Hugging Face's logo

tonyshark
/
ml_test

Model card Files
xet
Community
ml_test
File size: 4,499 Bytes 
cc69848
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
PRESET = {
    "full": {
        "enable_conv": True,
        "unet_target_module": [
            "Transformer2DModel",
            "ResnetBlock2D",
            "Downsample2D",
            "Upsample2D",
            "HunYuanDiTBlock", #HunYuanDiT
            "DoubleStreamBlock", #Flux
            "SingleStreamBlock", #Flux
            "SingleDiTBlock", #SD3.5
            "MMDoubleStreamBlock", #HunYuanVideo
            "MMSingleStreamBlock", #HunYuanVideo
        ],
        "unet_target_name": [
            "conv_in",
            "conv_out",
            "time_embedding.linear_1",
            "time_embedding.linear_2",
        ],
        "text_encoder_target_module": [
            "CLIPAttention",
            "CLIPSdpaAttention",
            "CLIPMLP",
            "MT5Block",
            "BertLayer",
        ],
        "text_encoder_target_name": [],
    },
    "full-lin": {
        "enable_conv": False,
        "unet_target_module": [
            "Transformer2DModel",
            "ResnetBlock2D",
            "HunYuanDiTBlock",
            "DoubleStreamBlock",
            "SingleStreamBlock",
            "SingleDiTBlock",
            "MMDoubleStreamBlock", #HunYuanVideo
            "MMSingleStreamBlock", #HunYuanVideo
        ],
        "unet_target_name": [
            "time_embedding.linear_1",
            "time_embedding.linear_2",
        ],
        "text_encoder_target_module": [
            "CLIPAttention",
            "CLIPSdpaAttention",
            "CLIPMLP",
            "MT5Block",
            "BertLayer",
        ],
        "text_encoder_target_name": [],
    },
    "attn-mlp": {
        "enable_conv": False,
        "unet_target_module": [
            "Transformer2DModel",
            "HunYuanDiTBlock",
            "DoubleStreamBlock",
            "SingleStreamBlock",
            "SingleDiTBlock",
            "MMDoubleStreamBlock", #HunYuanVideo
            "MMSingleStreamBlock", #HunYuanVideo
        ],
        "unet_target_name": [],
        "text_encoder_target_module": [
            "CLIPAttention",
            "CLIPSdpaAttention",
            "CLIPMLP",
            "MT5Block",
            "BertLayer",
        ],
        "text_encoder_target_name": [],
    },
    "attn-only": {
        "enable_conv": False,
        "unet_target_module": [
            "CrossAttention",
            "SelfAttention",
        ],
        "unet_target_name": [],
        "text_encoder_target_module": [
            "CLIPAttention",
            "CLIPSdpaAttention",
            "BertAttention",
            "MT5LayerSelfAttention",
        ],
        "text_encoder_target_name": [],
    },
    "unet-only": {
        "enable_conv": True,
        "unet_target_module": [
            "Transformer2DModel",
            "ResnetBlock2D",
            "Downsample2D",
            "Upsample2D",
            "HunYuanDiTBlock",
            "DoubleStreamBlock",
            "SingleStreamBlock",
            "SingleDiTBlock",
            "MMDoubleStreamBlock", #HunYuanVideo
            "MMSingleStreamBlock", #HunYuanVideo
        ],
        "unet_target_name": [
            "conv_in",
            "conv_out",
            "time_embedding.linear_1",
            "time_embedding.linear_2",
        ],
        "text_encoder_target_module": [],
        "text_encoder_target_name": [],
    },
    "unet-transformer-only": {
        "enable_conv": False,
        "unet_target_module": [
            "Transformer2DModel",
            "HunYuanDiTBlock",
            "DoubleStreamBlock",
            "SingleStreamBlock",
            "SingleDiTBlock",
            "MMDoubleStreamBlock", #HunYuanVideo
            "MMSingleStreamBlock", #HunYuanVideo
        ],
        "unet_target_name": [],
        "text_encoder_target_module": [],
        "text_encoder_target_name": [],
    },
    "unet-convblock-only": {
        "enable_conv": True,
        "unet_target_module": ["ResnetBlock2D", "Downsample2D", "Upsample2D"],
        "unet_target_name": [
            "conv_in",
            "conv_out",
        ],
        "text_encoder_target_module": [],
        "text_encoder_target_name": [],
    },
    "ia3": {
        "enable_conv": False,
        "unet_target_module": [],
        "unet_target_name": ["to_k", "to_v", "ff.net.2"],
        "text_encoder_target_module": [],
        "text_encoder_target_name": ["k_proj", "v_proj", "mlp.fc2"],
        "name_algo_map": {
            "mlp.fc2": {"train_on_input": True},
            "ff.net.2": {"train_on_input": True},
        },
    },
}