30 lines
1.5 KiB
Python
30 lines
1.5 KiB
Python
|
# -*- coding: utf-8 -*-
|
||
|
|
|
||
|
|
from fla.models.abc import ABCConfig, ABCForCausalLM, ABCModel
|
||
|
|
from fla.models.delta_net import (DeltaNetConfig, DeltaNetForCausalLM,
|
||
|
|
DeltaNetModel)
|
||
|
|
from fla.models.gla import GLAConfig, GLAForCausalLM, GLAModel
|
||
|
|
from fla.models.hgrn import HGRNConfig, HGRNForCausalLM, HGRNModel
|
||
|
|
from fla.models.hgrn2 import HGRN2Config, HGRN2ForCausalLM, HGRN2Model
|
||
|
|
from fla.models.linear_attn import (LinearAttentionConfig,
|
||
|
|
LinearAttentionForCausalLM,
|
||
|
|
LinearAttentionModel)
|
||
|
|
from fla.models.mamba import MambaConfig, MambaForCausalLM, MambaModel
|
||
|
|
from fla.models.retnet import RetNetConfig, RetNetForCausalLM, RetNetModel
|
||
|
|
from fla.models.rwkv6 import RWKV6Config, RWKV6ForCausalLM, RWKV6Model
|
||
|
|
from fla.models.transformer import (TransformerConfig, TransformerForCausalLM,
|
||
|
|
TransformerModel)
|
||
|
|
|
||
|
|
__all__ = [
|
||
|
|
'ABCConfig', 'ABCForCausalLM', 'ABCModel',
|
||
|
|
'DeltaNetConfig', 'DeltaNetForCausalLM', 'DeltaNetModel',
|
||
|
|
'GLAConfig', 'GLAForCausalLM', 'GLAModel',
|
||
|
|
'HGRNConfig', 'HGRNForCausalLM', 'HGRNModel',
|
||
|
|
'HGRN2Config', 'HGRN2ForCausalLM', 'HGRN2Model',
|
||
|
|
'LinearAttentionConfig', 'LinearAttentionForCausalLM', 'LinearAttentionModel',
|
||
|
|
'MambaConfig', 'MambaForCausalLM', 'MambaModel',
|
||
|
|
'RetNetConfig', 'RetNetForCausalLM', 'RetNetModel',
|
||
|
|
'RWKV6Config', 'RWKV6ForCausalLM', 'RWKV6Model',
|
||
|
|
'TransformerConfig', 'TransformerForCausalLM', 'TransformerModel'
|
||
|
|
]
|