<
   ir_version: 10,
   opset_import: ["" : 23],
   producer_name: "pytorch"
>
main_graph (uint8[batch,224,224,3] image) => (float[batch,768] image_embedding) 
   <
      float[batch,257,1024] add_1088
      float[batch,257,1024] add_1109
      float[batch,257,1024] add_1224
      float[batch,257,1024] add_1245
      float[batch,257,1024] add_136
      float[batch,257,1024] add_1360
      float[batch,257,1024] add_1381
      float[batch,257,1024] add_1496
      float[batch,257,1024] add_1517
      float[batch,257,1024] add_157
      float[batch,257,1024] add_1632
      float[batch,257,1024] add_1653
      float[batch,257,1024] add_17
      float[batch,257,1024] add_1768
      float[batch,257,1024] add_1789
      float[batch,257,1024] add_1904
      float[batch,257,1024] add_1925
      float[batch,257,1024] add_2040
      float[batch,257,1024] add_2061
      float[batch,257,1024] add_2176
      float[batch,257,1024] add_2197
      float[batch,257,1024] add_2312
      float[batch,257,1024] add_2333
      float[batch,257,1024] add_2448
      float[batch,257,1024] add_2469
      float[batch,257,1024] add_2584
      float[batch,257,1024] add_2605
      float[batch,257,1024] add_272
      float[batch,257,1024] add_2720
      float[batch,257,1024] add_2741
      float[batch,257,1024] add_2856
      float[batch,257,1024] add_2877
      float[batch,257,1024] add_293
      float[batch,257,1024] add_2992
      float[batch,257,1024] add_3013
      float[batch,257,1024] add_3128
      float[batch,257,1024] add_3149
      float[batch,1,1024] add_3149_pooled
      float[batch,1,1024] add_3264
      float[batch,1,1024] add_3285
      float[batch,257,1024] add_408
      float[batch,257,1024] add_429
      float[batch,257,1024] add_544
      float[batch,257,1024] add_565
      float[batch,257,1024] add_680
      float[batch,257,1024] add_701
      float[batch,257,1024] add_816
      float[batch,257,1024] add_837
      float[batch,257,1024] add_952
      float[batch,257,1024] add_973
      float[batch,1] clamp_min
      float[batch,1024,16,16] conv2d
      float[batch,257,4096] gelu
      float[batch,257,4096] gelu_1
      float[batch,257,4096] gelu_10
      float[batch,257,4096] gelu_11
      float[batch,257,4096] gelu_12
      float[batch,257,4096] gelu_13
      float[batch,257,4096] gelu_14
      float[batch,257,4096] gelu_15
      float[batch,257,4096] gelu_16
      float[batch,257,4096] gelu_17
      float[batch,257,4096] gelu_18
      float[batch,257,4096] gelu_19
      float[batch,257,4096] gelu_2
      float[batch,257,4096] gelu_20
      float[batch,257,4096] gelu_21
      float[batch,257,4096] gelu_22
      float[batch,1,4096] gelu_23
      float[batch,257,4096] gelu_3
      float[batch,257,4096] gelu_4
      float[batch,257,4096] gelu_5
      float[batch,257,4096] gelu_6
      float[batch,257,4096] gelu_7
      float[batch,257,4096] gelu_8
      float[batch,257,4096] gelu_9
      float[batch,3,224,224] image_chw
      float[batch,224,224,3] image_f32
      float[batch,257,1024] layer_norm
      float[batch,257,1024] layer_norm_1
      float[batch,257,1024] layer_norm_10
      float[batch,257,1024] layer_norm_11
      float[batch,257,1024] layer_norm_12
      float[batch,257,1024] layer_norm_13
      float[batch,257,1024] layer_norm_14
      float[batch,257,1024] layer_norm_15
      float[batch,257,1024] layer_norm_16
      float[batch,257,1024] layer_norm_17
      float[batch,257,1024] layer_norm_18
      float[batch,257,1024] layer_norm_19
      float[batch,257,1024] layer_norm_2
      float[batch,257,1024] layer_norm_20
      float[batch,257,1024] layer_norm_21
      float[batch,257,1024] layer_norm_22
      float[batch,257,1024] layer_norm_23
      float[batch,257,1024] layer_norm_24
      float[batch,257,1024] layer_norm_25
      float[batch,257,1024] layer_norm_26
      float[batch,257,1024] layer_norm_27
      float[batch,257,1024] layer_norm_28
      float[batch,257,1024] layer_norm_29
      float[batch,257,1024] layer_norm_3
      float[batch,257,1024] layer_norm_30
      float[batch,257,1024] layer_norm_31
      float[batch,257,1024] layer_norm_32
      float[batch,257,1024] layer_norm_33
      float[batch,257,1024] layer_norm_34
      float[batch,257,1024] layer_norm_35
      float[batch,257,1024] layer_norm_36
      float[batch,257,1024] layer_norm_37
      float[batch,257,1024] layer_norm_38
      float[batch,257,1024] layer_norm_39
      float[batch,257,1024] layer_norm_4
      float[batch,257,1024] layer_norm_40
      float[batch,257,1024] layer_norm_41
      float[batch,257,1024] layer_norm_42
      float[batch,257,1024] layer_norm_43
      float[batch,257,1024] layer_norm_44
      float[batch,257,1024] layer_norm_45
      float[batch,257,1024] layer_norm_46
      float[batch,257,1024] layer_norm_47
      float[batch,1,1024] layer_norm_48
      float[batch,257,1024] layer_norm_5
      float[batch,257,1024] layer_norm_6
      float[batch,257,1024] layer_norm_7
      float[batch,257,1024] layer_norm_8
      float[batch,257,1024] layer_norm_9
      float[batch,1] linalg_vector_norm
      float[batch,257,4096] linear_10
      float[batch,257,1024] linear_11
      float[batch,257,4096] linear_14
      float[batch,257,1024] linear_15
      float[batch,257,4096] linear_18
      float[batch,257,1024] linear_19
      float[batch,257,4096] linear_2
      float[batch,257,4096] linear_22
      float[batch,257,1024] linear_23
      float[batch,257,4096] linear_26
      float[batch,257,1024] linear_27
      float[batch,257,1024] linear_3
      float[batch,257,4096] linear_30
      float[batch,257,1024] linear_31
      float[batch,257,4096] linear_34
      float[batch,257,1024] linear_35
      float[batch,257,4096] linear_38
      float[batch,257,1024] linear_39
      float[batch,257,4096] linear_42
      float[batch,257,1024] linear_43
      float[batch,257,4096] linear_46
      float[batch,257,1024] linear_47
      float[batch,257,4096] linear_50
      float[batch,257,1024] linear_51
      float[batch,257,4096] linear_54
      float[batch,257,1024] linear_55
      float[batch,257,4096] linear_58
      float[batch,257,1024] linear_59
      float[batch,257,4096] linear_6
      float[batch,257,4096] linear_62
      float[batch,257,1024] linear_63
      float[batch,257,4096] linear_66
      float[batch,257,1024] linear_67
      float[batch,257,1024] linear_7
      float[batch,257,4096] linear_70
      float[batch,257,1024] linear_71
      float[batch,257,4096] linear_74
      float[batch,257,1024] linear_75
      float[batch,257,4096] linear_78
      float[batch,257,1024] linear_79
      float[batch,257,4096] linear_82
      float[batch,257,1024] linear_83
      float[batch,257,4096] linear_86
      float[batch,257,1024] linear_87
      float[batch,257,4096] linear_90
      float[batch,257,1024] linear_91
      float[batch,1,4096] linear_94
      float[batch,1,1024] linear_95
      float[batch,768] matmul
      float[batch,257,1024] node_scaled_dot_product_attention_10_k
      float[batch,257,1024] node_scaled_dot_product_attention_10_out
      float[batch,257,1024] node_scaled_dot_product_attention_10_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_10_q
      float[batch,257,3072] node_scaled_dot_product_attention_10_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_10_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_10_v
      float[batch,257,1024] node_scaled_dot_product_attention_11_k
      float[batch,257,1024] node_scaled_dot_product_attention_11_out
      float[batch,257,1024] node_scaled_dot_product_attention_11_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_11_q
      float[batch,257,3072] node_scaled_dot_product_attention_11_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_11_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_11_v
      float[batch,257,1024] node_scaled_dot_product_attention_12_k
      float[batch,257,1024] node_scaled_dot_product_attention_12_out
      float[batch,257,1024] node_scaled_dot_product_attention_12_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_12_q
      float[batch,257,3072] node_scaled_dot_product_attention_12_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_12_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_12_v
      float[batch,257,1024] node_scaled_dot_product_attention_13_k
      float[batch,257,1024] node_scaled_dot_product_attention_13_out
      float[batch,257,1024] node_scaled_dot_product_attention_13_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_13_q
      float[batch,257,3072] node_scaled_dot_product_attention_13_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_13_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_13_v
      float[batch,257,1024] node_scaled_dot_product_attention_14_k
      float[batch,257,1024] node_scaled_dot_product_attention_14_out
      float[batch,257,1024] node_scaled_dot_product_attention_14_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_14_q
