File size: 5,242 Bytes
099838f |
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 |
# coding=utf-8
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
#
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
# and OPT implementations in this library. It has been modified from its
# original forms to accommodate minor architectural differences compared
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
#
# 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.
""" XVERSE model configuration"""
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
XVERSE_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
class XverseConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`XverseModel`]. It is used to instantiate an Xverse
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 XVERSE-13B.
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 100278):
Vocabulary size of the XVERSE model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`XverseModel`]
hidden_size (`int`, *optional*, defaults to 5120):
Dimension of the hidden representations.
intermediate_size (`int`, *optional*, defaults to 13824):
Dimension of the MLP representations.
num_hidden_layers (`int`, *optional*, defaults to 40):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 40):
Number of attention heads for each attention layer in the Transformer encoder.
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
The non-linear activation function (function or string) in the decoder.
max_position_embeddings (`int`, *optional*, defaults to 8192):
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 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
rms_norm_eps (`float`, *optional*, defaults to 1e-6):
The epsilon used by the rms 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`.
tie_word_embeddings(`bool`, *optional*, defaults to `False`):
Whether to tie weight embeddings
Example:
```python
>>> from transformers import XverseModel, XverseConfig
>>> # Initializing a Xverse XVERSE-13B style configuration
>>> configuration = XverseConfig()
>>> # Initializing a model from the XVERSE-13B style configuration
>>> model = XverseModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "xverse"
keys_to_ignore_at_inference = ["past_key_values"]
def __init__(
self,
vocab_size=100278,
hidden_size=5120,
intermediate_size=13824,
num_hidden_layers=40,
num_attention_heads=40,
hidden_act="silu",
max_position_embeddings=8192,
max_tokenizer_truncation=8192,
initializer_range=0.02,
rms_norm_eps=1e-6,
use_cache=True,
pad_token_id=None,
bos_token_id=1,
eos_token_id=2,
tie_word_embeddings=False,
**kwargs,
):
self.vocab_size = vocab_size
self.max_position_embeddings = max_position_embeddings
self.hidden_size = hidden_size
self.intermediate_size = intermediate_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.hidden_act = hidden_act
self.initializer_range = initializer_range
self.rms_norm_eps = rms_norm_eps
self.use_cache = use_cache
self.max_tokenizer_truncation = max_tokenizer_truncation
super().__init__(
pad_token_id=pad_token_id,
bos_token_id=bos_token_id,
eos_token_id=eos_token_id,
tie_word_embeddings=tie_word_embeddings,
**kwargs,
) |