drbaph commited on
Commit
0690d4d
·
verified ·
1 Parent(s): a0fd0af

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +106 -0
  2. fp8_scales.json +600 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dit_adaln_type": "global",
3
+ "dit_adaln_use_text_cond": true,
4
+ "dit_bias": true,
5
+ "dit_cross_attn": true,
6
+ "dit_cross_attn_norm": false,
7
+ "dit_depth": 32,
8
+ "dit_dim": 2560,
9
+ "dit_dropout": 0.0,
10
+ "dit_eps": 1e-06,
11
+ "dit_ff_mult": 3.6,
12
+ "dit_heads": 32,
13
+ "dit_long_skip": true,
14
+ "dit_qk_norm": true,
15
+ "dit_text_conv": true,
16
+ "dit_text_dim": 768,
17
+ "dit_use_latent_condition": true,
18
+ "latent_dim": 64,
19
+ "latent_hop": 2048,
20
+ "max_wav_duration": 60,
21
+ "model_type": "audiodit",
22
+ "repa_dit_layer": 8,
23
+ "sampling_rate": 24000,
24
+ "sigma": 0.0,
25
+ "text_add_embed": true,
26
+ "text_encoder_config": {
27
+ "_name_or_path": "ArthurZ/umt5-base",
28
+ "architectures": [
29
+ "UMT5ForConditionalGeneration"
30
+ ],
31
+ "chunk_size_feed_forward": 0,
32
+ "classifier_dropout": 0.0,
33
+ "d_ff": 2048,
34
+ "d_kv": 64,
35
+ "d_model": 768,
36
+ "decoder_start_token_id": 0,
37
+ "dense_act_fn": "gelu_new",
38
+ "dropout_rate": 0.1,
39
+ "dtype": "float32",
40
+ "eos_token_id": 1,
41
+ "feed_forward_proj": "gated-gelu",
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1"
45
+ },
46
+ "initializer_factor": 1.0,
47
+ "is_decoder": false,
48
+ "is_encoder_decoder": true,
49
+ "is_gated_act": true,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "layer_norm_epsilon": 1e-06,
55
+ "model_type": "umt5",
56
+ "num_decoder_layers": 12,
57
+ "num_heads": 12,
58
+ "num_layers": 12,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_past": true,
62
+ "pad_token_id": 0,
63
+ "problem_type": null,
64
+ "relative_attention_max_distance": 128,
65
+ "relative_attention_num_buckets": 32,
66
+ "return_dict": true,
67
+ "scalable_attention": true,
68
+ "tie_word_embeddings": true,
69
+ "tokenizer_class": "T5Tokenizer",
70
+ "use_cache": true,
71
+ "vocab_size": 256384
72
+ },
73
+ "text_encoder_model": "google/umt5-base",
74
+ "text_norm_feat": true,
75
+ "transformers_version": "5.3.0",
76
+ "vae_config": {
77
+ "c_mults": [
78
+ 1,
79
+ 2,
80
+ 4,
81
+ 8,
82
+ 16
83
+ ],
84
+ "channels": 128,
85
+ "downsample_shortcut": "averaging",
86
+ "downsampling_ratio": 2048,
87
+ "encoder_latent_dim": 128,
88
+ "final_tanh": false,
89
+ "in_channels": 1,
90
+ "in_shortcut": "duplicating",
91
+ "latent_dim": 64,
92
+ "model_type": "audiodit_vae",
93
+ "out_shortcut": "averaging",
94
+ "sample_rate": 24000,
95
+ "scale": 0.71,
96
+ "strides": [
97
+ 2,
98
+ 4,
99
+ 4,
100
+ 8,
101
+ 8
102
+ ],
103
+ "upsample_shortcut": "duplicating",
104
+ "use_snake": true
105
+ }
106
+ }
fp8_scales.json ADDED
@@ -0,0 +1,600 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": 0.003016880580357143,
3
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": 0.015904017857142856,
4
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": 0.0004359654017857143,
5
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": 0.05915178571428571,
6
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.v.weight": 0.0019967215401785715,
7
+ "text_encoder.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": 0.0025460379464285715,
8
+ "text_encoder.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": 0.002894810267857143,
9
+ "text_encoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": 0.010044642857142858,
10
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.k.weight": 0.005580357142857143,
11
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.o.weight": 0.01708984375,
12
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.q.weight": 0.0003901890345982143,
13
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight": 3.6785714285714284,
14
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.v.weight": 0.0029820033482142855,
15
+ "text_encoder.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": 0.004377092633928571,
16
+ "text_encoder.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": 0.0038364955357142855,
17
+ "text_encoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": 0.007742745535714286,
18
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.k.weight": 0.005824497767857143,
19
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.o.weight": 0.03431919642857143,
20
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.q.weight": 0.0006626674107142857,
21
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.relative_attention_bias.weight": 0.06277901785714286,
22
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.v.weight": 0.007359095982142857,
23
+ "text_encoder.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": 0.007045200892857143,
24
+ "text_encoder.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": 0.016043526785714284,
25
+ "text_encoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": 0.018694196428571428,
26
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.k.weight": 0.00439453125,
27
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.o.weight": 0.018973214285714284,
28
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.q.weight": 0.0005711146763392857,
29
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.relative_attention_bias.weight": 0.06501116071428571,
30
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.v.weight": 0.009347098214285714,
31
+ "text_encoder.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": 0.007882254464285714,
32
+ "text_encoder.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": 0.025111607142857144,
33
+ "text_encoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": 0.018973214285714284,
34
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.k.weight": 0.003574916294642857,
35
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.o.weight": 0.006940569196428571,
36
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.q.weight": 0.0005384172712053571,
37
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.relative_attention_bias.weight": 0.07142857142857142,
38
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.v.weight": 0.0027901785714285715,
39
