File size: 4,789 Bytes
4c65bff |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
# coding=utf-8
# Copyright 2018 Salesforce and HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" Salesforce CTRL configuration"""
from ...configuration_utils import PretrainedConfig
from ...utils import logging
logger = logging.get_logger(__name__)
CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP = {
"Salesforce/ctrl": "https://huggingface.co/Salesforce/ctrl/resolve/main/config.json"
}
class CTRLConfig(PretrainedConfig):
"""
This is the configuration class to store the configuration of a [`CTRLModel`] or a [`TFCTRLModel`]. It is used to
instantiate a CTRL model according to the specified arguments, defining the model architecture. Instantiating a
configuration with the defaults will yield a similar configuration to that of the
[Salesforce/ctrl](https://huggingface.co/Salesforce/ctrl) architecture from SalesForce.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
vocab_size (`int`, *optional*, defaults to 246534):
Vocabulary size of the CTRL model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`CTRLModel`] or [`TFCTRLModel`].
n_positions (`int`, *optional*, defaults to 256):
The maximum sequence length that this model might ever be used with. Typically set this to something large
just in case (e.g., 512 or 1024 or 2048).
n_embd (`int`, *optional*, defaults to 1280):
Dimensionality of the embeddings and hidden states.
dff (`int`, *optional*, defaults to 8192):
Dimensionality of the inner dimension of the feed forward networks (FFN).
n_layer (`int`, *optional*, defaults to 48):
Number of hidden layers in the Transformer encoder.
n_head (`int`, *optional*, defaults to 16):
Number of attention heads for each attention layer in the Transformer encoder.
resid_pdrop (`float`, *optional*, defaults to 0.1):
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
embd_pdrop (`int`, *optional*, defaults to 0.1):
The dropout ratio for the embeddings.
layer_norm_epsilon (`float`, *optional*, defaults to 1e-06):
The epsilon to use in the layer normalization layers
initializer_range (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
use_cache (`bool`, *optional*, defaults to `True`):
Whether or not the model should return the last key/values attentions (not used by all models).
Examples:
```python
>>> from transformers import CTRLConfig, CTRLModel
>>> # Initializing a CTRL configuration
>>> configuration = CTRLConfig()
>>> # Initializing a model (with random weights) from the configuration
>>> model = CTRLModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "ctrl"
keys_to_ignore_at_inference = ["past_key_values"]
attribute_map = {
"max_position_embeddings": "n_positions",
"hidden_size": "n_embd",
"num_attention_heads": "n_head",
"num_hidden_layers": "n_layer",
}
def __init__(
self,
vocab_size=246534,
n_positions=256,
n_embd=1280,
dff=8192,
n_layer=48,
n_head=16,
resid_pdrop=0.1,
embd_pdrop=0.1,
layer_norm_epsilon=1e-6,
initializer_range=0.02,
use_cache=True,
**kwargs,
):
self.vocab_size = vocab_size
self.n_positions = n_positions
self.n_embd = n_embd
self.n_layer = n_layer
self.n_head = n_head
self.dff = dff
self.resid_pdrop = resid_pdrop
self.embd_pdrop = embd_pdrop
self.layer_norm_epsilon = layer_norm_epsilon
self.initializer_range = initializer_range
self.use_cache = use_cache
super().__init__(**kwargs)
|