You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

190 lines
9.9 KiB

# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# This file was automatically generated from src/transformers/models/exaone4/modular_exaone4.py.
# Do NOT edit this file manually as any edits will be overwritten by the generation of
# the file from the modular. If any change should be done, please apply the change to the
# modular_exaone4.py file directly. One of our CI enforces this.
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 The LG AI Research and 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.
from ...configuration_utils import PreTrainedConfig, layer_type_validation
from ...modeling_rope_utils import RopeParameters
class Exaone4Config(PreTrainedConfig):
r"""
This is the configuration class to store the configuration of a [`Exaone4Model`]. It is used to
instantiate a EXAONE 4.0 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 EXAONE-4.0-32B [LGAI-EXAONE/EXAONE-4.0-32B](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B)
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 102400):
Vocabulary size of the EXAONE 4.0 model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`Exaone4Model`].
hidden_size (`int`, *optional*, defaults to 4096):
Dimension of the hidden representations.
intermediate_size (`int`, *optional*, defaults to `hidden_size * 4`):
Dimensionality of the MLP representations.
num_hidden_layers (`int`, *optional*, defaults to 32):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 32):
Number of attention heads for each attention layer in the Transformer decoder.
num_key_value_heads (`int`, *optional*):
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 checkout [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) in the decoder.
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., 32768 for EXAONE 3.5).
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-05):
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``.
bos_token_id (`int`, *optional*, defaults to 0):
Beginning of stream token id.
eos_token_id (`int`, *optional*, defaults to 2):
End of stream token id.
pad_token_id (`int`, *optional*):
The id of the padding token.
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
Whether to tie weight embeddings
rope_parameters (`RopeParameters`, *optional*):
Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain
a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE
with longer `max_position_embeddings`.
attention_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio for the attention probabilities.
sliding_window (`int`, *optional*):
The size of the sliding window for the sliding window attention.
sliding_window_pattern (`str`, *optional*):
The pattern to use for sliding window attention. Can be one of:
- `None`: No sliding window attention is used
- `int`: Every `sliding_window` layers, use global attention, else use local attention.
- `str`: A sequence of "L" (local attention) and "G" (global attention) characters that defines the
attention pattern. The pattern starts from layer 0 and repeats every `sliding_window` layers. The
final layer always uses global attention regardless of the pattern.
For instance, sliding_window_pattern="LLLG" same as sliding_window=4, which means:
- Layer 0, 1, 2: local attention,
- Layer 3: global attention,
...(repeated)
layer_types (`list`, *optional*):
Attention pattern for each layer. Prioritized over `sliding_window_pattern`.
Example:
```python
>>> from transformers import Exaone4Model, Exaone4Config
>>> # Initializing a EXAONE configuration
>>> configuration = Exaone4Config()
>>> # Initializing a model from configuration
>>> model = Exaone4Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "exaone4"
keys_to_ignore_at_inference = ["past_key_values"]
# Default tensor parallel plan for base model `LlamaModel`
base_model_tp_plan = {
"layers.*.self_attn.q_proj": "colwise",
"layers.*.self_attn.k_proj": "colwise",
"layers.*.self_attn.v_proj": "colwise",
"layers.*.self_attn.o_proj": "rowwise",
"layers.*.mlp.gate_proj": "colwise",
"layers.*.mlp.up_proj": "colwise",
"layers.*.mlp.down_proj": "rowwise",
}
base_model_pp_plan = {
"embed_tokens": (["input_ids"], ["inputs_embeds"]),
"layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
"norm": (["hidden_states"], ["hidden_states"]),
}
def __init__(
self,
vocab_size: int | None = 102400,
hidden_size: int | None = 4096,
intermediate_size: int | None = 16384,
num_hidden_layers: int | None = 32,
num_attention_heads: int | None = 32,
num_key_value_heads: int | None = 32,
hidden_act: str | None = "silu",
max_position_embeddings: int | None = 2048,
initializer_range: float | None = 0.02,
rms_norm_eps: int | None = 1e-5,
use_cache: bool | None = True,
bos_token_id: int | None = 0,
eos_token_id: int | None = 2,
pad_token_id: int | None = None,
tie_word_embeddings: bool | None = False,
rope_parameters: RopeParameters | dict[str, RopeParameters] | None = None,
attention_dropout: float | None = 0.0,
sliding_window: int | None = 4096,
sliding_window_pattern: int | None = 4,
layer_types: list[str] | None = None,
**kwargs,
):
self.vocab_size = vocab_size
self.hidden_size = hidden_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.intermediate_size = intermediate_size
self.hidden_act = hidden_act
self.max_position_embeddings = max_position_embeddings
self.initializer_range = initializer_range
self.rms_norm_eps = rms_norm_eps
self.use_cache = use_cache
self.attention_dropout = attention_dropout
self.sliding_window = sliding_window
self.sliding_window_pattern = sliding_window_pattern
self.bos_token_id = bos_token_id
self.eos_token_id = eos_token_id
self.pad_token_id = pad_token_id
self.tie_word_embeddings = tie_word_embeddings
self.layer_types = layer_types
if self.sliding_window is None:
sliding_window_pattern = 0
if self.layer_types is None:
self.layer_types = [
"sliding_attention"
if ((i + 1) % (sliding_window_pattern) != 0 and i < self.num_hidden_layers)
else "full_attention"
for i in range(self.num_hidden_layers)
]
layer_type_validation(self.layer_types, self.num_hidden_layers)
self.rope_parameters = rope_parameters
super().__init__(**kwargs)
__all__ = ["Exaone4Config"]