216 lines
11 KiB
Python
216 lines
11 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
from typing import Any
|
|
|
|
from transformers import PretrainedConfig
|
|
|
|
|
|
class AXK1Config(PretrainedConfig):
|
|
r"""
|
|
This is the configuration class to store the configuration of a [`AXK1Model`].
|
|
It is used to instantiate an A.X 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 A.X K1.
|
|
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 163840):
|
|
Vocabulary size of the A.X K1 model. Defines the number of different
|
|
tokens that can be represented by the `inputs_ids` passed when calling
|
|
[`AXK1Model`]
|
|
hidden_size (`int`, *optional*, defaults to 7168):
|
|
Dimension of the hidden representations.
|
|
intermediate_size (`int`, *optional*, defaults to 18432):
|
|
Dimension of the MLP representations.
|
|
moe_intermediate_size (`int`, *optional*, defaults to 2048):
|
|
Dimension of the MoE representations.
|
|
num_hidden_layers (`int`, *optional*, defaults to 61):
|
|
Number of hidden layers in the Transformer decoder.
|
|
num_nextn_predict_layers (`int`, *optional*, defaults to 1):
|
|
Number of nextn predict layers in the AXK1 Model.
|
|
num_attention_heads (`int`, *optional*, defaults to 64):
|
|
Number of attention heads for each attention layer in the Transformer
|
|
decoder.
|
|
n_shared_experts (`int`, *optional*, defaults to 1):
|
|
Number of shared experts, None means dense model.
|
|
n_routed_experts (`int`, *optional*, defaults to 192):
|
|
Number of routed experts, None means dense model.
|
|
routed_scaling_factor (`float`, *optional*, defaults to 2.5):
|
|
Scaling factor or routed experts.
|
|
topk_method (`str`, *optional*, defaults to `noaux_tc`):
|
|
Topk method used in routed gate.
|
|
n_group (`int`, *optional*, defaults to 8):
|
|
Number of groups for routed experts.
|
|
topk_group (`int`, *optional*, defaults to 4):
|
|
Number of selected groups for each token(for each token, ensuring the
|
|
selected experts is only within `topk_group` groups).
|
|
num_experts_per_tok (`int`, *optional*, defaults to 8):
|
|
Number of selected experts, None means dense model.
|
|
moe_layer_freq (`int`, *optional*, defaults to 1):
|
|
The frequency of the MoE layer: one expert layer for every
|
|
`moe_layer_freq - 1` dense layers.
|
|
first_k_dense_replace (`int`, *optional*, defaults to 1):
|
|
Number of dense layers in shallow layers
|
|
(embed->dense->dense->...->dense->moe->moe...->lm_head).
|
|
\--k dense layers--/
|
|
norm_topk_prob (`bool`, *optional*, defaults to True):
|
|
Whether to normalize the weights of the routed experts.
|
|
scoring_func (`str`, *optional*, defaults to 'sigmoid'):
|
|
Method of computing expert weights.
|
|
aux_loss_alpha (`float`, *optional*, defaults to 0.0001):
|
|
Auxiliary loss weight coefficient.
|
|
seq_aux = (`bool`, *optional*, defaults to True):
|
|
Whether to compute the auxiliary loss for each individual sample.
|
|
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://arxiv.org/pdf/2305.13245.pdf).
|
|
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 131072):
|
|
The maximum sequence length that this model might ever be used with.
|
|
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-06):
|
|
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`.
|
|
pad_token_id (`int`, *optional*):
|
|
Padding token id.
|
|
bos_token_id (`int`, *optional*, defaults to 163691):
|
|
Beginning of stream token id.
|
|
eos_token_id (`int`, *optional*, defaults to 163691):
|
|
End of stream token id.
|
|
pretraining_tp (`int`, *optional*, defaults to 1):
|
|
Experimental feature. Tensor parallelism rank used during pretraining.
|
|
Please refer to
|
|
[this document](https://huggingface.co/docs/transformers/parallelism)
|
|
to understand more about it. This value is necessary to ensure exact
|
|
reproducibility of the pretraining results. Please refer to
|
|
[this issue](https://github.com/pytorch/pytorch/issues/76232).
|
|
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
|
Whether to tie weight embeddings
|
|
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.
|
|
Currently supports two scaling strategies: linear and dynamic.
|
|
Their scaling factor must be a float greater than 1. The expected format
|
|
is `{"type": strategy name, "factor": scaling factor}`. When using this
|
|
flag, don't update `max_position_embeddings` to the expected new maximum.
|
|
attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
|
|
Whether to use a bias in the query, key, value and output projection
|
|
layers during self-attention.
|
|
attention_dropout (`float`, *optional*, defaults to 0.0):
|
|
The dropout ratio for the attention probabilities.