+ "text_encoder.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": 0.004813058035714286,
40
+ "text_encoder.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": 0.006626674107142857,
41
+ "text_encoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": 0.008091517857142858,
42
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.k.weight": 0.0034877232142857145,
43
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.o.weight": 0.01025390625,
44
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.q.weight": 0.00054931640625,
45
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.relative_attention_bias.weight": 0.06277901785714286,
46
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.v.weight": 0.0030343191964285715,
47
+ "text_encoder.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": 0.005510602678571429,
48
+ "text_encoder.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": 0.006033761160714286,
49
+ "text_encoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": 0.011509486607142858,
50
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.k.weight": 0.004987444196428571,
51
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.o.weight": 0.012625558035714286,
52
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.q.weight": 0.0005623953683035714,
53
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.relative_attention_bias.weight": 0.07421875,
54
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.v.weight": 0.003958565848214286,
55
+ "text_encoder.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": 0.007184709821428571,
56
+ "text_encoder.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": 0.011509486607142858,
57
+ "text_encoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": 0.00927734375,
58
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.k.weight": 0.004010881696428571,
59
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.o.weight": 0.008614676339285714,
60
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.q.weight": 0.0005841936383928571,
61
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.relative_attention_bias.weight": 0.06529017857142858,
62
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.v.weight": 0.0035574776785714285,
63
+ "text_encoder.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": 0.004743303571428571,
64
+ "text_encoder.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": 0.007882254464285714,
65
+ "text_encoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": 0.008126395089285714,
66
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.k.weight": 0.004063197544642857,
67
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.o.weight": 0.016322544642857144,
68
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.q.weight": 0.0005841936383928571,
69
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.relative_attention_bias.weight": 0.06975446428571429,
70
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.v.weight": 0.004220145089285714,
71
+ "text_encoder.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": 0.004464285714285714,
72
+ "text_encoder.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": 0.009974888392857142,
73
+ "text_encoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": 0.009347098214285714,
74
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.k.weight": 0.005022321428571429,
75
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.o.weight": 0.01123046875,
76
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.q.weight": 0.0005035400390625,
77
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.relative_attention_bias.weight": 0.05998883928571429,
78
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.v.weight": 0.005057198660714286,
79
+ "text_encoder.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": 0.009765625,
80
+ "text_encoder.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": 0.009974888392857142,
81
+ "text_encoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": 0.0146484375,
82
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.k.weight": 0.005824497767857143,
83
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.o.weight": 0.0224609375,
84
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.q.weight": 0.0005100795200892857,
85
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.relative_attention_bias.weight": 0.06668526785714286,
86
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.v.weight": 0.005859375,
87
+ "text_encoder.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": 0.005510602678571429,
88
+ "text_encoder.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": 0.01513671875,
89
+ "text_encoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": 0.017229352678571428,
90
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.k.weight": 0.0033656529017857145,
91
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.o.weight": 0.023995535714285716,
92
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.q.weight": 0.0005405970982142857,
93
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.relative_attention_bias.weight": 0.06194196428571429,
94
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.v.weight": 0.005894252232142857,
95
+ "text_encoder.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": 0.007184709821428571,
96
+ "text_encoder.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": 0.012346540178571428,
97
+ "text_encoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": 0.018275669642857144,
98
+ "text_encoder.encoder.embed_tokens.weight": 0.33035714285714285,
99
+ "transformer.adaln_global_mlp.mlp.1.weight": 0.004167829241071429,
100
+ "transformer.blocks.0.cross_attn.to_k.weight": 0.0013689313616071428,
101
+ "transformer.blocks.0.cross_attn.to_out.0.weight": 0.0009591238839285714,
102
+ "transformer.blocks.0.cross_attn.to_q.weight": 0.00091552734375,
103
+ "transformer.blocks.0.cross_attn.to_v.weight": 0.0015171595982142857,
104
+ "transformer.blocks.0.ffn.ff.0.weight": 0.00115966796875,
105
+ "transformer.blocks.0.ffn.ff.3.weight": 0.0012991768973214285,
106
+ "transformer.blocks.0.self_attn.to_k.weight": 0.0024588448660714285,
107
