File size: 1,750 Bytes
7381480 | 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 | """Configuration for the SPEV multimodal decision model."""
import math
from typing import ClassVar
from transformers import PretrainedConfig, Qwen3OmniMoeThinkerConfig
class SPEVConfig(PretrainedConfig):
model_type = "spev"
sub_configs: ClassVar[dict] = {"thinker_config": Qwen3OmniMoeThinkerConfig}
def __init__(
self,
thinker_config=None,
adapter_rank=32,
adapter_alpha=64,
head_width=256,
temperature=1.0,
max_tokens=8192,
**kwargs,
):
if isinstance(thinker_config, dict):
thinker_config = Qwen3OmniMoeThinkerConfig(**thinker_config)
self.thinker_config = thinker_config or Qwen3OmniMoeThinkerConfig()
for name, value in (
("adapter_rank", adapter_rank),
("head_width", head_width),
("max_tokens", max_tokens),
):
if not isinstance(value, int) or isinstance(value, bool) or value <= 0:
raise ValueError(f"{name} must be a positive integer")
if not math.isfinite(adapter_alpha) or adapter_alpha <= 0:
raise ValueError("adapter_alpha must be positive and finite")
if not math.isfinite(temperature) or temperature <= 0:
raise ValueError("temperature must be positive and finite")
self.adapter_rank = adapter_rank
self.adapter_alpha = adapter_alpha
self.head_width = head_width
self.temperature = temperature
self.max_tokens = max_tokens
kwargs.setdefault("tie_word_embeddings", False)
super().__init__(**kwargs)
def get_text_config(self, decoder=False, encoder=False):
return self.thinker_config.text_config
SPEVConfig.register_for_auto_class()
|