File size: 10,450 Bytes
08c3b64 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 |
# coding=utf-8
# Copyright 2022 EleutherAI and The HuggingFace Inc. team. 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.
"""GPTNeoX model configuration"""
from transformers.configuration_utils import PretrainedConfig
from transformers.modeling_rope_utils import rope_config_validation
from transformers.utils import logging
logger = logging.get_logger(__name__)
class GPTNeoXConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`GPTNeoXModel`]. It is used to instantiate an
GPTNeoX 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 GPTNeoX
[EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) architecture.
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 50432):
Vocabulary size of the GPTNeoX model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`GPTNeoXModel`].
hidden_size (`int`, *optional*, defaults to 6144):
Dimension of the encoder layers and the pooler layer.
num_hidden_layers (`int`, *optional*, defaults to 44):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 64):
Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (`int`, *optional*, defaults to 24576):
Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
`"relu"`, `"selu"` and `"gelu_new"` are supported.
rotary_pct (`float`, *optional*, defaults to 0.25):
percentage of hidden dimensions to allocate to rotary embeddings
rotary_emb_base (`int`, *optional*, defaults to 10000)
base for computing rotary embeddings frequency
attention_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio probability of the attention score.
hidden_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio of (1) the word embeddings, (2) the post-attention hidden states, and (3) the post-mlp
hidden states.
classifier_dropout (`float`, *optional*, defaults to 0.1):
Argument used when doing token classification, used in the model [`GPTNeoXForTokenClassification`].
The dropout ratio for the hidden layer.
max_position_embeddings (`int`, *optional*, defaults to 2048):
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).
initializer_range (`float`, *optional*, defaults to 1e-5):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
layer_norm_eps (`float`, *optional*, defaults to 1e-12):
The epsilon used by the layer normalization layers.
use_cache (`bool`, *optional*, defaults to `True`):
Whether or not the model should return the last key/values attentions (not used by all models). Only
relevant if `config.is_decoder=True`.
use_parallel_residual (`bool`, *optional*, defaults to `True`):
Whether to use a "parallel" formulation in each Transformer layer, which can provide a slight training
speedup at large scales (e.g. 20B).
rope_scaling (`Dict`, *optional*):
Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
accordingly.
Expected contents:
`rope_type` (`str`):
The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
'llama3'], with 'default' being the original RoPE implementation.
`factor` (`float`, *optional*):
Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
most scaling types, a `factor` of x will enable the model to handle sequences of length x *
original maximum pre-trained length.
`original_max_position_embeddings` (`int`, *optional*):
Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
pretraining.
`attention_factor` (`float`, *optional*):
Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
computation. If unspecified, it defaults to value recommended by the implementation, using the
`factor` field to infer the suggested value.
`beta_fast` (`float`, *optional*):
Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
ramp function. If unspecified, it defaults to 32.
`beta_slow` (`float`, *optional*):
Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
ramp function. If unspecified, it defaults to 1.
`short_factor` (`List[float]`, *optional*):
Only used with 'longrope'. The scaling factor to be applied to short contexts (<
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
size divided by the number of attention heads divided by 2
`long_factor` (`List[float]`, *optional*):
Only used with 'longrope'. The scaling factor to be applied to long contexts (<
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
size divided by the number of attention heads divided by 2
`low_freq_factor` (`float`, *optional*):
Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
`high_freq_factor` (`float`, *optional*):
Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
attention_bias (`bool`, *optional*, defaults to `True`):
Whether to use a bias in the query, key, value and output projection layers during self-attention.
Example:
```python
>>> from transformers import GPTNeoXConfig, GPTNeoXModel
>>> # Initializing a GPTNeoX gpt-neox-20b style configuration
>>> configuration = GPTNeoXConfig()
>>> # Initializing a model (with random weights) from the gpt-neox-20b style configuration
>>> model = GPTNeoXModel(configuration) # doctest: +SKIP
>>> # Accessing the model configuration
>>> configuration = model.config # doctest: +SKIP
```"""
model_type = "gpt_neox"
keys_to_ignore_at_inference = ["past_key_values"]
def __init__(
self,
vocab_size=50432,
hidden_size=6144,
num_hidden_layers=44,
num_attention_heads=64,
intermediate_size=24576,
hidden_act="gelu",
rotary_pct=0.25,
rotary_emb_base=10000,
attention_dropout=0.0,
hidden_dropout=0.0,
classifier_dropout=0.1,
max_position_embeddings=2048,
initializer_range=0.02,
layer_norm_eps=1e-5,
use_cache=True,
bos_token_id=0,
eos_token_id=2,
tie_word_embeddings=False,
use_parallel_residual=True,
rope_scaling=None,
attention_bias=True,
**kwargs,
):
super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
self.vocab_size = vocab_size
self.max_position_embeddings = max_position_embeddings
self.hidden_size = hidden_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.intermediate_size = intermediate_size
self.hidden_act = hidden_act
self.rotary_pct = rotary_pct
self.partial_rotary_factor = rotary_pct
self.rotary_emb_base = rotary_emb_base
self.rope_theta = rotary_emb_base
self.attention_dropout = attention_dropout
self.hidden_dropout = hidden_dropout
self.classifier_dropout = classifier_dropout
self.initializer_range = initializer_range
self.layer_norm_eps = layer_norm_eps
self.use_cache = use_cache
self.tie_word_embeddings = tie_word_embeddings
self.use_parallel_residual = use_parallel_residual
self.rope_scaling = rope_scaling
self.attention_bias = attention_bias
# Validate the correctness of rotary position embeddings parameters
# BC: if there is a 'type' field, move it to 'rope_type'.
if self.rope_scaling is not None and "type" in self.rope_scaling:
self.rope_scaling["rope_type"] = self.rope_scaling["type"]
rope_config_validation(self)
if self.hidden_size % self.num_attention_heads != 0:
raise ValueError(
"The hidden size is not divisble by the number of attention heads! Make sure to update them!"
)
|