+ "transformer.blocks.0.self_attn.to_out.0.weight": 0.0012991768973214285,
108
+ "transformer.blocks.0.self_attn.to_q.weight": 0.0023716517857142855,
109
+ "transformer.blocks.0.self_attn.to_v.weight": 0.0013427734375,
110
+ "transformer.blocks.1.cross_attn.to_k.weight": 0.0011029924665178572,
111
+ "transformer.blocks.1.cross_attn.to_out.0.weight": 0.0010899135044642857,
112
+ "transformer.blocks.1.cross_attn.to_q.weight": 0.0011771065848214285,
113
+ "transformer.blocks.1.cross_attn.to_v.weight": 0.0007847377232142857,
114
+ "transformer.blocks.1.ffn.ff.0.weight": 0.0012730189732142857,
115
+ "transformer.blocks.1.ffn.ff.3.weight": 0.0010157993861607143,
116
+ "transformer.blocks.1.self_attn.to_k.weight": 0.0013776506696428572,
117
+ "transformer.blocks.1.self_attn.to_out.0.weight": 0.0010157993861607143,
118
+ "transformer.blocks.1.self_attn.to_q.weight": 0.0014561244419642857,
119
+ "transformer.blocks.1.self_attn.to_v.weight": 0.0009373256138392857,
120
+ "transformer.blocks.10.cross_attn.to_k.weight": 0.0012730189732142857,
121
+ "transformer.blocks.10.cross_attn.to_out.0.weight": 0.0009678431919642857,
122
+ "transformer.blocks.10.cross_attn.to_q.weight": 0.0011422293526785715,
123
+ "transformer.blocks.10.cross_attn.to_v.weight": 0.0008108956473214286,
124
+ "transformer.blocks.10.ffn.ff.0.weight": 0.0019269670758928572,
125
+ "transformer.blocks.10.ffn.ff.3.weight": 0.004150390625,
126
+ "transformer.blocks.10.self_attn.to_k.weight": 0.0012032645089285715,
127
+ "transformer.blocks.10.self_attn.to_out.0.weight": 0.0008457728794642857,
128
+ "transformer.blocks.10.self_attn.to_q.weight": 0.00164794921875,
129
+ "transformer.blocks.10.self_attn.to_v.weight": 0.0011117117745535715,
130
+ "transformer.blocks.11.cross_attn.to_k.weight": 0.0006365094866071429,
131
+ "transformer.blocks.11.cross_attn.to_out.0.weight": 0.006173270089285714,
132
+ "transformer.blocks.11.cross_attn.to_q.weight": 0.0008501325334821429,
133
+ "transformer.blocks.11.cross_attn.to_v.weight": 0.0006103515625,
134
+ "transformer.blocks.11.ffn.ff.0.weight": 0.0017874581473214285,
135
+ "transformer.blocks.11.ffn.ff.3.weight": 0.0038539341517857145,
136
+ "transformer.blocks.11.self_attn.to_k.weight": 0.0018484933035714285,
137
+ "transformer.blocks.11.self_attn.to_out.0.weight": 0.0015694754464285715,
138
+ "transformer.blocks.11.self_attn.to_q.weight": 0.0020054408482142855,
139
+ "transformer.blocks.11.self_attn.to_v.weight": 0.0013776506696428572,
140
+ "transformer.blocks.12.cross_attn.to_k.weight": 0.0006495884486607143,
141
+ "transformer.blocks.12.cross_attn.to_out.0.weight": 0.0025809151785714285,
142
+ "transformer.blocks.12.cross_attn.to_q.weight": 0.0008719308035714286,
143
+ "transformer.blocks.12.cross_attn.to_v.weight": 0.0005754743303571429,
144
+ "transformer.blocks.12.ffn.ff.0.weight": 0.0016392299107142857,
145
+ "transformer.blocks.12.ffn.ff.3.weight": 0.0013253348214285715,
146
+ "transformer.blocks.12.self_attn.to_k.weight": 0.0016392299107142857,
147
+ "transformer.blocks.12.self_attn.to_out.0.weight": 0.0006801060267857143,
148
+ "transformer.blocks.12.self_attn.to_q.weight": 0.002720424107142857,
149
+ "transformer.blocks.12.self_attn.to_v.weight": 0.0008152553013392857,
150
+ "transformer.blocks.13.cross_attn.to_k.weight": 0.0009722028459821429,
151
+ "transformer.blocks.13.cross_attn.to_out.0.weight": 0.003976004464285714,
152
+ "transformer.blocks.13.cross_attn.to_q.weight": 0.000885009765625,
153
+ "transformer.blocks.13.cross_attn.to_v.weight": 0.0005449567522321429,
154
+ "transformer.blocks.13.ffn.ff.0.weight": 0.0012468610491071428,
155
+ "transformer.blocks.13.ffn.ff.3.weight": 0.004377092633928571,
156
+ "transformer.blocks.13.self_attn.to_k.weight": 0.0013689313616071428,
157
+ "transformer.blocks.13.self_attn.to_out.0.weight": 0.0009940011160714285,
158
+ "transformer.blocks.13.self_attn.to_q.weight": 0.0021885463169642855,
159
+ "transformer.blocks.13.self_attn.to_v.weight": 0.0007367815290178571,
160
+ "transformer.blocks.14.cross_attn.to_k.weight": 0.0011771065848214285,
161
+ "transformer.blocks.14.cross_attn.to_out.0.weight": 0.0023193359375,
162
+ "transformer.blocks.14.cross_attn.to_q.weight": 0.0009678431919642857,
163
+ "transformer.blocks.14.cross_attn.to_v.weight": 0.0010201590401785715,
164
+ "transformer.blocks.14.ffn.ff.0.weight": 0.0015520368303571428,
165
+ "transformer.blocks.14.ffn.ff.3.weight": 0.0026681082589285715,
166
+ "transformer.blocks.14.self_attn.to_k.weight": 0.00164794921875,
167
+ "transformer.blocks.14.self_attn.to_out.0.weight": 0.0014386858258928572,
168
+ "transformer.blocks.14.self_attn.to_q.weight": 0.0021536690848214285,
169
+ "transformer.blocks.14.self_attn.to_v.weight": 0.0007455008370535714,
170
+ "transformer.blocks.15.cross_attn.to_k.weight": 0.0007890973772321429,
171
+ "transformer.blocks.15.cross_attn.to_out.0.weight": 0.002406529017857143,
172
+ "transformer.blocks.15.cross_attn.to_q.weight": 0.0008326939174107143,
173
+ "transformer.blocks.15.cross_attn.to_v.weight": 0.0006583077566964286,
174
+ "transformer.blocks.15.ffn.ff.0.weight": 0.0014561244419642857,
175
+ "transformer.blocks.15.ffn.ff.3.weight": 0.002101353236607143,
176
+ "transformer.blocks.15.self_attn.to_k.weight": 0.0018484933035714285,
177
+ "transformer.blocks.15.self_attn.to_out.0.weight": 0.0015869140625,
178
+ "transformer.blocks.15.self_attn.to_q.weight": 0.002284458705357143,
179
+ "transformer.blocks.15.self_attn.to_v.weight": 0.0009722028459821429,
180
+ "transformer.blocks.16.cross_attn.to_k.weight": 0.0008806501116071429,
181
+ "transformer.blocks.16.cross_attn.to_out.0.weight": 0.0028599330357142855,
182
+ "transformer.blocks.16.cross_attn.to_q.weight": 0.0010419573102678572,
183
+ "transformer.blocks.16.cross_attn.to_v.weight": 0.0009852818080357143,
184
+ "transformer.blocks.16.ffn.ff.0.weight": 0.0013253348214285715,
185
+ "transformer.blocks.16.ffn.ff.3.weight": 0.0017787388392857143,
186
+ "transformer.blocks.16.self_attn.to_k.weight": 0.0019444056919642857,
187
+ "transformer.blocks.16.self_attn.to_out.0.weight": 0.0009111676897321429,
188
+ "transformer.blocks.16.self_attn.to_q.weight": 0.002284458705357143,
189
+ "transformer.blocks.16.self_attn.to_v.weight": 0.0007455008370535714,