      float[batch,257,3072] node_scaled_dot_product_attention_14_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_14_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_14_v
      float[batch,257,1024] node_scaled_dot_product_attention_15_k
      float[batch,257,1024] node_scaled_dot_product_attention_15_out
      float[batch,257,1024] node_scaled_dot_product_attention_15_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_15_q
      float[batch,257,3072] node_scaled_dot_product_attention_15_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_15_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_15_v
      float[batch,257,1024] node_scaled_dot_product_attention_16_k
      float[batch,257,1024] node_scaled_dot_product_attention_16_out
      float[batch,257,1024] node_scaled_dot_product_attention_16_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_16_q
      float[batch,257,3072] node_scaled_dot_product_attention_16_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_16_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_16_v
      float[batch,257,1024] node_scaled_dot_product_attention_17_k
      float[batch,257,1024] node_scaled_dot_product_attention_17_out
      float[batch,257,1024] node_scaled_dot_product_attention_17_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_17_q
      float[batch,257,3072] node_scaled_dot_product_attention_17_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_17_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_17_v
      float[batch,257,1024] node_scaled_dot_product_attention_18_k
      float[batch,257,1024] node_scaled_dot_product_attention_18_out
      float[batch,257,1024] node_scaled_dot_product_attention_18_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_18_q
      float[batch,257,3072] node_scaled_dot_product_attention_18_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_18_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_18_v
      float[batch,257,1024] node_scaled_dot_product_attention_19_k
      float[batch,257,1024] node_scaled_dot_product_attention_19_out
      float[batch,257,1024] node_scaled_dot_product_attention_19_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_19_q
      float[batch,257,3072] node_scaled_dot_product_attention_19_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_19_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_19_v
      float[batch,257,1024] node_scaled_dot_product_attention_1_k
      float[batch,257,1024] node_scaled_dot_product_attention_1_out
      float[batch,257,1024] node_scaled_dot_product_attention_1_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_1_q
      float[batch,257,3072] node_scaled_dot_product_attention_1_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_1_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_1_v
      float[batch,257,1024] node_scaled_dot_product_attention_20_k
      float[batch,257,1024] node_scaled_dot_product_attention_20_out
      float[batch,257,1024] node_scaled_dot_product_attention_20_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_20_q
      float[batch,257,3072] node_scaled_dot_product_attention_20_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_20_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_20_v
      float[batch,257,1024] node_scaled_dot_product_attention_21_k
      float[batch,257,1024] node_scaled_dot_product_attention_21_out
      float[batch,257,1024] node_scaled_dot_product_attention_21_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_21_q
      float[batch,257,3072] node_scaled_dot_product_attention_21_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_21_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_21_v
      float[batch,257,1024] node_scaled_dot_product_attention_22_k
      float[batch,257,1024] node_scaled_dot_product_attention_22_out
      float[batch,257,1024] node_scaled_dot_product_attention_22_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_22_q
      float[batch,257,3072] node_scaled_dot_product_attention_22_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_22_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_22_v
      float[batch,257,1024] node_scaled_dot_product_attention_23_k
      float[batch,1,1024] node_scaled_dot_product_attention_23_out
      float[batch,1,1024] node_scaled_dot_product_attention_23_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_23_q
      float[batch,1,1024] node_scaled_dot_product_attention_23_q_pooled
      float[batch,257,3072] node_scaled_dot_product_attention_23_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_23_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_23_v
      float[batch,257,1024] node_scaled_dot_product_attention_2_k
      float[batch,257,1024] node_scaled_dot_product_attention_2_out
      float[batch,257,1024] node_scaled_dot_product_attention_2_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_2_q
      float[batch,257,3072] node_scaled_dot_product_attention_2_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_2_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_2_v
      float[batch,257,1024] node_scaled_dot_product_attention_3_k
      float[batch,257,1024] node_scaled_dot_product_attention_3_out
      float[batch,257,1024] node_scaled_dot_product_attention_3_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_3_q
      float[batch,257,3072] node_scaled_dot_product_attention_3_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_3_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_3_v
      float[batch,257,1024] node_scaled_dot_product_attention_4_k
      float[batch,257,1024] node_scaled_dot_product_attention_4_out
      float[batch,257,1024] node_scaled_dot_product_attention_4_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_4_q
      float[batch,257,3072] node_scaled_dot_product_attention_4_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_4_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_4_v
      float[batch,257,1024] node_scaled_dot_product_attention_5_k
      float[batch,257,1024] node_scaled_dot_product_attention_5_out
      float[batch,257,1024] node_scaled_dot_product_attention_5_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_5_q
      float[batch,257,3072] node_scaled_dot_product_attention_5_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_5_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_5_v
      float[batch,257,1024] node_scaled_dot_product_attention_6_k
      float[batch,257,1024] node_scaled_dot_product_attention_6_out
      float[batch,257,1024] node_scaled_dot_product_attention_6_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_6_q
      float[batch,257,3072] node_scaled_dot_product_attention_6_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_6_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_6_v
      float[batch,257,1024] node_scaled_dot_product_attention_7_k
      float[batch,257,1024] node_scaled_dot_product_attention_7_out
      float[batch,257,1024] node_scaled_dot_product_attention_7_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_7_q
      float[batch,257,3072] node_scaled_dot_product_attention_7_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_7_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_7_v
      float[batch,257,1024] node_scaled_dot_product_attention_8_k
      float[batch,257,1024] node_scaled_dot_product_attention_8_out
      float[batch,257,1024] node_scaled_dot_product_attention_8_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_8_q
      float[batch,257,3072] node_scaled_dot_product_attention_8_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_8_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_8_v
      float[batch,257,1024] node_scaled_dot_product_attention_9_k
      float[batch,257,1024] node_scaled_dot_product_attention_9_out
      float[batch,257,1024] node_scaled_dot_product_attention_9_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_9_q
      float[batch,257,3072] node_scaled_dot_product_attention_9_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_9_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_9_v
      float[batch,257,1024] node_scaled_dot_product_attention_k
      float[batch,257,1024] node_scaled_dot_product_attention_out
      float[batch,257,1024] node_scaled_dot_product_attention_out_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_q
      float[batch,257,3072] node_scaled_dot_product_attention_qkv
      float[batch,257,3072] node_scaled_dot_product_attention_qkv_mm_out
      float[batch,257,1024] node_scaled_dot_product_attention_v
      float[batch,256,1024] permute
      float[batch,257,1024] scaled_dot_product_attention
      float[batch,257,1024] scaled_dot_product_attention_1
      float[batch,257,1024] scaled_dot_product_attention_10
      float[batch,257,1024] scaled_dot_product_attention_11
      float[batch,257,1024] scaled_dot_product_attention_12
