File size: 4,960 Bytes
d000bbe |
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 |
# coding=utf-8
# Copyright 2023 Better Planet Investments and labml.ai 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.
""" GeoV model configuration"""
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
GEOV_PRETRAINED_CONFIG_ARCHIVE_MAP = {
"GeoV/GeoV-9b": "https://huggingface.co/GeoV/GeoV-9b/resolve/main/config.json",
}
class GeoVConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`GeoVModel`]. It is used to instantiate a
GeoV 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 GeoV
[GeoV/GeoV-9b](https://huggingface.co/GeoV/GeoV-9b) 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 65536):
Vocabulary size of the GeoV model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`GeoVModel`].
hidden_size (`int`, *optional*, defaults to 5120):
Dimension of the encoder layers and the pooler layer.
num_hidden_layers (`int`, *optional*, defaults to 32):
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.
intermediate_size (`int`, *optional*, defaults to 20480):
Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
rotary_emb_base (`int`, *optional*, defaults to 10000)
base for computing rotary embeddings frequency
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).
layer_norm_eps (`float`, *optional*, defaults to 1e-4):
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_extra_biases_ffn (`bool`, *optional*, defaults to `False`):
Whether or not to have extra bias parameters in the final layer of FFN modules.
Example:
```python
>>> from transformers import GeoVConfig, GeoVModel
>>> # Initializing a GeoV configuration
>>> configuration = GeoVConfig()
>>> # Initializing a model (with random weights) from the configuration
>>> model = GeoVModel(configuration) # doctest: +SKIP
>>> # Accessing the model configuration
>>> configuration = model.config # doctest: +SKIP
```"""
model_type = "geov"
def __init__(
self,
vocab_size=65_536,
hidden_size=5_120,
num_hidden_layers=32,
num_attention_heads=40,
intermediate_size=1024 * 5 * 4,
layer_norm_eps=1e-4,
rotary_emb_base=10000,
max_position_embeddings=2048,
use_extra_biases_ffn=False,
use_cache=True,
bos_token_id=0,
eos_token_id=2,
tie_word_embeddings=False,
tokenizer_class="GeoVTokenizer",
**kwargs,
):
super().__init__(
bos_token_id=bos_token_id,
eos_token_id=eos_token_id,
tie_word_embeddings=tie_word_embeddings,
tokenizer_class=tokenizer_class,
**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.rotary_emb_base = rotary_emb_base
self.use_cache = use_cache
self.layer_norm_eps = layer_norm_eps
self.use_extra_biases_ffn = use_extra_biases_ffn
|