File size: 2,212 Bytes
1c0d09d |
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 |
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT license.
import math
from typing import Optional
from transformers import PretrainedConfig
class PhiConfig(PretrainedConfig):
"""Phi configuration."""
model_type = "phi-msft"
attribute_map = {
"max_position_embeddings": "n_positions",
"hidden_size": "n_embd",
"num_attention_heads": "n_head",
"num_hidden_layers": "n_layer",
}
def __init__(
self,
vocab_size: int = 50304,
n_positions: int = 2048,
n_embd: int = 1024,
n_layer: int = 20,
n_inner: Optional[int] = None,
n_head: int = 16,
n_head_kv: Optional[int] = None,
num_experts_per_tok: int = 2,
num_local_experts: int = 4,
rotary_dim: Optional[int] = 32,
activation_function: Optional[str] = "gelu_new",
flash_attn: bool = False,
flash_rotary: bool = False,
fused_dense: bool = False,
attn_pdrop: float = 0.0,
embd_pdrop: float = 0.0,
resid_pdrop: float = 0.0,
layer_norm_epsilon: float = 1e-5,
initializer_range: float = 0.02,
tie_word_embeddings: bool = False,
pad_vocab_size_multiple: int = 64,
**kwargs
) -> None:
self.vocab_size = int(math.ceil(vocab_size / pad_vocab_size_multiple) * pad_vocab_size_multiple)
self.n_positions = n_positions
self.n_embd = n_embd
self.n_layer = n_layer
self.n_inner = n_inner
self.n_head = n_head
self.n_head_kv = n_head_kv
self.num_experts_per_tok = num_experts_per_tok
self.num_local_experts = num_local_experts
self.rotary_dim = min(rotary_dim, n_embd // n_head)
self.activation_function = activation_function
self.flash_attn = flash_attn
self.flash_rotary = flash_rotary
self.fused_dense = fused_dense
self.attn_pdrop = attn_pdrop
self.embd_pdrop = embd_pdrop
self.resid_pdrop = resid_pdrop
self.layer_norm_epsilon = layer_norm_epsilon
self.initializer_range = initializer_range
super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)
|