190
+ "transformer.blocks.17.cross_attn.to_k.weight": 0.0008588518415178571,
191
+ "transformer.blocks.17.cross_attn.to_out.0.weight": 0.0023890904017857145,
192
+ "transformer.blocks.17.cross_attn.to_q.weight": 0.0009329659598214286,
193
+ "transformer.blocks.17.cross_attn.to_v.weight": 0.0011771065848214285,
194
+ "transformer.blocks.17.ffn.ff.0.weight": 0.0010811941964285715,
195
+ "transformer.blocks.17.ffn.ff.3.weight": 0.004185267857142857,
196
+ "transformer.blocks.17.self_attn.to_k.weight": 0.0018136160714285715,
197
+ "transformer.blocks.17.self_attn.to_out.0.weight": 0.0013776506696428572,
198
+ "transformer.blocks.17.self_attn.to_q.weight": 0.0021885463169642855,
199
+ "transformer.blocks.17.self_attn.to_v.weight": 0.0007978166852678571,
200
+ "transformer.blocks.18.cross_attn.to_k.weight": 0.000885009765625,
201
+ "transformer.blocks.18.cross_attn.to_out.0.weight": 0.0020839146205357145,
202
+ "transformer.blocks.18.cross_attn.to_q.weight": 0.0012119838169642857,
203
+ "transformer.blocks.18.cross_attn.to_v.weight": 0.0007542201450892857,
204
+ "transformer.blocks.18.ffn.ff.0.weight": 0.0018223353794642857,
205
+ "transformer.blocks.18.ffn.ff.3.weight": 0.00634765625,
206
+ "transformer.blocks.18.self_attn.to_k.weight": 0.0021275111607142855,
207
+ "transformer.blocks.18.self_attn.to_out.0.weight": 0.0017613002232142857,
208
+ "transformer.blocks.18.self_attn.to_q.weight": 0.002406529017857143,
209
+ "transformer.blocks.18.self_attn.to_v.weight": 0.00091552734375,
210
+ "transformer.blocks.19.cross_attn.to_k.weight": 0.0008893694196428571,
211
+ "transformer.blocks.19.cross_attn.to_out.0.weight": 0.0026681082589285715,
212
+ "transformer.blocks.19.cross_attn.to_q.weight": 0.0010419573102678572,
213
+ "transformer.blocks.19.cross_attn.to_v.weight": 0.000762939453125,
214
+ "transformer.blocks.19.ffn.ff.0.weight": 0.0013166155133928572,
215
+ "transformer.blocks.19.ffn.ff.3.weight": 0.0013514927455357143,
216
+ "transformer.blocks.19.self_attn.to_k.weight": 0.0016653878348214285,
217
+ "transformer.blocks.19.self_attn.to_out.0.weight": 0.0019182477678571428,
218
+ "transformer.blocks.19.self_attn.to_q.weight": 0.0028250558035714285,
219
+ "transformer.blocks.19.self_attn.to_v.weight": 0.0008893694196428571,
220
+ "transformer.blocks.2.cross_attn.to_k.weight": 0.0009722028459821429,
221
+ "transformer.blocks.2.cross_attn.to_out.0.weight": 0.0015171595982142857,
222
+ "transformer.blocks.2.cross_attn.to_q.weight": 0.0012555803571428572,
223
+ "transformer.blocks.2.cross_attn.to_v.weight": 0.0009111676897321429,
224
+ "transformer.blocks.2.ffn.ff.0.weight": 0.0011160714285714285,
225
+ "transformer.blocks.2.ffn.ff.3.weight": 0.0012991768973214285,
226
+ "transformer.blocks.2.self_attn.to_k.weight": 0.0011945452008928572,
227
+ "transformer.blocks.2.self_attn.to_out.0.weight": 0.0011945452008928572,
228
+ "transformer.blocks.2.self_attn.to_q.weight": 0.0011509486607142857,
229
+ "transformer.blocks.2.self_attn.to_v.weight": 0.0006234305245535714,
230
+ "transformer.blocks.20.cross_attn.to_k.weight": 0.0009809221540178572,
231
+ "transformer.blocks.20.cross_attn.to_out.0.weight": 0.009626116071428572,
232
+ "transformer.blocks.20.cross_attn.to_q.weight": 0.0012642996651785715,
233
+ "transformer.blocks.20.cross_attn.to_v.weight": 0.0011945452008928572,
234
+ "transformer.blocks.20.ffn.ff.0.weight": 0.0018136160714285715,
235
+ "transformer.blocks.20.ffn.ff.3.weight": 0.0023193359375,
236
+ "transformer.blocks.20.self_attn.to_k.weight": 0.0015781947544642857,
237
+ "transformer.blocks.20.self_attn.to_out.0.weight": 0.0021275111607142855,
238
+ "transformer.blocks.20.self_attn.to_q.weight": 0.0021275111607142855,
239
+ "transformer.blocks.20.self_attn.to_v.weight": 0.0006626674107142857,
240
+ "transformer.blocks.21.cross_attn.to_k.weight": 0.00115966796875,
241
+ "transformer.blocks.21.cross_attn.to_out.0.weight": 0.010184151785714286,
242
+ "transformer.blocks.21.cross_attn.to_q.weight": 0.0009809221540178572,
243
+ "transformer.blocks.21.cross_attn.to_v.weight": 0.0008893694196428571,
244
+ "transformer.blocks.21.ffn.ff.0.weight": 0.0021275111607142855,
245
+ "transformer.blocks.21.ffn.ff.3.weight": 0.003016880580357143,
246
+ "transformer.blocks.21.self_attn.to_k.weight": 0.0018484933035714285,
247
+ "transformer.blocks.21.self_attn.to_out.0.weight": 0.002110072544642857,
248
+ "transformer.blocks.21.self_attn.to_q.weight": 0.002040318080357143,
249
+ "transformer.blocks.21.self_attn.to_v.weight": 0.0007716587611607143,
250
+ "transformer.blocks.22.cross_attn.to_k.weight": 0.0010114397321428572,
251
+ "transformer.blocks.22.cross_attn.to_out.0.weight": 0.010463169642857142,
252
+ "transformer.blocks.22.cross_attn.to_q.weight": 0.0011073521205357143,
253
+ "transformer.blocks.22.cross_attn.to_v.weight": 0.000823974609375,
254
+ "transformer.blocks.22.ffn.ff.0.weight": 0.0018397739955357143,
255
+ "transformer.blocks.22.ffn.ff.3.weight": 0.0033133370535714285,
256
+ "transformer.blocks.22.self_attn.to_k.weight": 0.00201416015625,
257
+ "transformer.blocks.22.self_attn.to_out.0.weight": 0.0019967215401785715,
258
+ "transformer.blocks.22.self_attn.to_q.weight": 0.0023367745535714285,
259
+ "transformer.blocks.22.self_attn.to_v.weight": 0.0009286063058035714,
260
+ "transformer.blocks.23.cross_attn.to_k.weight": 0.0010463169642857143,
261
+ "transformer.blocks.23.cross_attn.to_out.0.weight": 0.004446847098214286,
262
+ "transformer.blocks.23.cross_attn.to_q.weight": 0.0014299665178571428,
263
+ "transformer.blocks.23.cross_attn.to_v.weight": 0.0006801060267857143,
264
+ "transformer.blocks.23.ffn.ff.0.weight": 0.0014299665178571428,
265
+ "transformer.blocks.23.ffn.ff.3.weight": 0.0013863699776785715,
266
+ "transformer.blocks.23.self_attn.to_k.weight": 0.0016828264508928572,
267
+ "transformer.blocks.23.self_attn.to_out.0.weight": 0.002040318080357143,
268
+ "transformer.blocks.23.self_attn.to_q.weight": 0.0017351422991071428,
269
+ "transformer.blocks.23.self_attn.to_v.weight": 0.0009198869977678571,
270
+ "transformer.blocks.24.cross_attn.to_k.weight": 0.0011335100446428572,
271
+ "transformer.blocks.24.cross_attn.to_out.0.weight": 0.0025634765625,
272
