|
|
|
|
|
|
|
|
|
from transformers.configuration_utils import PretrainedConfig |
|
from transformers.utils import logging |
|
|
|
|
|
logger = logging.get_logger(__name__) |
|
|
|
LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP = {} |
|
|
|
|
|
class MoeConfig(PretrainedConfig): |
|
|
|
model_type = "MoE++" |
|
keys_to_ignore_at_inference = ["past_key_values"] |
|
|
|
def __init__( |
|
self, |
|
vocab_size=32000, |
|
hidden_size=4096, |
|
intermediate_size=11008, |
|
num_hidden_layers=32, |
|
num_attention_heads=32, |
|
num_key_value_heads=None, |
|
hidden_act="silu", |
|
max_position_embeddings=2048, |
|
initializer_range=0.02, |
|
rms_norm_eps=1e-6, |
|
use_cache=True, |
|
pad_token_id=None, |
|
bos_token_id=1, |
|
eos_token_id=2, |
|
pretraining_tp=1, |
|
tie_word_embeddings=False, |
|
rope_theta=10000.0, |
|
rope_scaling=None, |
|
num_experts=[32], |
|
moe_expert_interval=1, |
|
moe_use_mixtral_gating=False, |
|
moe_2layer_gate=True, |
|
moe_use_logits_norm=False, |
|
moe_gate_norm_std=1.0, |
|
moe_feature_no_mul_topk=False, |
|
|
|
**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 |
|
|
|
|
|
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_scaling_validation() |
|
self.num_experts = num_experts |
|
self.moe_expert_interval = moe_expert_interval |
|
self.moe_use_mixtral_gating = moe_use_mixtral_gating |
|
self.moe_2layer_gate = moe_2layer_gate |
|
self.moe_use_logits_norm = moe_use_logits_norm |
|
self.moe_gate_norm_std = moe_gate_norm_std |
|
self.moe_feature_no_mul_topk = moe_feature_no_mul_topk |
|
|
|
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, |
|
) |
|
|
|
def _rope_scaling_validation(self): |
|
""" |
|
Validate the `rope_scaling` configuration. |
|
""" |
|
if self.rope_scaling is None: |
|
return |
|
|
|
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2: |
|
raise ValueError( |
|
"`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, " |
|
f"got {self.rope_scaling}" |
|
) |
|
rope_scaling_type = self.rope_scaling.get("type", None) |
|
rope_scaling_factor = self.rope_scaling.get("factor", None) |
|
if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic", "ntk"]: |
|
raise ValueError( |
|
f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}" |
|
) |
|
if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0: |
|
raise ValueError(f"`rope_scaling`'s factor field must be an float > 1, got {rope_scaling_factor}") |
|
|