      float[batch,257,1024] scaled_dot_product_attention_13
      float[batch,257,1024] scaled_dot_product_attention_14
      float[batch,257,1024] scaled_dot_product_attention_15
      float[batch,257,1024] scaled_dot_product_attention_16
      float[batch,257,1024] scaled_dot_product_attention_17
      float[batch,257,1024] scaled_dot_product_attention_18
      float[batch,257,1024] scaled_dot_product_attention_19
      float[batch,257,1024] scaled_dot_product_attention_2
      float[batch,257,1024] scaled_dot_product_attention_20
      float[batch,257,1024] scaled_dot_product_attention_21
      float[batch,257,1024] scaled_dot_product_attention_22
      float[batch,1,1024] scaled_dot_product_attention_23
      float[batch,257,1024] scaled_dot_product_attention_3
      float[batch,257,1024] scaled_dot_product_attention_4
      float[batch,257,1024] scaled_dot_product_attention_5
      float[batch,257,1024] scaled_dot_product_attention_6
      float[batch,257,1024] scaled_dot_product_attention_7
      float[batch,257,1024] scaled_dot_product_attention_8
      float[batch,257,1024] scaled_dot_product_attention_9
      float[batch,1024] select_72
      float[batch,257,4096] val_100
      float[batch,257,1024] val_101
      float[batch,257,4096] val_102
      float[batch,257,1024] val_103
      float[batch,257,4096] val_104
      float[batch,257,1024] val_105
      float[batch,257,4096] val_106
      float[batch,257,1024] val_107
      float[batch,257,4096] val_108
      float[batch,257,1024] val_109
      float[batch,257,4096] val_110
      float[batch,257,1024] val_111
      float[batch,257,4096] val_112
      float[batch,257,1024] val_113
      float[batch,257,4096] val_114
      float[batch,257,1024] val_115
      float[batch,257,4096] val_116
      float[batch,257,1024] val_117
      float[batch,257,4096] val_118
      float[batch,257,1024] val_119
      float[batch,257,4096] val_120
      float[batch,257,1024] val_121
      float[batch,257,4096] val_122
      float[batch,257,1024] val_123
      float[batch,257,4096] val_124
      float[batch,257,1024] val_125
      float[batch,1,4096] val_126
      float[batch,1,1024] val_127
      float[batch,1024] val_128
      float[batch,257,1024] val_79
      float[batch,257,4096] val_80
      float[batch,257,1024] val_81
      float[batch,257,4096] val_82
      float[batch,257,1024] val_83
      float[batch,257,4096] val_84
      float[batch,257,1024] val_85
      float[batch,257,4096] val_86
      float[batch,257,1024] val_87
      float[batch,257,4096] val_88
      float[batch,257,1024] val_89
      float[batch,257,4096] val_90
      float[batch,257,1024] val_91
      float[batch,257,4096] val_92
      float[batch,257,1024] val_93
      float[batch,257,4096] val_94
      float[batch,257,1024] val_95
      float[batch,257,4096] val_96
      float[batch,257,1024] val_97
      float[batch,257,4096] val_98
      float[batch,257,1024] val_99
      float[batch,1024,256] view
   >
{
   [pre_cast] image_f32 = Cast <to: int = 1> (image)
   [pre_nhwc_to_nchw] image_chw = Transpose <perm: ints = [0, 3, 1, 2]> (image_f32)
   conv2d = Conv <auto_pad: string = "NOTSET", dilations: ints = [1, 1], group: int = 1, pads: ints = [0, 0, 0, 0], strides: ints = [14, 14]> (image_chw, "visual.conv1.weight", node_Conv_1352_fused_bias)
   view = Reshape <allowzero: int = 1> (conv2d, view_target)
   [node_permute] permute = Transpose <perm: ints = [0, 2, 1]> (view)
   val_79 = Pad (permute, val_3, val_4)
   add_17 = Add (val_79, val_78)
   [node_layer_norm] layer_norm = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_17, "visual.ln_pre.weight", "visual.ln_pre.bias")
   layer_norm_1 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (layer_norm, "visual.transformer.resblocks.0.ln_1.weight", "visual.transformer.resblocks.0.ln_1.bias")
   [node_scaled_dot_product_attention_qkv_mm] node_scaled_dot_product_attention_qkv_mm_out = MatMul (layer_norm_1, val_6)
   [node_scaled_dot_product_attention_qkv_bias] node_scaled_dot_product_attention_qkv = Add (node_scaled_dot_product_attention_qkv_mm_out, "visual.transformer.resblocks.0.attn.in_proj_bias")
   [node_scaled_dot_product_attention_qkv_split] node_scaled_dot_product_attention_q, node_scaled_dot_product_attention_k, node_scaled_dot_product_attention_v = Split <axis: int = -1> (node_scaled_dot_product_attention_qkv, attn3d_split_3x1024)
   [node_scaled_dot_product_attention] scaled_dot_product_attention = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_q, node_scaled_dot_product_attention_k, node_scaled_dot_product_attention_v)
   [node_scaled_dot_product_attention_out_mm] node_scaled_dot_product_attention_out_mm_out = MatMul (scaled_dot_product_attention, node_scaled_dot_product_attention_wo_t)
   [node_scaled_dot_product_attention_out_bias] node_scaled_dot_product_attention_out = Add (node_scaled_dot_product_attention_out_mm_out, "visual.transformer.resblocks.0.attn.out_proj.bias")
   add_136 = Add (layer_norm, node_scaled_dot_product_attention_out)
   layer_norm_2 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_136, "visual.transformer.resblocks.0.ln_2.weight", "visual.transformer.resblocks.0.ln_2.bias")
   val_80 = MatMul (layer_norm_2, val_7)
   linear_2 = Add (val_80, "visual.transformer.resblocks.0.mlp.c_fc.bias")
   [node_gelu] gelu = Gelu <approximate: string = "none"> (linear_2)
   val_81 = MatMul (gelu, val_8)
   linear_3 = Add (val_81, "visual.transformer.resblocks.0.mlp.c_proj.bias")
   add_157 = Add (add_136, linear_3)
   layer_norm_3 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_157, "visual.transformer.resblocks.1.ln_1.weight", "visual.transformer.resblocks.1.ln_1.bias")
   [node_scaled_dot_product_attention_1_qkv_mm] node_scaled_dot_product_attention_1_qkv_mm_out = MatMul (layer_norm_3, val_9)
   [node_scaled_dot_product_attention_1_qkv_bias] node_scaled_dot_product_attention_1_qkv = Add (node_scaled_dot_product_attention_1_qkv_mm_out, "visual.transformer.resblocks.1.attn.in_proj_bias")
   [node_scaled_dot_product_attention_1_qkv_split] node_scaled_dot_product_attention_1_q, node_scaled_dot_product_attention_1_k, node_scaled_dot_product_attention_1_v = Split <axis: int = -1> (node_scaled_dot_product_attention_1_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_1 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_1_q, node_scaled_dot_product_attention_1_k, node_scaled_dot_product_attention_1_v)
   [node_scaled_dot_product_attention_1_out_mm] node_scaled_dot_product_attention_1_out_mm_out = MatMul (scaled_dot_product_attention_1, node_scaled_dot_product_attention_1_wo_t)
   [node_scaled_dot_product_attention_1_out_bias] node_scaled_dot_product_attention_1_out = Add (node_scaled_dot_product_attention_1_out_mm_out, "visual.transformer.resblocks.1.attn.out_proj.bias")
   add_272 = Add (add_157, node_scaled_dot_product_attention_1_out)
   layer_norm_4 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_272, "visual.transformer.resblocks.1.ln_2.weight", "visual.transformer.resblocks.1.ln_2.bias")
   val_82 = MatMul (layer_norm_4, val_10)
   linear_6 = Add (val_82, "visual.transformer.resblocks.1.mlp.c_fc.bias")
   gelu_1 = Gelu <approximate: string = "none"> (linear_6)
   val_83 = MatMul (gelu_1, val_11)
   linear_7 = Add (val_83, "visual.transformer.resblocks.1.mlp.c_proj.bias")
   add_293 = Add (add_272, linear_7)
   layer_norm_5 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_293, "visual.transformer.resblocks.2.ln_1.weight", "visual.transformer.resblocks.2.ln_1.bias")
   [node_scaled_dot_product_attention_2_qkv_mm] node_scaled_dot_product_attention_2_qkv_mm_out = MatMul (layer_norm_5, val_12)
   [node_scaled_dot_product_attention_2_qkv_bias] node_scaled_dot_product_attention_2_qkv = Add (node_scaled_dot_product_attention_2_qkv_mm_out, "visual.transformer.resblocks.2.attn.in_proj_bias")
   [node_scaled_dot_product_attention_2_qkv_split] node_scaled_dot_product_attention_2_q, node_scaled_dot_product_attention_2_k, node_scaled_dot_product_attention_2_v = Split <axis: int = -1> (node_scaled_dot_product_attention_2_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_2 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_2_q, node_scaled_dot_product_attention_2_k, node_scaled_dot_product_attention_2_v)
   [node_scaled_dot_product_attention_2_out_mm] node_scaled_dot_product_attention_2_out_mm_out = MatMul (scaled_dot_product_attention_2, node_scaled_dot_product_attention_2_wo_t)
   [node_scaled_dot_product_attention_2_out_bias] node_scaled_dot_product_attention_2_out = Add (node_scaled_dot_product_attention_2_out_mm_out, "visual.transformer.resblocks.2.attn.out_proj.bias")
   add_408 = Add (add_293, node_scaled_dot_product_attention_2_out)
   layer_norm_6 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_408, "visual.transformer.resblocks.2.ln_2.weight", "visual.transformer.resblocks.2.ln_2.bias")