|
|
"""
|
|
|
|
model_type = "AXK1"
|
|
keys_to_ignore_at_inference = ["past_key_values"]
|
|
|
|
def __init__(
|
|
self,
|
|
vocab_size: int = 163840,
|
|
hidden_size: int = 7168,
|
|
intermediate_size: int = 18432,
|
|
moe_intermediate_size: int = 2048,
|
|
num_hidden_layers: int = 61,
|
|
num_nextn_predict_layers: int | None = 1,
|
|
num_attention_heads: int = 64,
|
|
num_key_value_heads: int = 64,
|
|
n_shared_experts: int | None = 1,
|
|
n_routed_experts: int | None = 192,
|
|
ep_size: int | None = 8, ## Ignored - Expert parallel size
|
|
routed_scaling_factor: float | None = 2.5,
|
|
kv_lora_rank: int | None = 512,
|
|
q_lora_rank: int | None = 1536,
|
|
qk_rope_head_dim: int | None = 64,
|
|
v_head_dim: int | None = 128,
|
|
qk_nope_head_dim: int | None = 128,
|
|
topk_method: str | None = "noaux_tc",
|
|
n_group: int | None = 8,
|
|
topk_group: int | None = 4,
|
|
num_experts_per_tok: int | None = 8,
|
|
moe_layer_freq: int | None = 1,
|
|
first_k_dense_replace: int = 1,
|
|
norm_topk_prob: bool = True,
|
|
scoring_func: str | None = "sigmoid",
|
|
aux_loss_alpha: float | None = 0.0001,
|
|
seq_aux: float | None = True,
|
|
hidden_act: str | None = "silu",
|
|
max_position_embeddings: int | None = 131072,
|
|
initializer_range: float | None = 0.02,
|
|
rms_norm_eps: float = 1e-6,
|
|
use_cache: bool | None = True,
|
|
pad_token_id: int | None = None,
|
|
bos_token_id: int | None = 163691,
|
|
eos_token_id: int | None = 163691,
|
|
pretraining_tp: int | None = 1,
|
|
tie_word_embeddings: bool | None = False,
|
|
rope_theta: float | None = 10000.0,
|
|
rope_scaling: dict[str, Any] | None = None,
|
|
rope_parameters: dict[str, Any] | None = None,
|
|
attention_bias: bool | None = False,
|
|
attention_dropout: float | None = 0.0,
|
|
**kwargs,
|
|
):
|
|
self.vocab_size = vocab_size
|
|
self.max_position_embeddings = max_position_embeddings
|
|
self.hidden_size = hidden_size
|
|
self.intermediate_size = intermediate_size
|
|
self.moe_intermediate_size = moe_intermediate_size
|
|
self.num_hidden_layers = num_hidden_layers
|
|
self.num_nextn_predict_layers = num_nextn_predict_layers
|
|
self.num_attention_heads = num_attention_heads
|
|
self.n_shared_experts = n_shared_experts
|
|
self.n_routed_experts = n_routed_experts
|
|
self.ep_size = ep_size
|
|
self.routed_scaling_factor = routed_scaling_factor
|
|
self.kv_lora_rank = kv_lora_rank
|
|
self.q_lora_rank = q_lora_rank
|
|
self.qk_rope_head_dim = qk_rope_head_dim
|
|
self.v_head_dim = v_head_dim
|
|
self.qk_nope_head_dim = qk_nope_head_dim
|
|
self.topk_method = topk_method
|
|
self.n_group = n_group
|
|
self.topk_group = topk_group
|
|
self.num_experts_per_tok = num_experts_per_tok
|
|
self.moe_layer_freq = moe_layer_freq
|
|
self.first_k_dense_replace = first_k_dense_replace
|
|
self.norm_topk_prob = norm_topk_prob
|
|
self.scoring_func = scoring_func
|
|
self.aux_loss_alpha = aux_loss_alpha
|
|
self.seq_aux = seq_aux
|
|
# for backward compatibility
|
|
if num_key_value_heads is None:
|
|
num_key_value_heads = num_attention_heads
|
|
|
|
self.num_key_value_heads = num_key_value_heads
|
|
self.hidden_act = hidden_act
|
|
self.initializer_range = initializer_range
|
|
self.rms_norm_eps = rms_norm_eps
|
|
self.pretraining_tp = pretraining_tp
|
|
self.use_cache = use_cache
|
|
self.rope_theta = rope_theta
|
|
self.rope_scaling = rope_scaling
|
|
self.rope_parameters = rope_parameters
|
|
self.attention_bias = attention_bias
|
|
self.attention_dropout = attention_dropout
|
|
|
|
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,
|
|
)
|