+ "transformer.blocks.24.cross_attn.to_q.weight": 0.002284458705357143,
273
+ "transformer.blocks.24.cross_attn.to_v.weight": 0.0005754743303571429,
274
+ "transformer.blocks.24.ffn.ff.0.weight": 0.0015694754464285715,
275
+ "transformer.blocks.24.ffn.ff.3.weight": 0.00189208984375,
276
+ "transformer.blocks.24.self_attn.to_k.weight": 0.0016130719866071428,
277
+ "transformer.blocks.24.self_attn.to_out.0.weight": 0.0015520368303571428,
278
+ "transformer.blocks.24.self_attn.to_q.weight": 0.001708984375,
279
+ "transformer.blocks.24.self_attn.to_v.weight": 0.0008544921875,
280
+ "transformer.blocks.25.cross_attn.to_k.weight": 0.0013602120535714285,
281
+ "transformer.blocks.25.cross_attn.to_out.0.weight": 0.003574916294642857,
282
+ "transformer.blocks.25.cross_attn.to_q.weight": 0.0014735630580357143,
283
+ "transformer.blocks.25.cross_attn.to_v.weight": 0.00079345703125,
284
+ "transformer.blocks.25.ffn.ff.0.weight": 0.0013166155133928572,
285
+ "transformer.blocks.25.ffn.ff.3.weight": 0.0014212472098214285,
286
+ "transformer.blocks.25.self_attn.to_k.weight": 0.0021798270089285715,
287
+ "transformer.blocks.25.self_attn.to_out.0.weight": 0.0014386858258928572,
288
+ "transformer.blocks.25.self_attn.to_q.weight": 0.0017874581473214285,
289
+ "transformer.blocks.25.self_attn.to_v.weight": 0.00115966796875,
290
+ "transformer.blocks.26.cross_attn.to_k.weight": 0.0009242466517857143,
291
+ "transformer.blocks.26.cross_attn.to_out.0.weight": 0.0011683872767857143,
292
+ "transformer.blocks.26.cross_attn.to_q.weight": 0.0012991768973214285,
293
+ "transformer.blocks.26.cross_attn.to_v.weight": 0.0012032645089285715,
294
+ "transformer.blocks.26.ffn.ff.0.weight": 0.0016653878348214285,
295
+ "transformer.blocks.26.ffn.ff.3.weight": 0.0029994419642857145,
296
+ "transformer.blocks.26.self_attn.to_k.weight": 0.0017525809151785715,
297
+ "transformer.blocks.26.self_attn.to_out.0.weight": 0.0012904575892857143,
298
+ "transformer.blocks.26.self_attn.to_q.weight": 0.0015694754464285715,
299
+ "transformer.blocks.26.self_attn.to_v.weight": 0.0013776506696428572,
300
+ "transformer.blocks.27.cross_attn.to_k.weight": 0.0010811941964285715,
301
+ "transformer.blocks.27.cross_attn.to_out.0.weight": 0.008231026785714286,
302
+ "transformer.blocks.27.cross_attn.to_q.weight": 0.0016217912946428572,
303
+ "transformer.blocks.27.cross_attn.to_v.weight": 0.0007978166852678571,
304
+ "transformer.blocks.27.ffn.ff.0.weight": 0.0011858258928571428,
305
+ "transformer.blocks.27.ffn.ff.3.weight": 0.002894810267857143,
306
+ "transformer.blocks.27.self_attn.to_k.weight": 0.0011247907366071428,
307
+ "transformer.blocks.27.self_attn.to_out.0.weight": 0.002197265625,
308
+ "transformer.blocks.27.self_attn.to_q.weight": 0.0010899135044642857,
309
+ "transformer.blocks.27.self_attn.to_v.weight": 0.0006365094866071429,
310
+ "transformer.blocks.28.cross_attn.to_k.weight": 0.0009591238839285714,
311
+ "transformer.blocks.28.cross_attn.to_out.0.weight": 0.010602678571428572,
312
+ "transformer.blocks.28.cross_attn.to_q.weight": 0.0015956333705357143,
313
+ "transformer.blocks.28.cross_attn.to_v.weight": 0.0007062639508928571,
314
+ "transformer.blocks.28.ffn.ff.0.weight": 0.0017438616071428572,
315
+ "transformer.blocks.28.ffn.ff.3.weight": 0.004150390625,
316
+ "transformer.blocks.28.self_attn.to_k.weight": 0.0016915457589285715,
317
+ "transformer.blocks.28.self_attn.to_out.0.weight": 0.0020751953125,
318
+ "transformer.blocks.28.self_attn.to_q.weight": 0.0027029854910714285,
319
+ "transformer.blocks.28.self_attn.to_v.weight": 0.001007080078125,
320
+ "transformer.blocks.29.cross_attn.to_k.weight": 0.0009765625,
321
+ "transformer.blocks.29.cross_attn.to_out.0.weight": 0.012276785714285714,
322
+ "transformer.blocks.29.cross_attn.to_q.weight": 0.0008021763392857143,
323
+ "transformer.blocks.29.cross_attn.to_v.weight": 0.0010986328125,
324
+ "transformer.blocks.29.ffn.ff.0.weight": 0.0015607561383928572,
325
+ "transformer.blocks.29.ffn.ff.3.weight": 0.003871372767857143,
326
+ "transformer.blocks.29.self_attn.to_k.weight": 0.0019182477678571428,
327
+ "transformer.blocks.29.self_attn.to_out.0.weight": 0.0027901785714285715,
328
+ "transformer.blocks.29.self_attn.to_q.weight": 0.0018048967633928572,
329
+ "transformer.blocks.29.self_attn.to_v.weight": 0.0008544921875,
330
+ "transformer.blocks.3.cross_attn.to_k.weight": 0.0007978166852678571,
331
+ "transformer.blocks.3.cross_attn.to_out.0.weight": 0.0010332380022321428,
332
+ "transformer.blocks.3.cross_attn.to_q.weight": 0.0013602120535714285,
333
+ "transformer.blocks.3.cross_attn.to_v.weight": 0.0008021763392857143,
334
+ "transformer.blocks.3.ffn.ff.0.weight": 0.0010288783482142857,
335
+ "transformer.blocks.3.ffn.ff.3.weight": 0.001708984375,
336
+ "transformer.blocks.3.self_attn.to_k.weight": 0.0013950892857142857,
337
+ "transformer.blocks.3.self_attn.to_out.0.weight": 0.00115966796875,
338
+ "transformer.blocks.3.self_attn.to_q.weight": 0.0012730189732142857,
339
+ "transformer.blocks.3.self_attn.to_v.weight": 0.000762939453125,
340
+ "transformer.blocks.30.cross_attn.to_k.weight": 0.0008196149553571429,
341
+ "transformer.blocks.30.cross_attn.to_out.0.weight": 0.007952008928571428,
342
+ "transformer.blocks.30.cross_attn.to_q.weight": 0.0011422293526785715,
343
+ "transformer.blocks.30.cross_attn.to_v.weight": 0.0009809221540178572,
344
+ "transformer.blocks.30.ffn.ff.0.weight": 0.0016043526785714285,
345
+ "transformer.blocks.30.ffn.ff.3.weight": 0.002528599330357143,
346
+ "transformer.blocks.30.self_attn.to_k.weight": 0.0019356863839285715,
347
+ "transformer.blocks.30.self_attn.to_out.0.weight": 0.0017351422991071428,
348
+ "transformer.blocks.30.self_attn.to_q.weight": 0.0017002650669642857,
349
+ "transformer.blocks.30.self_attn.to_v.weight": 0.0013950892857142857,
350
+ "transformer.blocks.31.cross_attn.to_k.weight": 0.0006583077566964286,
351
+ "transformer.blocks.31.cross_attn.to_out.0.weight": 0.006870814732142857,
352
+ "transformer.blocks.31.cross_attn.to_q.weight": 0.0009809221540178572,
353
+ "transformer.blocks.31.cross_attn.to_v.weight": 0.0011683872767857143,
354
+ "transformer.blocks.31.ffn.ff.0.weight": 0.00152587890625,
355
+ "transformer.blocks.31.ffn.ff.3.weight": 0.0021187918526785715,