   val_84 = MatMul (layer_norm_6, val_13)
   linear_10 = Add (val_84, "visual.transformer.resblocks.2.mlp.c_fc.bias")
   gelu_2 = Gelu <approximate: string = "none"> (linear_10)
   val_85 = MatMul (gelu_2, val_14)
   linear_11 = Add (val_85, "visual.transformer.resblocks.2.mlp.c_proj.bias")
   add_429 = Add (add_408, linear_11)
   layer_norm_7 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_429, "visual.transformer.resblocks.3.ln_1.weight", "visual.transformer.resblocks.3.ln_1.bias")
   [node_scaled_dot_product_attention_3_qkv_mm] node_scaled_dot_product_attention_3_qkv_mm_out = MatMul (layer_norm_7, val_15)
   [node_scaled_dot_product_attention_3_qkv_bias] node_scaled_dot_product_attention_3_qkv = Add (node_scaled_dot_product_attention_3_qkv_mm_out, "visual.transformer.resblocks.3.attn.in_proj_bias")
   [node_scaled_dot_product_attention_3_qkv_split] node_scaled_dot_product_attention_3_q, node_scaled_dot_product_attention_3_k, node_scaled_dot_product_attention_3_v = Split <axis: int = -1> (node_scaled_dot_product_attention_3_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_3 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_3_q, node_scaled_dot_product_attention_3_k, node_scaled_dot_product_attention_3_v)
   [node_scaled_dot_product_attention_3_out_mm] node_scaled_dot_product_attention_3_out_mm_out = MatMul (scaled_dot_product_attention_3, node_scaled_dot_product_attention_3_wo_t)
   [node_scaled_dot_product_attention_3_out_bias] node_scaled_dot_product_attention_3_out = Add (node_scaled_dot_product_attention_3_out_mm_out, "visual.transformer.resblocks.3.attn.out_proj.bias")
   add_544 = Add (add_429, node_scaled_dot_product_attention_3_out)
   layer_norm_8 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_544, "visual.transformer.resblocks.3.ln_2.weight", "visual.transformer.resblocks.3.ln_2.bias")
   val_86 = MatMul (layer_norm_8, val_16)
   linear_14 = Add (val_86, "visual.transformer.resblocks.3.mlp.c_fc.bias")
   gelu_3 = Gelu <approximate: string = "none"> (linear_14)
   val_87 = MatMul (gelu_3, val_17)
   linear_15 = Add (val_87, "visual.transformer.resblocks.3.mlp.c_proj.bias")
   add_565 = Add (add_544, linear_15)
   layer_norm_9 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_565, "visual.transformer.resblocks.4.ln_1.weight", "visual.transformer.resblocks.4.ln_1.bias")
   [node_scaled_dot_product_attention_4_qkv_mm] node_scaled_dot_product_attention_4_qkv_mm_out = MatMul (layer_norm_9, val_18)
   [node_scaled_dot_product_attention_4_qkv_bias] node_scaled_dot_product_attention_4_qkv = Add (node_scaled_dot_product_attention_4_qkv_mm_out, "visual.transformer.resblocks.4.attn.in_proj_bias")
   [node_scaled_dot_product_attention_4_qkv_split] node_scaled_dot_product_attention_4_q, node_scaled_dot_product_attention_4_k, node_scaled_dot_product_attention_4_v = Split <axis: int = -1> (node_scaled_dot_product_attention_4_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_4 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_4_q, node_scaled_dot_product_attention_4_k, node_scaled_dot_product_attention_4_v)
   [node_scaled_dot_product_attention_4_out_mm] node_scaled_dot_product_attention_4_out_mm_out = MatMul (scaled_dot_product_attention_4, node_scaled_dot_product_attention_4_wo_t)
   [node_scaled_dot_product_attention_4_out_bias] node_scaled_dot_product_attention_4_out = Add (node_scaled_dot_product_attention_4_out_mm_out, "visual.transformer.resblocks.4.attn.out_proj.bias")
   add_680 = Add (add_565, node_scaled_dot_product_attention_4_out)
   layer_norm_10 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_680, "visual.transformer.resblocks.4.ln_2.weight", "visual.transformer.resblocks.4.ln_2.bias")
   val_88 = MatMul (layer_norm_10, val_19)
   linear_18 = Add (val_88, "visual.transformer.resblocks.4.mlp.c_fc.bias")
   gelu_4 = Gelu <approximate: string = "none"> (linear_18)
   val_89 = MatMul (gelu_4, val_20)
   linear_19 = Add (val_89, "visual.transformer.resblocks.4.mlp.c_proj.bias")
   add_701 = Add (add_680, linear_19)
   layer_norm_11 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_701, "visual.transformer.resblocks.5.ln_1.weight", "visual.transformer.resblocks.5.ln_1.bias")
   [node_scaled_dot_product_attention_5_qkv_mm] node_scaled_dot_product_attention_5_qkv_mm_out = MatMul (layer_norm_11, val_21)
   [node_scaled_dot_product_attention_5_qkv_bias] node_scaled_dot_product_attention_5_qkv = Add (node_scaled_dot_product_attention_5_qkv_mm_out, "visual.transformer.resblocks.5.attn.in_proj_bias")
   [node_scaled_dot_product_attention_5_qkv_split] node_scaled_dot_product_attention_5_q, node_scaled_dot_product_attention_5_k, node_scaled_dot_product_attention_5_v = Split <axis: int = -1> (node_scaled_dot_product_attention_5_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_5 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_5_q, node_scaled_dot_product_attention_5_k, node_scaled_dot_product_attention_5_v)
   [node_scaled_dot_product_attention_5_out_mm] node_scaled_dot_product_attention_5_out_mm_out = MatMul (scaled_dot_product_attention_5, node_scaled_dot_product_attention_5_wo_t)
   [node_scaled_dot_product_attention_5_out_bias] node_scaled_dot_product_attention_5_out = Add (node_scaled_dot_product_attention_5_out_mm_out, "visual.transformer.resblocks.5.attn.out_proj.bias")
   add_816 = Add (add_701, node_scaled_dot_product_attention_5_out)
   layer_norm_12 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_816, "visual.transformer.resblocks.5.ln_2.weight", "visual.transformer.resblocks.5.ln_2.bias")
   val_90 = MatMul (layer_norm_12, val_22)
   linear_22 = Add (val_90, "visual.transformer.resblocks.5.mlp.c_fc.bias")
   gelu_5 = Gelu <approximate: string = "none"> (linear_22)
   val_91 = MatMul (gelu_5, val_23)
   linear_23 = Add (val_91, "visual.transformer.resblocks.5.mlp.c_proj.bias")
   add_837 = Add (add_816, linear_23)
   layer_norm_13 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_837, "visual.transformer.resblocks.6.ln_1.weight", "visual.transformer.resblocks.6.ln_1.bias")
   [node_scaled_dot_product_attention_6_qkv_mm] node_scaled_dot_product_attention_6_qkv_mm_out = MatMul (layer_norm_13, val_24)
   [node_scaled_dot_product_attention_6_qkv_bias] node_scaled_dot_product_attention_6_qkv = Add (node_scaled_dot_product_attention_6_qkv_mm_out, "visual.transformer.resblocks.6.attn.in_proj_bias")
   [node_scaled_dot_product_attention_6_qkv_split] node_scaled_dot_product_attention_6_q, node_scaled_dot_product_attention_6_k, node_scaled_dot_product_attention_6_v = Split <axis: int = -1> (node_scaled_dot_product_attention_6_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_6 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_6_q, node_scaled_dot_product_attention_6_k, node_scaled_dot_product_attention_6_v)
   [node_scaled_dot_product_attention_6_out_mm] node_scaled_dot_product_attention_6_out_mm_out = MatMul (scaled_dot_product_attention_6, node_scaled_dot_product_attention_6_wo_t)
   [node_scaled_dot_product_attention_6_out_bias] node_scaled_dot_product_attention_6_out = Add (node_scaled_dot_product_attention_6_out_mm_out, "visual.transformer.resblocks.6.attn.out_proj.bias")
   add_952 = Add (add_837, node_scaled_dot_product_attention_6_out)
   layer_norm_14 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_952, "visual.transformer.resblocks.6.ln_2.weight", "visual.transformer.resblocks.6.ln_2.bias")
   val_92 = MatMul (layer_norm_14, val_25)
   linear_26 = Add (val_92, "visual.transformer.resblocks.6.mlp.c_fc.bias")
   gelu_6 = Gelu <approximate: string = "none"> (linear_26)
   val_93 = MatMul (gelu_6, val_26)
   linear_27 = Add (val_93, "visual.transformer.resblocks.6.mlp.c_proj.bias")
   add_973 = Add (add_952, linear_27)
   layer_norm_15 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_973, "visual.transformer.resblocks.7.ln_1.weight", "visual.transformer.resblocks.7.ln_1.bias")
   [node_scaled_dot_product_attention_7_qkv_mm] node_scaled_dot_product_attention_7_qkv_mm_out = MatMul (layer_norm_15, val_27)
   [node_scaled_dot_product_attention_7_qkv_bias] node_scaled_dot_product_attention_7_qkv = Add (node_scaled_dot_product_attention_7_qkv_mm_out, "visual.transformer.resblocks.7.attn.in_proj_bias")
   [node_scaled_dot_product_attention_7_qkv_split] node_scaled_dot_product_attention_7_q, node_scaled_dot_product_attention_7_k, node_scaled_dot_product_attention_7_v = Split <axis: int = -1> (node_scaled_dot_product_attention_7_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_7 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_7_q, node_scaled_dot_product_attention_7_k, node_scaled_dot_product_attention_7_v)
   [node_scaled_dot_product_attention_7_out_mm] node_scaled_dot_product_attention_7_out_mm_out = MatMul (scaled_dot_product_attention_7, node_scaled_dot_product_attention_7_wo_t)
