File size: 6,439 Bytes
301ba04 054e6fd 301ba04 054e6fd 301ba04 054e6fd 301ba04 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
# Copyright (c) 2024, OrionStar Inc. All rights reserved.
# Copied and adapted from https://github.com/huggingface/transformers/blob/main/src/transformers/models/mixtral/configuration_mixtral.py
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
class OrionMOEConfig(PretrainedConfig):
"""
Args:
vocab_size (`int`, *optional*, defaults to 113664):
Vocabulary size of the OrionMOE model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`OrionMOEModel`]
hidden_size (`int`, *optional*, defaults to 4096):
Dimension of the hidden representations.
intermediate_size (`int`, *optional*, defaults to 14592):
Dimension 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 encoder.
num_key_value_heads (`int`, *optional*, defaults to 8):
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 `8`.
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. OrionMOE's sliding window attention
allows sequence of up to 4096*32 tokens.
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 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*):
The id of the padding token.
bos_token_id (`int`, *optional*, defaults to 1):
The id of the "beginning-of-sequence" token.
eos_token_id (`int`, *optional*, defaults to 2):
The id of the "end-of-sequence" token.
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 1000000.0):
The base period of the RoPE embeddings.
sliding_window (`int`, *optional*):
Sliding window attention window size. If not specified, will default to `4096`.
attention_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio for the attention probabilities.
num_experts_per_tok (`int`, *optional*, defaults to 2):
The number of experts to root per-token, can be also interpreted as the `top-p` routing
parameter
num_local_experts (`int`, *optional*, defaults to 8):
Number of experts per Sparse MLP layer.
output_router_logits (`bool`, *optional*, defaults to `False`):
Whether or not the router logits should be returned by the model. Enabeling this will also
allow the model to output the auxiliary loss. See [here]() for more details
router_aux_loss_coef (`float`, *optional*, defaults to 0.001):
The aux loss factor for the total loss.
"""
model_type = "orion_moe"
keys_to_ignore_at_inference = ["past_key_values"]
def __init__(
self,
vocab_size=113664,
hidden_size=4096,
intermediate_size=14592,
num_hidden_layers=32,
num_attention_heads=32,
num_key_value_heads=8,
hidden_act="silu",
max_position_embeddings=8192,
initializer_range=0.02,
rms_norm_eps=1e-5,
use_cache=True,
pad_token_id=None,
bos_token_id=1,
eos_token_id=2,
tie_word_embeddings=False,
rope_theta=1e6,
sliding_window=None,
attention_dropout=0.0,
num_experts_per_tok=2,
num_local_experts=8,
output_router_logits=False,
router_aux_loss_coef=0.01,
router_jitter_noise=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.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.sliding_window = sliding_window
# 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.use_cache = use_cache
self.rope_theta = rope_theta
self.attention_dropout = attention_dropout
self.num_experts_per_tok = num_experts_per_tok
self.num_local_experts = num_local_experts
self.output_router_logits = output_router_logits
self.router_aux_loss_coef = router_aux_loss_coef
self.router_jitter_noise = router_jitter_noise
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,
)
|