356
+ "transformer.blocks.31.self_attn.to_k.weight": 0.0019705636160714285,
357
+ "transformer.blocks.31.self_attn.to_out.0.weight": 0.0013340541294642857,
358
+ "transformer.blocks.31.self_attn.to_q.weight": 0.0018659319196428572,
359
+ "transformer.blocks.31.self_attn.to_v.weight": 0.0014997209821428572,
360
+ "transformer.blocks.4.cross_attn.to_k.weight": 0.000885009765625,
361
+ "transformer.blocks.4.cross_attn.to_out.0.weight": 0.0011683872767857143,
362
+ "transformer.blocks.4.cross_attn.to_q.weight": 0.0014474051339285715,
363
+ "transformer.blocks.4.cross_attn.to_v.weight": 0.0006626674107142857,
364
+ "transformer.blocks.4.ffn.ff.0.weight": 0.0012381417410714285,
365
+ "transformer.blocks.4.ffn.ff.3.weight": 0.0011247907366071428,
366
+ "transformer.blocks.4.self_attn.to_k.weight": 0.0016217912946428572,
367
+ "transformer.blocks.4.self_attn.to_out.0.weight": 0.000762939453125,
368
+ "transformer.blocks.4.self_attn.to_q.weight": 0.00164794921875,
369
+ "transformer.blocks.4.self_attn.to_v.weight": 0.0008675711495535714,
370
+ "transformer.blocks.5.cross_attn.to_k.weight": 0.0009547642299107143,
371
+ "transformer.blocks.5.cross_attn.to_out.0.weight": 0.0014561244419642857,
372
+ "transformer.blocks.5.cross_attn.to_q.weight": 0.0009111676897321429,
373
+ "transformer.blocks.5.cross_attn.to_v.weight": 0.0008675711495535714,
374
+ "transformer.blocks.5.ffn.ff.0.weight": 0.0012032645089285715,
375
+ "transformer.blocks.5.ffn.ff.3.weight": 0.0016566685267857143,
376
+ "transformer.blocks.5.self_attn.to_k.weight": 0.0014474051339285715,
377
+ "transformer.blocks.5.self_attn.to_out.0.weight": 0.0008501325334821429,
378
+ "transformer.blocks.5.self_attn.to_q.weight": 0.0015869140625,
379
+ "transformer.blocks.5.self_attn.to_v.weight": 0.0007760184151785714,
380
+ "transformer.blocks.6.cross_attn.to_k.weight": 0.0008588518415178571,
381
+ "transformer.blocks.6.cross_attn.to_out.0.weight": 0.0010114397321428572,
382
+ "transformer.blocks.6.cross_attn.to_q.weight": 0.0011335100446428572,
383
+ "transformer.blocks.6.cross_attn.to_v.weight": 0.001068115234375,
384
+ "transformer.blocks.6.ffn.ff.0.weight": 0.0012381417410714285,
385
+ "transformer.blocks.6.ffn.ff.3.weight": 0.0020926339285714285,
386
+ "transformer.blocks.6.self_attn.to_k.weight": 0.0011029924665178572,
387
+ "transformer.blocks.6.self_attn.to_out.0.weight": 0.000762939453125,
388
+ "transformer.blocks.6.self_attn.to_q.weight": 0.0016741071428571428,
389
+ "transformer.blocks.6.self_attn.to_v.weight": 0.0008501325334821429,
390
+ "transformer.blocks.7.cross_attn.to_k.weight": 0.0008283342633928571,
391
+ "transformer.blocks.7.cross_attn.to_out.0.weight": 0.0013602120535714285,
392
+ "transformer.blocks.7.cross_attn.to_q.weight": 0.0007760184151785714,
393
+ "transformer.blocks.7.cross_attn.to_v.weight": 0.0009329659598214286,
394
+ "transformer.blocks.7.ffn.ff.0.weight": 0.0016392299107142857,
395
+ "transformer.blocks.7.ffn.ff.3.weight": 0.00244140625,
396
+ "transformer.blocks.7.self_attn.to_k.weight": 0.0017525809151785715,
397
+ "transformer.blocks.7.self_attn.to_out.0.weight": 0.0008675711495535714,
398
+ "transformer.blocks.7.self_attn.to_q.weight": 0.001708984375,
399
+ "transformer.blocks.7.self_attn.to_v.weight": 0.0010724748883928572,
400
+ "transformer.blocks.8.cross_attn.to_k.weight": 0.0007716587611607143,
401
+ "transformer.blocks.8.cross_attn.to_out.0.weight": 0.0013078962053571428,
402
+ "transformer.blocks.8.cross_attn.to_q.weight": 0.0008632114955357143,
403
+ "transformer.blocks.8.cross_attn.to_v.weight": 0.0009416852678571429,
404
+ "transformer.blocks.8.ffn.ff.0.weight": 0.0012381417410714285,
405
+ "transformer.blocks.8.ffn.ff.3.weight": 0.001953125,
406
+ "transformer.blocks.8.self_attn.to_k.weight": 0.0011422293526785715,
407
+ "transformer.blocks.8.self_attn.to_out.0.weight": 0.0008021763392857143,
408
+ "transformer.blocks.8.self_attn.to_q.weight": 0.0015171595982142857,
409
+ "transformer.blocks.8.self_attn.to_v.weight": 0.0012119838169642857,
410
+ "transformer.blocks.9.cross_attn.to_k.weight": 0.0008326939174107143,
411
+ "transformer.blocks.9.cross_attn.to_out.0.weight": 0.0008588518415178571,
412
+ "transformer.blocks.9.cross_attn.to_q.weight": 0.0007803780691964286,
413
+ "transformer.blocks.9.cross_attn.to_v.weight": 0.0006321498325892857,
414
+ "transformer.blocks.9.ffn.ff.0.weight": 0.0016130719866071428,
415
+ "transformer.blocks.9.ffn.ff.3.weight": 0.0023018973214285715,
416
+ "transformer.blocks.9.self_attn.to_k.weight": 0.00128173828125,
417
+ "transformer.blocks.9.self_attn.to_out.0.weight": 0.0006495884486607143,
418
+ "transformer.blocks.9.self_attn.to_q.weight": 0.0014212472098214285,
419
+ "transformer.blocks.9.self_attn.to_v.weight": 0.0007716587611607143,
420
+ "transformer.input_embed.proj.0.weight": 0.00029427664620535713,
421
+ "transformer.input_embed.proj.2.weight": 0.00032479422433035713,
422
+ "transformer.latent_cond_embedder.proj.0.weight": 0.000732421875,
423
+ "transformer.latent_cond_embedder.proj.2.weight": 0.0024239676339285715,
424
+ "transformer.latent_embed.proj.0.weight": 0.0004730224609375,
425
+ "transformer.latent_embed.proj.2.weight": 0.00037057059151785713,
426
+ "transformer.norm_out.linear.weight": 0.0009286063058035714,
427
+ "transformer.proj_out.weight": 0.0003880092075892857,
428
+ "transformer.text_conv_layer.0.dwconv.weight": 0.0015171595982142857,
429
+ "transformer.text_conv_layer.0.grn.beta": 0.0008632114955357143,
430
+ "transformer.text_conv_layer.0.grn.gamma": 0.0010986328125,
431
+ "transformer.text_conv_layer.0.pwconv1.weight": 0.0011509486607142857,
432
+ "transformer.text_conv_layer.0.pwconv2.weight": 0.00164794921875,
433
+ "transformer.text_conv_layer.1.dwconv.weight": 0.0023018973214285715,
434
+ "transformer.text_conv_layer.1.grn.beta": 0.0006321498325892857,
435
+ "transformer.text_conv_layer.1.grn.gamma": 0.0011858258928571428,
436
+ "transformer.text_conv_layer.1.pwconv1.weight": 0.0012119838169642857,
437
+ "transformer.text_conv_layer.1.pwconv2.weight": 0.0017787388392857143,
438
+ "transformer.text_conv_layer.2.dwconv.weight": 0.0026157924107142855,
439
+ "transformer.text_conv_layer.2.grn.beta": 0.000579833984375,
440