   [node_scaled_dot_product_attention_7_out_bias] node_scaled_dot_product_attention_7_out = Add (node_scaled_dot_product_attention_7_out_mm_out, "visual.transformer.resblocks.7.attn.out_proj.bias")
   add_1088 = Add (add_973, node_scaled_dot_product_attention_7_out)
   layer_norm_16 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1088, "visual.transformer.resblocks.7.ln_2.weight", "visual.transformer.resblocks.7.ln_2.bias")
   val_94 = MatMul (layer_norm_16, val_28)
   linear_30 = Add (val_94, "visual.transformer.resblocks.7.mlp.c_fc.bias")
   gelu_7 = Gelu <approximate: string = "none"> (linear_30)
   val_95 = MatMul (gelu_7, val_29)
   linear_31 = Add (val_95, "visual.transformer.resblocks.7.mlp.c_proj.bias")
   add_1109 = Add (add_1088, linear_31)
   layer_norm_17 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1109, "visual.transformer.resblocks.8.ln_1.weight", "visual.transformer.resblocks.8.ln_1.bias")
   [node_scaled_dot_product_attention_8_qkv_mm] node_scaled_dot_product_attention_8_qkv_mm_out = MatMul (layer_norm_17, val_30)
   [node_scaled_dot_product_attention_8_qkv_bias] node_scaled_dot_product_attention_8_qkv = Add (node_scaled_dot_product_attention_8_qkv_mm_out, "visual.transformer.resblocks.8.attn.in_proj_bias")
   [node_scaled_dot_product_attention_8_qkv_split] node_scaled_dot_product_attention_8_q, node_scaled_dot_product_attention_8_k, node_scaled_dot_product_attention_8_v = Split <axis: int = -1> (node_scaled_dot_product_attention_8_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_8 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_8_q, node_scaled_dot_product_attention_8_k, node_scaled_dot_product_attention_8_v)
   [node_scaled_dot_product_attention_8_out_mm] node_scaled_dot_product_attention_8_out_mm_out = MatMul (scaled_dot_product_attention_8, node_scaled_dot_product_attention_8_wo_t)
   [node_scaled_dot_product_attention_8_out_bias] node_scaled_dot_product_attention_8_out = Add (node_scaled_dot_product_attention_8_out_mm_out, "visual.transformer.resblocks.8.attn.out_proj.bias")
   add_1224 = Add (add_1109, node_scaled_dot_product_attention_8_out)
   layer_norm_18 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1224, "visual.transformer.resblocks.8.ln_2.weight", "visual.transformer.resblocks.8.ln_2.bias")
   val_96 = MatMul (layer_norm_18, val_31)
   linear_34 = Add (val_96, "visual.transformer.resblocks.8.mlp.c_fc.bias")
   gelu_8 = Gelu <approximate: string = "none"> (linear_34)
   val_97 = MatMul (gelu_8, val_32)
   linear_35 = Add (val_97, "visual.transformer.resblocks.8.mlp.c_proj.bias")
   add_1245 = Add (add_1224, linear_35)
   layer_norm_19 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1245, "visual.transformer.resblocks.9.ln_1.weight", "visual.transformer.resblocks.9.ln_1.bias")
   [node_scaled_dot_product_attention_9_qkv_mm] node_scaled_dot_product_attention_9_qkv_mm_out = MatMul (layer_norm_19, val_33)
   [node_scaled_dot_product_attention_9_qkv_bias] node_scaled_dot_product_attention_9_qkv = Add (node_scaled_dot_product_attention_9_qkv_mm_out, "visual.transformer.resblocks.9.attn.in_proj_bias")
   [node_scaled_dot_product_attention_9_qkv_split] node_scaled_dot_product_attention_9_q, node_scaled_dot_product_attention_9_k, node_scaled_dot_product_attention_9_v = Split <axis: int = -1> (node_scaled_dot_product_attention_9_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_9 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_9_q, node_scaled_dot_product_attention_9_k, node_scaled_dot_product_attention_9_v)
   [node_scaled_dot_product_attention_9_out_mm] node_scaled_dot_product_attention_9_out_mm_out = MatMul (scaled_dot_product_attention_9, node_scaled_dot_product_attention_9_wo_t)
   [node_scaled_dot_product_attention_9_out_bias] node_scaled_dot_product_attention_9_out = Add (node_scaled_dot_product_attention_9_out_mm_out, "visual.transformer.resblocks.9.attn.out_proj.bias")
   add_1360 = Add (add_1245, node_scaled_dot_product_attention_9_out)
   layer_norm_20 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1360, "visual.transformer.resblocks.9.ln_2.weight", "visual.transformer.resblocks.9.ln_2.bias")
   val_98 = MatMul (layer_norm_20, val_34)
   linear_38 = Add (val_98, "visual.transformer.resblocks.9.mlp.c_fc.bias")
   gelu_9 = Gelu <approximate: string = "none"> (linear_38)
   val_99 = MatMul (gelu_9, val_35)
   linear_39 = Add (val_99, "visual.transformer.resblocks.9.mlp.c_proj.bias")
   add_1381 = Add (add_1360, linear_39)
   layer_norm_21 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1381, "visual.transformer.resblocks.10.ln_1.weight", "visual.transformer.resblocks.10.ln_1.bias")
   [node_scaled_dot_product_attention_10_qkv_mm] node_scaled_dot_product_attention_10_qkv_mm_out = MatMul (layer_norm_21, val_36)
   [node_scaled_dot_product_attention_10_qkv_bias] node_scaled_dot_product_attention_10_qkv = Add (node_scaled_dot_product_attention_10_qkv_mm_out, "visual.transformer.resblocks.10.attn.in_proj_bias")
   [node_scaled_dot_product_attention_10_qkv_split] node_scaled_dot_product_attention_10_q, node_scaled_dot_product_attention_10_k, node_scaled_dot_product_attention_10_v = Split <axis: int = -1> (node_scaled_dot_product_attention_10_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_10 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_10_q, node_scaled_dot_product_attention_10_k, node_scaled_dot_product_attention_10_v)
   [node_scaled_dot_product_attention_10_out_mm] node_scaled_dot_product_attention_10_out_mm_out = MatMul (scaled_dot_product_attention_10, node_scaled_dot_product_attention_10_wo_t)
   [node_scaled_dot_product_attention_10_out_bias] node_scaled_dot_product_attention_10_out = Add (node_scaled_dot_product_attention_10_out_mm_out, "visual.transformer.resblocks.10.attn.out_proj.bias")
   add_1496 = Add (add_1381, node_scaled_dot_product_attention_10_out)
   layer_norm_22 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1496, "visual.transformer.resblocks.10.ln_2.weight", "visual.transformer.resblocks.10.ln_2.bias")
   val_100 = MatMul (layer_norm_22, val_37)
   linear_42 = Add (val_100, "visual.transformer.resblocks.10.mlp.c_fc.bias")
   gelu_10 = Gelu <approximate: string = "none"> (linear_42)
   val_101 = MatMul (gelu_10, val_38)
   linear_43 = Add (val_101, "visual.transformer.resblocks.10.mlp.c_proj.bias")
   add_1517 = Add (add_1496, linear_43)
   layer_norm_23 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1517, "visual.transformer.resblocks.11.ln_1.weight", "visual.transformer.resblocks.11.ln_1.bias")
   [node_scaled_dot_product_attention_11_qkv_mm] node_scaled_dot_product_attention_11_qkv_mm_out = MatMul (layer_norm_23, val_39)
   [node_scaled_dot_product_attention_11_qkv_bias] node_scaled_dot_product_attention_11_qkv = Add (node_scaled_dot_product_attention_11_qkv_mm_out, "visual.transformer.resblocks.11.attn.in_proj_bias")
   [node_scaled_dot_product_attention_11_qkv_split] node_scaled_dot_product_attention_11_q, node_scaled_dot_product_attention_11_k, node_scaled_dot_product_attention_11_v = Split <axis: int = -1> (node_scaled_dot_product_attention_11_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_11 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_11_q, node_scaled_dot_product_attention_11_k, node_scaled_dot_product_attention_11_v)
   [node_scaled_dot_product_attention_11_out_mm] node_scaled_dot_product_attention_11_out_mm_out = MatMul (scaled_dot_product_attention_11, node_scaled_dot_product_attention_11_wo_t)
   [node_scaled_dot_product_attention_11_out_bias] node_scaled_dot_product_attention_11_out = Add (node_scaled_dot_product_attention_11_out_mm_out, "visual.transformer.resblocks.11.attn.out_proj.bias")
   add_1632 = Add (add_1517, node_scaled_dot_product_attention_11_out)
   layer_norm_24 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1632, "visual.transformer.resblocks.11.ln_2.weight", "visual.transformer.resblocks.11.ln_2.bias")
   val_102 = MatMul (layer_norm_24, val_40)
   linear_46 = Add (val_102, "visual.transformer.resblocks.11.mlp.c_fc.bias")
   gelu_11 = Gelu <approximate: string = "none"> (linear_46)
   val_103 = MatMul (gelu_11, val_41)
   linear_47 = Add (val_103, "visual.transformer.resblocks.11.mlp.c_proj.bias")
   add_1653 = Add (add_1632, linear_47)
   layer_norm_25 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1653, "visual.transformer.resblocks.12.ln_1.weight", "visual.transformer.resblocks.12.ln_1.bias")
   [node_scaled_dot_product_attention_12_qkv_mm] node_scaled_dot_product_attention_12_qkv_mm_out = MatMul (layer_norm_25, val_42)
   [node_scaled_dot_product_attention_12_qkv_bias] node_scaled_dot_product_attention_12_qkv = Add (node_scaled_dot_product_attention_12_qkv_mm_out, "visual.transformer.resblocks.12.attn.in_proj_bias")
   [node_scaled_dot_product_attention_12_qkv_split] node_scaled_dot_product_attention_12_q, node_scaled_dot_product_attention_12_k, node_scaled_dot_product_attention_12_v = Split <axis: int = -1> (node_scaled_dot_product_attention_12_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_12 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_12_q, node_scaled_dot_product_attention_12_k, node_scaled_dot_product_attention_12_v)
