectional Encoder Representations from Transformers
74-------------------------------------------------------
75
76Components
77
78.. autosummary::
79    :nosignatures:
80
81    BERTModel
82    BERTEncoder
83
84Pre-defined models
85
86.. autosummary::
87    :nosignatures:
88
89    bert_12_768_12
90    bert_24_1024_16
91
92Convolutional Encoder
93---------------------
94
95.. autosummary::
96    :nosignatures:
97
98    ConvolutionalEncoder
99
100ELMo
101----
102
103Components
104
105.. autosummary::
106    :nosignatures:
107
108    ELMoBiLM
109    ELMoCharacterEncoder
110
111Pre-defined models
112
113.. autosummary::
114    :nosignatures:
115
116    elmo_2x1024_128_2048cnn_1xhighway
117    elmo_2x2048_256_2048cnn_1xhighway
118    elmo_2x4096_512_2048cnn_2xhighway
119
120Highway Network
121-----------------
122
123.. autosummary::
124    :nosignatures:
125
126    Highway
127
128Attention Cell
129--------------
130
131.. autosummary::
132    :nosignatures:
133
134    AttentionCell
135    MultiHeadAttentionCell
136    MLPAttentionCell
137    DotProductAttentionCell
138
139Sequence Sampling
140-----------------
141
142.. autosummary::
143    :nosignatures:
144
145    BeamSearchScorer
146    BeamSearchSampler
147    SequenceSampler
148
149
150Other Modeling Utilities
151------------------------
152
153.. autosummary::
154    :nosignatures:
155
156    WeightDropParameter
157    apply_weight_drop
158    L2Normalization
159    GELU
160    ISDense
161    NCEDense
162    SparseISDense
163    SparseNCEDense
164
165API Reference
166-------------
167
168.. automodule:: gluonnlp.model
169    :members:
170    :imported-members:
171