+ "transformer.text_conv_layer.2.grn.gamma": 0.0012642996651785715,
441
+ "transformer.text_conv_layer.2.pwconv1.weight": 0.0013253348214285715,
442
+ "transformer.text_conv_layer.2.pwconv2.weight": 0.0021449497767857145,
443
+ "transformer.text_conv_layer.3.dwconv.weight": 0.002685546875,
444
+ "transformer.text_conv_layer.3.grn.beta": 0.00040762765066964287,
445
+ "transformer.text_conv_layer.3.grn.gamma": 0.0016043526785714285,
446
+ "transformer.text_conv_layer.3.pwconv1.weight": 0.0015869140625,
447
+ "transformer.text_conv_layer.3.pwconv2.weight": 0.0027901785714285715,
448
+ "transformer.text_embed.proj.0.weight": 0.0004795619419642857,
449
+ "transformer.text_embed.proj.2.weight": 0.0015869140625,
450
+ "transformer.time_embed.time_mlp.0.weight": 0.0006277901785714286,
451
+ "transformer.time_embed.time_mlp.2.weight": 0.0014822823660714285,
452
+ "vae.decoder.layers.0.weight_g": 0.0021536690848214285,
453
+ "vae.decoder.layers.0.weight_v": 0.002528599330357143,
454
+ "vae.decoder.layers.1.layers.1.weight_g": 0.003208705357142857,
455
+ "vae.decoder.layers.1.layers.1.weight_v": 0.0023890904017857145,
456
+ "vae.decoder.layers.1.layers.2.layers.1.weight_g": 0.0029820033482142855,
457
+ "vae.decoder.layers.1.layers.2.layers.1.weight_v": 0.0017264229910714285,
458
+ "vae.decoder.layers.1.layers.2.layers.3.weight_g": 0.0027901785714285715,
459
+ "vae.decoder.layers.1.layers.2.layers.3.weight_v": 0.0016392299107142857,
460
+ "vae.decoder.layers.1.layers.3.layers.1.weight_g": 0.0032784598214285715,
461
+ "vae.decoder.layers.1.layers.3.layers.1.weight_v": 0.0024239676339285715,
462
+ "vae.decoder.layers.1.layers.3.layers.3.weight_g": 0.0031215122767857145,
463
+ "vae.decoder.layers.1.layers.3.layers.3.weight_v": 0.0011422293526785715,
464
+ "vae.decoder.layers.1.layers.4.layers.1.weight_g": 0.0020751953125,
465
+ "vae.decoder.layers.1.layers.4.layers.1.weight_v": 0.0009373256138392857,
466
+ "vae.decoder.layers.1.layers.4.layers.3.weight_g": 0.0029994419642857145,
467
+ "vae.decoder.layers.1.layers.4.layers.3.weight_v": 0.0011117117745535715,
468
+ "vae.decoder.layers.2.layers.1.weight_g": 0.003923688616071429,
469
+ "vae.decoder.layers.2.layers.1.weight_v": 0.002197265625,
470
+ "vae.decoder.layers.2.layers.2.layers.1.weight_g": 0.0029820033482142855,
471
+ "vae.decoder.layers.2.layers.2.layers.1.weight_v": 0.0011683872767857143,
472
+ "vae.decoder.layers.2.layers.2.layers.3.weight_g": 0.0028773716517857145,
473
+ "vae.decoder.layers.2.layers.2.layers.3.weight_v": 0.0010855538504464285,
474
+ "vae.decoder.layers.2.layers.3.layers.1.weight_g": 0.002720424107142857,
475
+ "vae.decoder.layers.2.layers.3.layers.1.weight_v": 0.0008501325334821429,
476
+ "vae.decoder.layers.2.layers.3.layers.3.weight_g": 0.0031040736607142855,
477
+ "vae.decoder.layers.2.layers.3.layers.3.weight_v": 0.0013078962053571428,
478
+ "vae.decoder.layers.2.layers.4.layers.1.weight_g": 0.002528599330357143,
479
+ "vae.decoder.layers.2.layers.4.layers.1.weight_v": 0.0012991768973214285,
480
+ "vae.decoder.layers.2.layers.4.layers.3.weight_g": 0.003208705357142857,
481
+ "vae.decoder.layers.2.layers.4.layers.3.weight_v": 0.0010768345424107143,
482
+ "vae.decoder.layers.3.layers.1.weight_g": 0.0029471261160714285,
483
+ "vae.decoder.layers.3.layers.1.weight_v": 0.0018833705357142857,
484
+ "vae.decoder.layers.3.layers.2.layers.1.weight_g": 0.002162388392857143,
485
+ "vae.decoder.layers.3.layers.2.layers.1.weight_v": 0.0007498604910714286,
486
+ "vae.decoder.layers.3.layers.2.layers.3.weight_g": 0.002528599330357143,
487
+ "vae.decoder.layers.3.layers.2.layers.3.weight_v": 0.0007237025669642857,
488
+ "vae.decoder.layers.3.layers.3.layers.1.weight_g": 0.0032784598214285715,
489
+ "vae.decoder.layers.3.layers.3.layers.1.weight_v": 0.0007542201450892857,
490
+ "vae.decoder.layers.3.layers.3.layers.3.weight_g": 0.0037144252232142855,
491
+ "vae.decoder.layers.3.layers.3.layers.3.weight_v": 0.0007847377232142857,
492
+ "vae.decoder.layers.3.layers.4.layers.1.weight_g": 0.002720424107142857,
493
+ "vae.decoder.layers.3.layers.4.layers.1.weight_v": 0.0010855538504464285,
494
+ "vae.decoder.layers.3.layers.4.layers.3.weight_g": 0.0026681082589285715,
495
+ "vae.decoder.layers.3.layers.4.layers.3.weight_v": 0.0009504045758928571,
496
+ "vae.decoder.layers.4.layers.1.weight_g": 0.0020926339285714285,
497
+ "vae.decoder.layers.4.layers.1.weight_v": 0.0008980887276785714,
498
+ "vae.decoder.layers.4.layers.2.layers.1.weight_g": 0.002406529017857143,
499
+ "vae.decoder.layers.4.layers.2.layers.1.weight_v": 0.0006059919084821429,
500
+ "vae.decoder.layers.4.layers.2.layers.3.weight_g": 0.0019444056919642857,
501
+ "vae.decoder.layers.4.layers.2.layers.3.weight_v": 0.0008980887276785714,
502
+ "vae.decoder.layers.4.layers.3.layers.1.weight_g": 0.0022495814732142855,
503
+ "vae.decoder.layers.4.layers.3.layers.1.weight_v": 0.0008021763392857143,
504
+ "vae.decoder.layers.4.layers.3.layers.3.weight_g": 0.0020751953125,
505
+ "vae.decoder.layers.4.layers.3.layers.3.weight_v": 0.0007803780691964286,
506
+ "vae.decoder.layers.4.layers.4.layers.1.weight_g": 0.002528599330357143,
507
+ "vae.decoder.layers.4.layers.4.layers.1.weight_v": 0.0006059919084821429,
508
+ "vae.decoder.layers.4.layers.4.layers.3.weight_g": 0.003086635044642857,
509
+ "vae.decoder.layers.4.layers.4.layers.3.weight_v": 0.0009940011160714285,
510
+ "vae.decoder.layers.5.layers.1.weight_g": 0.0013689313616071428,
511
+ "vae.decoder.layers.5.layers.1.weight_v": 0.0005558558872767857,
512
+ "vae.decoder.layers.5.layers.2.layers.1.weight_g": 0.0025634765625,
513
+ "vae.decoder.layers.5.layers.2.layers.1.weight_v": 0.0005449567522321429,
514
+ "vae.decoder.layers.5.layers.2.layers.3.weight_g": 0.0023193359375,
515
+ "vae.decoder.layers.5.layers.2.layers.3.weight_v": 0.0006931849888392857,
516
+ "vae.decoder.layers.5.layers.3.layers.1.weight_g": 0.0020839146205357145,
517
+ "vae.decoder.layers.5.layers.3.layers.1.weight_v": 0.0005362374441964286,
518
+ "vae.decoder.layers.5.layers.3.layers.3.weight_g": 0.0020054408482142855,
519
+ "vae.decoder.layers.5.layers.3.layers.3.weight_v": 0.0009068080357142857,
520
+ "vae.decoder.layers.5.layers.4.layers.1.weight_g": 0.002040318080357143,