   [node_scaled_dot_product_attention_12_out_mm] node_scaled_dot_product_attention_12_out_mm_out = MatMul (scaled_dot_product_attention_12, node_scaled_dot_product_attention_12_wo_t)
   [node_scaled_dot_product_attention_12_out_bias] node_scaled_dot_product_attention_12_out = Add (node_scaled_dot_product_attention_12_out_mm_out, "visual.transformer.resblocks.12.attn.out_proj.bias")
   add_1768 = Add (add_1653, node_scaled_dot_product_attention_12_out)
   layer_norm_26 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1768, "visual.transformer.resblocks.12.ln_2.weight", "visual.transformer.resblocks.12.ln_2.bias")
   val_104 = MatMul (layer_norm_26, val_43)
   linear_50 = Add (val_104, "visual.transformer.resblocks.12.mlp.c_fc.bias")
   gelu_12 = Gelu <approximate: string = "none"> (linear_50)
   val_105 = MatMul (gelu_12, val_44)
   linear_51 = Add (val_105, "visual.transformer.resblocks.12.mlp.c_proj.bias")
   add_1789 = Add (add_1768, linear_51)
   layer_norm_27 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1789, "visual.transformer.resblocks.13.ln_1.weight", "visual.transformer.resblocks.13.ln_1.bias")
   [node_scaled_dot_product_attention_13_qkv_mm] node_scaled_dot_product_attention_13_qkv_mm_out = MatMul (layer_norm_27, val_45)
   [node_scaled_dot_product_attention_13_qkv_bias] node_scaled_dot_product_attention_13_qkv = Add (node_scaled_dot_product_attention_13_qkv_mm_out, "visual.transformer.resblocks.13.attn.in_proj_bias")
   [node_scaled_dot_product_attention_13_qkv_split] node_scaled_dot_product_attention_13_q, node_scaled_dot_product_attention_13_k, node_scaled_dot_product_attention_13_v = Split <axis: int = -1> (node_scaled_dot_product_attention_13_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_13 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_13_q, node_scaled_dot_product_attention_13_k, node_scaled_dot_product_attention_13_v)
   [node_scaled_dot_product_attention_13_out_mm] node_scaled_dot_product_attention_13_out_mm_out = MatMul (scaled_dot_product_attention_13, node_scaled_dot_product_attention_13_wo_t)
   [node_scaled_dot_product_attention_13_out_bias] node_scaled_dot_product_attention_13_out = Add (node_scaled_dot_product_attention_13_out_mm_out, "visual.transformer.resblocks.13.attn.out_proj.bias")
   add_1904 = Add (add_1789, node_scaled_dot_product_attention_13_out)
   layer_norm_28 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1904, "visual.transformer.resblocks.13.ln_2.weight", "visual.transformer.resblocks.13.ln_2.bias")
   val_106 = MatMul (layer_norm_28, val_46)
   linear_54 = Add (val_106, "visual.transformer.resblocks.13.mlp.c_fc.bias")
   gelu_13 = Gelu <approximate: string = "none"> (linear_54)
   val_107 = MatMul (gelu_13, val_47)
   linear_55 = Add (val_107, "visual.transformer.resblocks.13.mlp.c_proj.bias")
   add_1925 = Add (add_1904, linear_55)
   layer_norm_29 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_1925, "visual.transformer.resblocks.14.ln_1.weight", "visual.transformer.resblocks.14.ln_1.bias")
   [node_scaled_dot_product_attention_14_qkv_mm] node_scaled_dot_product_attention_14_qkv_mm_out = MatMul (layer_norm_29, val_48)
   [node_scaled_dot_product_attention_14_qkv_bias] node_scaled_dot_product_attention_14_qkv = Add (node_scaled_dot_product_attention_14_qkv_mm_out, "visual.transformer.resblocks.14.attn.in_proj_bias")
   [node_scaled_dot_product_attention_14_qkv_split] node_scaled_dot_product_attention_14_q, node_scaled_dot_product_attention_14_k, node_scaled_dot_product_attention_14_v = Split <axis: int = -1> (node_scaled_dot_product_attention_14_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_14 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_14_q, node_scaled_dot_product_attention_14_k, node_scaled_dot_product_attention_14_v)
   [node_scaled_dot_product_attention_14_out_mm] node_scaled_dot_product_attention_14_out_mm_out = MatMul (scaled_dot_product_attention_14, node_scaled_dot_product_attention_14_wo_t)
   [node_scaled_dot_product_attention_14_out_bias] node_scaled_dot_product_attention_14_out = Add (node_scaled_dot_product_attention_14_out_mm_out, "visual.transformer.resblocks.14.attn.out_proj.bias")
   add_2040 = Add (add_1925, node_scaled_dot_product_attention_14_out)
   layer_norm_30 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2040, "visual.transformer.resblocks.14.ln_2.weight", "visual.transformer.resblocks.14.ln_2.bias")
   val_108 = MatMul (layer_norm_30, val_49)
   linear_58 = Add (val_108, "visual.transformer.resblocks.14.mlp.c_fc.bias")
   gelu_14 = Gelu <approximate: string = "none"> (linear_58)
   val_109 = MatMul (gelu_14, val_50)
   linear_59 = Add (val_109, "visual.transformer.resblocks.14.mlp.c_proj.bias")
   add_2061 = Add (add_2040, linear_59)
   layer_norm_31 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2061, "visual.transformer.resblocks.15.ln_1.weight", "visual.transformer.resblocks.15.ln_1.bias")
   [node_scaled_dot_product_attention_15_qkv_mm] node_scaled_dot_product_attention_15_qkv_mm_out = MatMul (layer_norm_31, val_51)
   [node_scaled_dot_product_attention_15_qkv_bias] node_scaled_dot_product_attention_15_qkv = Add (node_scaled_dot_product_attention_15_qkv_mm_out, "visual.transformer.resblocks.15.attn.in_proj_bias")
   [node_scaled_dot_product_attention_15_qkv_split] node_scaled_dot_product_attention_15_q, node_scaled_dot_product_attention_15_k, node_scaled_dot_product_attention_15_v = Split <axis: int = -1> (node_scaled_dot_product_attention_15_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_15 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_15_q, node_scaled_dot_product_attention_15_k, node_scaled_dot_product_attention_15_v)
   [node_scaled_dot_product_attention_15_out_mm] node_scaled_dot_product_attention_15_out_mm_out = MatMul (scaled_dot_product_attention_15, node_scaled_dot_product_attention_15_wo_t)
   [node_scaled_dot_product_attention_15_out_bias] node_scaled_dot_product_attention_15_out = Add (node_scaled_dot_product_attention_15_out_mm_out, "visual.transformer.resblocks.15.attn.out_proj.bias")
   add_2176 = Add (add_2061, node_scaled_dot_product_attention_15_out)
   layer_norm_32 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2176, "visual.transformer.resblocks.15.ln_2.weight", "visual.transformer.resblocks.15.ln_2.bias")
   val_110 = MatMul (layer_norm_32, val_52)
   linear_62 = Add (val_110, "visual.transformer.resblocks.15.mlp.c_fc.bias")
   gelu_15 = Gelu <approximate: string = "none"> (linear_62)
   val_111 = MatMul (gelu_15, val_53)
   linear_63 = Add (val_111, "visual.transformer.resblocks.15.mlp.c_proj.bias")
   add_2197 = Add (add_2176, linear_63)
   layer_norm_33 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2197, "visual.transformer.resblocks.16.ln_1.weight", "visual.transformer.resblocks.16.ln_1.bias")
   [node_scaled_dot_product_attention_16_qkv_mm] node_scaled_dot_product_attention_16_qkv_mm_out = MatMul (layer_norm_33, val_54)
   [node_scaled_dot_product_attention_16_qkv_bias] node_scaled_dot_product_attention_16_qkv = Add (node_scaled_dot_product_attention_16_qkv_mm_out, "visual.transformer.resblocks.16.attn.in_proj_bias")
   [node_scaled_dot_product_attention_16_qkv_split] node_scaled_dot_product_attention_16_q, node_scaled_dot_product_attention_16_k, node_scaled_dot_product_attention_16_v = Split <axis: int = -1> (node_scaled_dot_product_attention_16_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_16 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_16_q, node_scaled_dot_product_attention_16_k, node_scaled_dot_product_attention_16_v)
   [node_scaled_dot_product_attention_16_out_mm] node_scaled_dot_product_attention_16_out_mm_out = MatMul (scaled_dot_product_attention_16, node_scaled_dot_product_attention_16_wo_t)
   [node_scaled_dot_product_attention_16_out_bias] node_scaled_dot_product_attention_16_out = Add (node_scaled_dot_product_attention_16_out_mm_out, "visual.transformer.resblocks.16.attn.out_proj.bias")
   add_2312 = Add (add_2197, node_scaled_dot_product_attention_16_out)
   layer_norm_34 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2312, "visual.transformer.resblocks.16.ln_2.weight", "visual.transformer.resblocks.16.ln_2.bias")
   val_112 = MatMul (layer_norm_34, val_55)
   linear_66 = Add (val_112, "visual.transformer.resblocks.16.mlp.c_fc.bias")
   gelu_16 = Gelu <approximate: string = "none"> (linear_66)
   val_113 = MatMul (gelu_16, val_56)
   linear_67 = Add (val_113, "visual.transformer.resblocks.16.mlp.c_proj.bias")
   add_2333 = Add (add_2312, linear_67)
   layer_norm_35 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2333, "visual.transformer.resblocks.17.ln_1.weight", "visual.transformer.resblocks.17.ln_1.bias")
