202 lines
11 KiB
Python
202 lines
11 KiB
Python
# coding=utf-8
|
|
# Copyright 2024 Stability AI 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.
|
|
"""StableLM model configuration"""
|
|
|
|
from ...configuration_utils import PretrainedConfig
|
|
from ...modeling_rope_utils import rope_config_validation
|
|
from ...utils import logging
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
class StableLmConfig(PretrainedConfig):
|
|
r"""
|
|
This is the configuration class to store the configuration of a [`~StableLmModel`].
|
|
It is used to instantiate an StableLM 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 StableLM [stabilityai/stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t) 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 50304):
|
|
Vocabulary size of the StableLM model. Defines the number of different tokens that
|
|
can be represented by the `inputs_ids` passed when calling [`StableLmModel`].
|
|
intermediate_size (`int`, *optional*, defaults to 6912):
|
|
Dimension of the MLP representations.
|
|
hidden_size (`int`, *optional*, defaults to 2560):
|
|
Number of hidden layers in the Transformer decoder.
|
|
num_hidden_layers (`int`, *optional*, defaults to 32):
|
|
Number of hidden layers in the Transformer decoder.
|
|
num_attention_heads (`int`, *optional*, defaults to 32):
|
|
Number of attention heads for each attention layer in the Transformer encoder.
|
|
num_key_value_heads (`int`, *optional*, defaults to 32):
|
|
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
|
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
|
`num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
|
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
|
by meanpooling all the original heads within that group. For more details, check out [this
|
|
paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
|
|
`num_attention_heads`.
|
|
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
|
The non-linear activation function (function or string).
|
|
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
|
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.
|
|
layer_norm_eps (`float`, *optional*, defaults to 1e-05):
|
|
The epsilon used by the 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 the model's input and output word embeddings should be tied.
|
|
rope_theta (`float`, *optional*, defaults to `10000.0`):
|
|
The base period of the RoPE embeddings.
|
|
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
|
|
use_qkv_bias (`bool`, *optional*, defaults to `False`):
|
|
Whether or not the model should use bias for qkv layers.
|
|
qk_layernorm (`bool`, *optional*, defaults to `False`):
|
|
Whether or not to normalize, per head, the Queries and Keys after projecting the hidden states.
|
|
use_parallel_residual (`bool`, *optional*, defaults to `False`):
|
|
Whether to use a "parallel" formulation in each Transformer layer, which can provide a slight training
|
|
speedup at large scales.
|
|
hidden_dropout (`float`, *optional*, defaults to 0.0):
|
|
The dropout ratio after applying the MLP to the hidden states.
|
|
attention_dropout (`float`, *optional*, defaults to 0.0):
|
|
The dropout ratio for the attention probabilities.
|
|
partial_rotary_factor (`float`, *optional*, defaults to 0.25):
|
|
Percentage of the query and keys which will have rotary embedding.
|
|
bos_token_id (int, *optional*, defaults to 0):
|
|
The id of the `BOS` token in the vocabulary.
|
|
eos_token_id (int, *optional*, defaults to 0):
|
|
The id of the `EOS` token in the vocabulary.
|
|
|
|
Example:
|
|
|
|
```python
|
|
>>> from transformers import StableLmModel, StableLmConfig
|
|
|
|
>>> # Initializing a StableLM stablelm-3b style configuration
|
|
>>> configuration = StableLmConfig()
|
|
```"""
|
|
|
|
model_type = "stablelm"
|
|
keys_to_ignore_at_inference = ["past_key_values"]
|
|
|
|
def __init__(
|
|
self,
|
|
vocab_size=50304,
|
|
intermediate_size=6912,
|
|
hidden_size=2560,
|
|
num_hidden_layers=32,
|
|
num_attention_heads=32,
|
|
num_key_value_heads=32,
|
|
hidden_act="silu",
|
|
max_position_embeddings=4096,
|
|
initializer_range=0.02,
|
|
layer_norm_eps=1.0e-5,
|
|
use_cache=True,
|
|
tie_word_embeddings=False,
|
|
rope_theta=10_000,
|
|
rope_scaling=None,
|
|
use_qkv_bias=False,
|
|
qk_layernorm=False,
|
|
use_parallel_residual=False,
|
|
hidden_dropout=0.0,
|
|
attention_dropout=0.0,
|
|
partial_rotary_factor=0.25,
|
|
bos_token_id=0,
|
|
eos_token_id=0,
|
|
**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.num_key_value_heads = num_key_value_heads
|
|
self.hidden_act = hidden_act
|
|
|
|
self.initializer_range = initializer_range
|
|
self.layer_norm_eps = layer_norm_eps
|
|
self.use_cache = use_cache
|
|
self.rope_theta = rope_theta
|
|
self.rope_scaling = rope_scaling
|
|
self.use_qkv_bias = use_qkv_bias
|
|
self.qk_layernorm = qk_layernorm
|
|
self.use_parallel_residual = use_parallel_residual
|
|
self.hidden_dropout = hidden_dropout
|
|
self.attention_dropout = attention_dropout
|
|
self.partial_rotary_factor = partial_rotary_factor
|
|
# 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)
|
|
|
|
super().__init__(
|
|
bos_token_id=bos_token_id,
|
|
eos_token_id=eos_token_id,
|
|
tie_word_embeddings=tie_word_embeddings,
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
__all__ = ["StableLmConfig"]
|