521
+ "vae.decoder.layers.5.layers.4.layers.1.weight_v": 0.0008152553013392857,
522
+ "vae.decoder.layers.5.layers.4.layers.3.weight_g": 0.0016653878348214285,
523
+ "vae.decoder.layers.5.layers.4.layers.3.weight_v": 0.0013950892857142857,
524
+ "vae.decoder.layers.7.weight_g": 1.0132789611816406e-06,
525
+ "vae.decoder.layers.7.weight_v": 0.00015803745814732144,
526
+ "vae.encoder.layers.0.weight_g": 0.0031215122767857145,
527
+ "vae.encoder.layers.0.weight_v": 0.0011683872767857143,
528
+ "vae.encoder.layers.1.layers.0.layers.1.weight_g": 0.002354213169642857,
529
+ "vae.encoder.layers.1.layers.0.layers.1.weight_v": 0.00067138671875,
530
+ "vae.encoder.layers.1.layers.0.layers.3.weight_g": 0.0014299665178571428,
531
+ "vae.encoder.layers.1.layers.0.layers.3.weight_v": 0.0005754743303571429,
532
+ "vae.encoder.layers.1.layers.1.layers.1.weight_g": 0.0014822823660714285,
533
+ "vae.encoder.layers.1.layers.1.layers.1.weight_v": 0.0004795619419642857,
534
+ "vae.encoder.layers.1.layers.1.layers.3.weight_g": 0.0019444056919642857,
535
+ "vae.encoder.layers.1.layers.1.layers.3.weight_v": 0.0004664829799107143,
536
+ "vae.encoder.layers.1.layers.2.layers.1.weight_g": 0.00164794921875,
537
+ "vae.encoder.layers.1.layers.2.layers.1.weight_v": 0.0004991803850446429,
538
+ "vae.encoder.layers.1.layers.2.layers.3.weight_g": 0.0015781947544642857,
539
+ "vae.encoder.layers.1.layers.2.layers.3.weight_v": 0.00047520228794642856,
540
+ "vae.encoder.layers.1.layers.4.weight_g": 0.0013950892857142857,
541
+ "vae.encoder.layers.1.layers.4.weight_v": 0.00034659249441964287,
542
+ "vae.encoder.layers.2.layers.0.layers.1.weight_g": 0.0015433175223214285,
543
+ "vae.encoder.layers.2.layers.0.layers.1.weight_v": 0.0004991803850446429,
544
+ "vae.encoder.layers.2.layers.0.layers.3.weight_g": 0.0018397739955357143,
545
+ "vae.encoder.layers.2.layers.0.layers.3.weight_v": 0.0004926409040178571,
546
+ "vae.encoder.layers.2.layers.1.layers.1.weight_g": 0.0015607561383928572,
547
+ "vae.encoder.layers.2.layers.1.layers.1.weight_v": 0.0007890973772321429,
548
+ "vae.encoder.layers.2.layers.1.layers.3.weight_g": 0.0021449497767857145,
549
+ "vae.encoder.layers.2.layers.1.layers.3.weight_v": 0.0005623953683035714,
550
+ "vae.encoder.layers.2.layers.2.layers.1.weight_g": 0.0018484933035714285,
551
+ "vae.encoder.layers.2.layers.2.layers.1.weight_v": 0.0006365094866071429,
552
+ "vae.encoder.layers.2.layers.2.layers.3.weight_g": 0.002354213169642857,
553
+ "vae.encoder.layers.2.layers.2.layers.3.weight_v": 0.0005536760602678571,
554
+ "vae.encoder.layers.2.layers.4.weight_g": 0.0014299665178571428,
555
+ "vae.encoder.layers.2.layers.4.weight_v": 0.0005166190011160714,
556
+ "vae.encoder.layers.3.layers.0.layers.1.weight_g": 0.001708984375,
557
+ "vae.encoder.layers.3.layers.0.layers.1.weight_v": 0.0007455008370535714,
558
+ "vae.encoder.layers.3.layers.0.layers.3.weight_g": 0.0028773716517857145,
559
+ "vae.encoder.layers.3.layers.0.layers.3.weight_v": 0.0005711146763392857,
560
+ "vae.encoder.layers.3.layers.1.layers.1.weight_g": 0.0016305106026785715,
561
+ "vae.encoder.layers.3.layers.1.layers.1.weight_v": 0.0009242466517857143,
562
+ "vae.encoder.layers.3.layers.1.layers.3.weight_g": 0.0025634765625,
563
+ "vae.encoder.layers.3.layers.1.layers.3.weight_v": 0.0006277901785714286,
564
+ "vae.encoder.layers.3.layers.2.layers.1.weight_g": 0.0017438616071428572,
565
+ "vae.encoder.layers.3.layers.2.layers.1.weight_v": 0.000946044921875,
566
+ "vae.encoder.layers.3.layers.2.layers.3.weight_g": 0.0022147042410714285,
567
+ "vae.encoder.layers.3.layers.2.layers.3.weight_v": 0.0005318777901785714,
568
+ "vae.encoder.layers.3.layers.4.weight_g": 0.0017002650669642857,
569
+ "vae.encoder.layers.3.layers.4.weight_v": 0.0010811941964285715,
570
+ "vae.encoder.layers.4.layers.0.layers.1.weight_g": 0.0017787388392857143,
571
+ "vae.encoder.layers.4.layers.0.layers.1.weight_v": 0.0010855538504464285,
572
+ "vae.encoder.layers.4.layers.0.layers.3.weight_g": 0.0025460379464285715,
573
+ "vae.encoder.layers.4.layers.0.layers.3.weight_v": 0.0010114397321428572,
574
+ "vae.encoder.layers.4.layers.1.layers.1.weight_g": 0.0018310546875,
575
+ "vae.encoder.layers.4.layers.1.layers.1.weight_v": 0.0010288783482142857,
576
+ "vae.encoder.layers.4.layers.1.layers.3.weight_g": 0.0022670200892857145,
577
+ "vae.encoder.layers.4.layers.1.layers.3.weight_v": 0.0006059919084821429,
578
+ "vae.encoder.layers.4.layers.2.layers.1.weight_g": 0.002110072544642857,
579
+ "vae.encoder.layers.4.layers.2.layers.1.weight_v": 0.0011335100446428572,
580
+ "vae.encoder.layers.4.layers.2.layers.3.weight_g": 0.002842494419642857,
581
+ "vae.encoder.layers.4.layers.2.layers.3.weight_v": 0.0006321498325892857,
582
+ "vae.encoder.layers.4.layers.4.weight_g": 0.0015781947544642857,
583
+ "vae.encoder.layers.4.layers.4.weight_v": 0.0019705636160714285,
584
+ "vae.encoder.layers.5.layers.0.layers.1.weight_g": 0.0022059849330357145,
585
+ "vae.encoder.layers.5.layers.0.layers.1.weight_v": 0.0010899135044642857,
586
+ "vae.encoder.layers.5.layers.0.layers.3.weight_g": 0.002685546875,
587
+ "vae.encoder.layers.5.layers.0.layers.3.weight_v": 0.0010332380022321428,
588
+ "vae.encoder.layers.5.layers.1.layers.1.weight_g": 0.002528599330357143,
589
+ "vae.encoder.layers.5.layers.1.layers.1.weight_v": 0.0016915457589285715,
590
+ "vae.encoder.layers.5.layers.1.layers.3.weight_g": 0.0028076171875,
591
+ "vae.encoder.layers.5.layers.1.layers.3.weight_v": 0.0010506766183035715,
592
+ "vae.encoder.layers.5.layers.2.layers.1.weight_g": 0.003138950892857143,
593
+ "vae.encoder.layers.5.layers.2.layers.1.weight_v": 0.0013689313616071428,
594
+ "vae.encoder.layers.5.layers.2.layers.3.weight_g": 0.0027553013392857145,
595
+ "vae.encoder.layers.5.layers.2.layers.3.weight_v": 0.0011073521205357143,
596
+ "vae.encoder.layers.5.layers.4.weight_g": 0.0012381417410714285,
597
+ "vae.encoder.layers.5.layers.4.weight_v": 0.00128173828125,
598
+ "vae.encoder.layers.6.weight_g": 0.0019356863839285715,
599
+ "vae.encoder.layers.6.weight_v": 0.0009024483816964286
600
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07dbc962ceae00333505c1daf649e4bd15709168f7295cc01bd750813c193085
3
+ size 3836215977