   [node_scaled_dot_product_attention_17_qkv_mm] node_scaled_dot_product_attention_17_qkv_mm_out = MatMul (layer_norm_35, val_57)
   [node_scaled_dot_product_attention_17_qkv_bias] node_scaled_dot_product_attention_17_qkv = Add (node_scaled_dot_product_attention_17_qkv_mm_out, "visual.transformer.resblocks.17.attn.in_proj_bias")
   [node_scaled_dot_product_attention_17_qkv_split] node_scaled_dot_product_attention_17_q, node_scaled_dot_product_attention_17_k, node_scaled_dot_product_attention_17_v = Split <axis: int = -1> (node_scaled_dot_product_attention_17_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_17 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_17_q, node_scaled_dot_product_attention_17_k, node_scaled_dot_product_attention_17_v)
   [node_scaled_dot_product_attention_17_out_mm] node_scaled_dot_product_attention_17_out_mm_out = MatMul (scaled_dot_product_attention_17, node_scaled_dot_product_attention_17_wo_t)
   [node_scaled_dot_product_attention_17_out_bias] node_scaled_dot_product_attention_17_out = Add (node_scaled_dot_product_attention_17_out_mm_out, "visual.transformer.resblocks.17.attn.out_proj.bias")
   add_2448 = Add (add_2333, node_scaled_dot_product_attention_17_out)
   layer_norm_36 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2448, "visual.transformer.resblocks.17.ln_2.weight", "visual.transformer.resblocks.17.ln_2.bias")
   val_114 = MatMul (layer_norm_36, val_58)
   linear_70 = Add (val_114, "visual.transformer.resblocks.17.mlp.c_fc.bias")
   gelu_17 = Gelu <approximate: string = "none"> (linear_70)
   val_115 = MatMul (gelu_17, val_59)
   linear_71 = Add (val_115, "visual.transformer.resblocks.17.mlp.c_proj.bias")
   add_2469 = Add (add_2448, linear_71)
   layer_norm_37 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2469, "visual.transformer.resblocks.18.ln_1.weight", "visual.transformer.resblocks.18.ln_1.bias")
   [node_scaled_dot_product_attention_18_qkv_mm] node_scaled_dot_product_attention_18_qkv_mm_out = MatMul (layer_norm_37, val_60)
   [node_scaled_dot_product_attention_18_qkv_bias] node_scaled_dot_product_attention_18_qkv = Add (node_scaled_dot_product_attention_18_qkv_mm_out, "visual.transformer.resblocks.18.attn.in_proj_bias")
   [node_scaled_dot_product_attention_18_qkv_split] node_scaled_dot_product_attention_18_q, node_scaled_dot_product_attention_18_k, node_scaled_dot_product_attention_18_v = Split <axis: int = -1> (node_scaled_dot_product_attention_18_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_18 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_18_q, node_scaled_dot_product_attention_18_k, node_scaled_dot_product_attention_18_v)
   [node_scaled_dot_product_attention_18_out_mm] node_scaled_dot_product_attention_18_out_mm_out = MatMul (scaled_dot_product_attention_18, node_scaled_dot_product_attention_18_wo_t)
   [node_scaled_dot_product_attention_18_out_bias] node_scaled_dot_product_attention_18_out = Add (node_scaled_dot_product_attention_18_out_mm_out, "visual.transformer.resblocks.18.attn.out_proj.bias")
   add_2584 = Add (add_2469, node_scaled_dot_product_attention_18_out)
   layer_norm_38 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2584, "visual.transformer.resblocks.18.ln_2.weight", "visual.transformer.resblocks.18.ln_2.bias")
   val_116 = MatMul (layer_norm_38, val_61)
   linear_74 = Add (val_116, "visual.transformer.resblocks.18.mlp.c_fc.bias")
   gelu_18 = Gelu <approximate: string = "none"> (linear_74)
   val_117 = MatMul (gelu_18, val_62)
   linear_75 = Add (val_117, "visual.transformer.resblocks.18.mlp.c_proj.bias")
   add_2605 = Add (add_2584, linear_75)
   layer_norm_39 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2605, "visual.transformer.resblocks.19.ln_1.weight", "visual.transformer.resblocks.19.ln_1.bias")
   [node_scaled_dot_product_attention_19_qkv_mm] node_scaled_dot_product_attention_19_qkv_mm_out = MatMul (layer_norm_39, val_63)
   [node_scaled_dot_product_attention_19_qkv_bias] node_scaled_dot_product_attention_19_qkv = Add (node_scaled_dot_product_attention_19_qkv_mm_out, "visual.transformer.resblocks.19.attn.in_proj_bias")
   [node_scaled_dot_product_attention_19_qkv_split] node_scaled_dot_product_attention_19_q, node_scaled_dot_product_attention_19_k, node_scaled_dot_product_attention_19_v = Split <axis: int = -1> (node_scaled_dot_product_attention_19_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_19 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_19_q, node_scaled_dot_product_attention_19_k, node_scaled_dot_product_attention_19_v)
   [node_scaled_dot_product_attention_19_out_mm] node_scaled_dot_product_attention_19_out_mm_out = MatMul (scaled_dot_product_attention_19, node_scaled_dot_product_attention_19_wo_t)
   [node_scaled_dot_product_attention_19_out_bias] node_scaled_dot_product_attention_19_out = Add (node_scaled_dot_product_attention_19_out_mm_out, "visual.transformer.resblocks.19.attn.out_proj.bias")
   add_2720 = Add (add_2605, node_scaled_dot_product_attention_19_out)
   layer_norm_40 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2720, "visual.transformer.resblocks.19.ln_2.weight", "visual.transformer.resblocks.19.ln_2.bias")
   val_118 = MatMul (layer_norm_40, val_64)
   linear_78 = Add (val_118, "visual.transformer.resblocks.19.mlp.c_fc.bias")
   gelu_19 = Gelu <approximate: string = "none"> (linear_78)
   val_119 = MatMul (gelu_19, val_65)
   linear_79 = Add (val_119, "visual.transformer.resblocks.19.mlp.c_proj.bias")
   add_2741 = Add (add_2720, linear_79)
   layer_norm_41 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2741, "visual.transformer.resblocks.20.ln_1.weight", "visual.transformer.resblocks.20.ln_1.bias")
   [node_scaled_dot_product_attention_20_qkv_mm] node_scaled_dot_product_attention_20_qkv_mm_out = MatMul (layer_norm_41, val_66)
   [node_scaled_dot_product_attention_20_qkv_bias] node_scaled_dot_product_attention_20_qkv = Add (node_scaled_dot_product_attention_20_qkv_mm_out, "visual.transformer.resblocks.20.attn.in_proj_bias")
   [node_scaled_dot_product_attention_20_qkv_split] node_scaled_dot_product_attention_20_q, node_scaled_dot_product_attention_20_k, node_scaled_dot_product_attention_20_v = Split <axis: int = -1> (node_scaled_dot_product_attention_20_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_20 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_20_q, node_scaled_dot_product_attention_20_k, node_scaled_dot_product_attention_20_v)
   [node_scaled_dot_product_attention_20_out_mm] node_scaled_dot_product_attention_20_out_mm_out = MatMul (scaled_dot_product_attention_20, node_scaled_dot_product_attention_20_wo_t)
   [node_scaled_dot_product_attention_20_out_bias] node_scaled_dot_product_attention_20_out = Add (node_scaled_dot_product_attention_20_out_mm_out, "visual.transformer.resblocks.20.attn.out_proj.bias")
   add_2856 = Add (add_2741, node_scaled_dot_product_attention_20_out)
   layer_norm_42 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2856, "visual.transformer.resblocks.20.ln_2.weight", "visual.transformer.resblocks.20.ln_2.bias")
   val_120 = MatMul (layer_norm_42, val_67)
   linear_82 = Add (val_120, "visual.transformer.resblocks.20.mlp.c_fc.bias")
   gelu_20 = Gelu <approximate: string = "none"> (linear_82)
   val_121 = MatMul (gelu_20, val_68)
   linear_83 = Add (val_121, "visual.transformer.resblocks.20.mlp.c_proj.bias")
   add_2877 = Add (add_2856, linear_83)
   layer_norm_43 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2877, "visual.transformer.resblocks.21.ln_1.weight", "visual.transformer.resblocks.21.ln_1.bias")
   [node_scaled_dot_product_attention_21_qkv_mm] node_scaled_dot_product_attention_21_qkv_mm_out = MatMul (layer_norm_43, val_69)
   [node_scaled_dot_product_attention_21_qkv_bias] node_scaled_dot_product_attention_21_qkv = Add (node_scaled_dot_product_attention_21_qkv_mm_out, "visual.transformer.resblocks.21.attn.in_proj_bias")
   [node_scaled_dot_product_attention_21_qkv_split] node_scaled_dot_product_attention_21_q, node_scaled_dot_product_attention_21_k, node_scaled_dot_product_attention_21_v = Split <axis: int = -1> (node_scaled_dot_product_attention_21_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_21 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_21_q, node_scaled_dot_product_attention_21_k, node_scaled_dot_product_attention_21_v)
   [node_scaled_dot_product_attention_21_out_mm] node_scaled_dot_product_attention_21_out_mm_out = MatMul (scaled_dot_product_attention_21, node_scaled_dot_product_attention_21_wo_t)
   [node_scaled_dot_product_attention_21_out_bias] node_scaled_dot_product_attention_21_out = Add (node_scaled_dot_product_attention_21_out_mm_out, "visual.transformer.resblocks.21.attn.out_proj.bias")
   add_2992 = Add (add_2877, node_scaled_dot_product_attention_21_out)
   layer_norm_44 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_2992, "visual.transformer.resblocks.21.ln_2.weight", "visual.transformer.resblocks.21.ln_2.bias")
