Hugging Face's logo

zaydzuhri
/
softpick-340M-4096-batch16-steps100000

Safetensors
transformer
Model card Files Community
1
softpick-340M-4096-batch16-steps100000
File size: 2,328 Bytes 
0298ad2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
# -*- coding: utf-8 -*-

from fla.layers import (
    ABCAttention,
    Attention,
    BasedLinearAttention,
    BitAttention,
    DeltaNet,
    GatedDeltaNet,
    GatedDeltaProduct,
    GatedLinearAttention,
    GatedSlotAttention,
    HGRN2Attention,
    HGRNAttention,
    LightNetAttention,
    LinearAttention,
    MultiScaleRetention,
    NativeSparseAttention,
    ReBasedLinearAttention,
    RWKV6Attention,
    RWKV7Attention
)
from fla.models import (
    ABCForCausalLM,
    ABCModel,
    BitNetForCausalLM,
    BitNetModel,
    DeltaNetForCausalLM,
    DeltaNetModel,
    GatedDeltaNetForCausalLM,
    GatedDeltaNetModel,
    GatedDeltaProductForCausalLM,
    GatedDeltaProductModel,
    GLAForCausalLM,
    GLAModel,
    GSAForCausalLM,
    GSAModel,
    HGRN2ForCausalLM,
    HGRN2Model,
    HGRNForCausalLM,
    LightNetForCausalLM,
    LightNetModel,
    LinearAttentionForCausalLM,
    LinearAttentionModel,
    NSAForCausalLM,
    NSAModel,
    RetNetForCausalLM,
    RetNetModel,
    RWKV6ForCausalLM,
    RWKV6Model,
    RWKV7ForCausalLM,
    RWKV7Model,
    TransformerForCausalLM,
    TransformerModel
)

__all__ = [
    'ABCAttention',
    'Attention',
    'BasedLinearAttention',
    'BitAttention',
    'DeltaNet',
    'GatedDeltaNet',
    'GatedDeltaProduct',
    'GatedLinearAttention',
    'GatedSlotAttention',
    'HGRNAttention',
    'HGRN2Attention',
    'LightNetAttention',
    'LinearAttention',
    'MultiScaleRetention',
    'NativeSparseAttention',
    'ReBasedLinearAttention',
    'RWKV6Attention',
    'RWKV7Attention',
    'ABCForCausalLM',
    'ABCModel',
    'BitNetForCausalLM',
    'BitNetModel',
    'DeltaNetForCausalLM',
    'DeltaNetModel',
    'GatedDeltaNetForCausalLM',
    'GatedDeltaNetModel',
    'GatedDeltaProductForCausalLM',
    'GatedDeltaProductModel',
    'GLAForCausalLM',
    'GLAModel',
    'GSAForCausalLM',
    'GSAModel',
    'HGRNForCausalLM',
    'HGRNModel',
    'HGRN2ForCausalLM',
    'HGRN2Model',
    'LightNetForCausalLM',
    'LightNetModel',
    'LinearAttentionForCausalLM',
    'LinearAttentionModel',
    'NSAForCausalLM',
    'NSAModel',
    'RetNetForCausalLM',
    'RetNetModel',
    'RWKV6ForCausalLM',
    'RWKV6Model',
    'RWKV7ForCausalLM',
    'RWKV7Model',
    'TransformerForCausalLM',
    'TransformerModel',
]

__version__ = '0.1.2'