   val_122 = MatMul (layer_norm_44, val_70)
   linear_86 = Add (val_122, "visual.transformer.resblocks.21.mlp.c_fc.bias")
   gelu_21 = Gelu <approximate: string = "none"> (linear_86)
   val_123 = MatMul (gelu_21, val_71)
   linear_87 = Add (val_123, "visual.transformer.resblocks.21.mlp.c_proj.bias")
   add_3013 = Add (add_2992, linear_87)
   layer_norm_45 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_3013, "visual.transformer.resblocks.22.ln_1.weight", "visual.transformer.resblocks.22.ln_1.bias")
   [node_scaled_dot_product_attention_22_qkv_mm] node_scaled_dot_product_attention_22_qkv_mm_out = MatMul (layer_norm_45, val_72)
   [node_scaled_dot_product_attention_22_qkv_bias] node_scaled_dot_product_attention_22_qkv = Add (node_scaled_dot_product_attention_22_qkv_mm_out, "visual.transformer.resblocks.22.attn.in_proj_bias")
   [node_scaled_dot_product_attention_22_qkv_split] node_scaled_dot_product_attention_22_q, node_scaled_dot_product_attention_22_k, node_scaled_dot_product_attention_22_v = Split <axis: int = -1> (node_scaled_dot_product_attention_22_qkv, attn3d_split_3x1024)
   scaled_dot_product_attention_22 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_22_q, node_scaled_dot_product_attention_22_k, node_scaled_dot_product_attention_22_v)
   [node_scaled_dot_product_attention_22_out_mm] node_scaled_dot_product_attention_22_out_mm_out = MatMul (scaled_dot_product_attention_22, node_scaled_dot_product_attention_22_wo_t)
   [node_scaled_dot_product_attention_22_out_bias] node_scaled_dot_product_attention_22_out = Add (node_scaled_dot_product_attention_22_out_mm_out, "visual.transformer.resblocks.22.attn.out_proj.bias")
   add_3128 = Add (add_3013, node_scaled_dot_product_attention_22_out)
   layer_norm_46 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_3128, "visual.transformer.resblocks.22.ln_2.weight", "visual.transformer.resblocks.22.ln_2.bias")
   val_124 = MatMul (layer_norm_46, val_73)
   linear_90 = Add (val_124, "visual.transformer.resblocks.22.mlp.c_fc.bias")
   gelu_22 = Gelu <approximate: string = "none"> (linear_90)
   val_125 = MatMul (gelu_22, val_74)
   linear_91 = Add (val_125, "visual.transformer.resblocks.22.mlp.c_proj.bias")
   add_3149 = Add (add_3128, linear_91)
   layer_norm_47 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_3149, "visual.transformer.resblocks.23.ln_1.weight", "visual.transformer.resblocks.23.ln_1.bias")
   [node_scaled_dot_product_attention_23_qkv_mm] node_scaled_dot_product_attention_23_qkv_mm_out = MatMul (layer_norm_47, val_75)
   [node_scaled_dot_product_attention_23_qkv_bias] node_scaled_dot_product_attention_23_qkv = Add (node_scaled_dot_product_attention_23_qkv_mm_out, "visual.transformer.resblocks.23.attn.in_proj_bias")
   [node_scaled_dot_product_attention_23_qkv_split] node_scaled_dot_product_attention_23_q, node_scaled_dot_product_attention_23_k, node_scaled_dot_product_attention_23_v = Split <axis: int = -1> (node_scaled_dot_product_attention_23_qkv, attn3d_split_3x1024)
   [pool_hoist_node_scaled_dot_product_attention_23_q] node_scaled_dot_product_attention_23_q_pooled = Slice (node_scaled_dot_product_attention_23_q, val_2, val_5, val_5)
   scaled_dot_product_attention_23 = Attention <is_causal: int = 0, kv_num_heads: int = 16, q_num_heads: int = 16, qk_matmul_output_mode: int = 0, softcap: float = 0> (node_scaled_dot_product_attention_23_q_pooled, node_scaled_dot_product_attention_23_k, node_scaled_dot_product_attention_23_v)
   [node_scaled_dot_product_attention_23_out_mm] node_scaled_dot_product_attention_23_out_mm_out = MatMul (scaled_dot_product_attention_23, node_scaled_dot_product_attention_23_wo_t)
   [node_scaled_dot_product_attention_23_out_bias] node_scaled_dot_product_attention_23_out = Add (node_scaled_dot_product_attention_23_out_mm_out, "visual.transformer.resblocks.23.attn.out_proj.bias")
   [pool_hoist_add_3149] add_3149_pooled = Slice (add_3149, val_2, val_5, val_5)
   add_3264 = Add (add_3149_pooled, node_scaled_dot_product_attention_23_out)
   layer_norm_48 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (add_3264, "visual.transformer.resblocks.23.ln_2.weight", "visual.transformer.resblocks.23.ln_2.bias")
   val_126 = MatMul (layer_norm_48, val_76)
   linear_94 = Add (val_126, "visual.transformer.resblocks.23.mlp.c_fc.bias")
   gelu_23 = Gelu <approximate: string = "none"> (linear_94)
   val_127 = MatMul (gelu_23, val_77)
   linear_95 = Add (val_127, "visual.transformer.resblocks.23.mlp.c_proj.bias")
   add_3285 = Add (add_3264, linear_95)
   val_128 = Squeeze (add_3285, val_5)
   select_72 = LayerNormalization <axis: int = -1, epsilon: float = 1e-05, stash_type: int = 1> (val_128, "visual.ln_post.weight", "visual.ln_post.bias")
   [node_matmul] matmul = MatMul (select_72, "visual.proj")
   [node_linalg_vector_norm] linalg_vector_norm = ReduceL2 <keepdims: int = 1, noop_with_empty_axes: int = 0> (matmul, val_0)
   [node_clamp_min] clamp_min = Clip (linalg_vector_norm, val_1)
   [node_div] image_embedding = Div (matmul, clamp_min)
}

weights:
attn3d_split_3x1024 INT64[3] 0ec6f5651fd5
node_Conv_1352_fused_bias FLOAT[1024] 888d3aa8c182
node_scaled_dot_product_attention_10_wo_t FLOAT[1024,1024] 78a3341bad18
node_scaled_dot_product_attention_11_wo_t FLOAT[1024,1024] 6d8de2c1ee0e
node_scaled_dot_product_attention_12_wo_t FLOAT[1024,1024] 90f35896cf61
node_scaled_dot_product_attention_13_wo_t FLOAT[1024,1024] 9a58d221ce2a
node_scaled_dot_product_attention_14_wo_t FLOAT[1024,1024] 0e94292f8e95
node_scaled_dot_product_attention_15_wo_t FLOAT[1024,1024] 5dab7523c66c
node_scaled_dot_product_attention_16_wo_t FLOAT[1024,1024] 9e627ce0bfb1
node_scaled_dot_product_attention_17_wo_t FLOAT[1024,1024] 1db53429bdf9
node_scaled_dot_product_attention_18_wo_t FLOAT[1024,1024] 83e89877374a
node_scaled_dot_product_attention_19_wo_t FLOAT[1024,1024] 9ade838f0fb9
node_scaled_dot_product_attention_1_wo_t FLOAT[1024,1024] ee2a17b938ed
node_scaled_dot_product_attention_20_wo_t FLOAT[1024,1024] c232e6f1654f
node_scaled_dot_product_attention_21_wo_t FLOAT[1024,1024] cd90ab25f009
node_scaled_dot_product_attention_22_wo_t FLOAT[1024,1024] 5bde2bc41d86
node_scaled_dot_product_attention_23_wo_t FLOAT[1024,1024] 2013c46d84d5
node_scaled_dot_product_attention_2_wo_t FLOAT[1024,1024] e96868dba59d
node_scaled_dot_product_attention_3_wo_t FLOAT[1024,1024] 612a16d8d4fe
node_scaled_dot_product_attention_4_wo_t FLOAT[1024,1024] bf7fe38656f7
node_scaled_dot_product_attention_5_wo_t FLOAT[1024,1024] 353222bf7fac
node_scaled_dot_product_attention_6_wo_t FLOAT[1024,1024] ee9fe5c216c0
node_scaled_dot_product_attention_7_wo_t FLOAT[1024,1024] bb20cfd17d0e
node_scaled_dot_product_attention_8_wo_t FLOAT[1024,1024] 553ba34d0138
node_scaled_dot_product_attention_9_wo_t FLOAT[1024,1024] e8949f501870
node_scaled_dot_product_attention_wo_t FLOAT[1024,1024] 3e92775d4f76
val_0 INT64[1] 12a3ae445661
val_1 FLOAT[] 6708d9be4956
val_10 FLOAT[1024,4096] becbb0f81ced
val_11 FLOAT[4096,1024] f3c605d11142
val_12 FLOAT[1024,3072] 7f41962de643
val_13 FLOAT[1024,4096] f8bacd6b7c13
val_14 FLOAT[4096,1024] d09f3d8757ea
val_15 FLOAT[1024,3072] aac9a9345cb7
val_16 FLOAT[1024,4096] 138b99505894
val_17 FLOAT[4096,1024] 5f86158e2888
val_18 FLOAT[1024,3072] 3b6ef53021a1
val_19 FLOAT[1024,4096] 00de22ba1c68
val_2 INT64[1] af5570f5a181
val_20 FLOAT[4096,1024] aa9ae706023f
val_21 FLOAT[1024,3072] 3400e2b77325
val_22 FLOAT[1024,4096] 2fefa2b39e8e
val_23 FLOAT[4096,1024] 44a8c551af3b
val_24 FLOAT[1024,3072] 6eaa5f62077f
val_25 FLOAT[1024,4096] d3fb706639ec
val_26 FLOAT[4096,1024] 78783ecb4d7b
val_27 FLOAT[1024,3072] 93eba520ab8e
val_28 FLOAT[1024,4096] acc3eb16854b
val_29 FLOAT[4096,1024] 2fa0bd786670
val_3 INT64[6] 6b7d92eaae70
val_30 FLOAT[1024,3072] 8e1b56e5ea56
val_31 FLOAT[1024,4096] 27740e189d50
val_32 FLOAT[4096,1024] e409d2ba7c16
val_33 FLOAT[1024,3072] 829df605e68c
val_34 FLOAT[1024,4096] 975f441412c7
val_35 FLOAT[4096,1024] 6badfe97b90a
val_36 FLOAT[1024,3072] 3040cebd8fd1
val_37 FLOAT[1024,4096] 0afa2e67b4b6
val_38 FLOAT[4096,1024] 174bbaf0008c
val_39 FLOAT[1024,3072] 0197109458af
val_4 FLOAT[] df3f619804a9
val_40 FLOAT[1024,4096] 6437c49c6bb1
val_41 FLOAT[4096,1024] 11b6146956e1
val_42 FLOAT[1024,3072] 6792b495047e
val_43 FLOAT[1024,4096] 329a0b6bbdbd
val_44 FLOAT[4096,1024] 01ff7fa447b2
val_45 FLOAT[1024,3072] 92177823e2f1
val_46 FLOAT[1024,4096] c204a0dac3b3
val_47 FLOAT[4096,1024] 036858891dc7
val_48 FLOAT[1024,3072] 30ecd0013fb8
val_49 FLOAT[1024,4096] df338bfebcc2
val_5 INT64[1] 7c9fa136d441
val_50 FLOAT[4096,1024] 38f5d2e6dcaa
val_51 FLOAT[1024,3072] 893ff6e33a1c
val_52 FLOAT[1024,4096] 670f479b30ec
val_53 FLOAT[4096,1024] 088fce32420c
val_54 FLOAT[1024,3072] 1583b369eb1d
val_55 FLOAT[1024,4096] 94be38371f78
val_56 FLOAT[4096,1024] b1ebfe772c07
val_57 FLOAT[1024,3072] d67f4fbe39d1
val_58 FLOAT[1024,4096] 4fbd86378784
val_59 FLOAT[4096,1024] 708c987b713d
val_6 FLOAT[1024,3072] 71ccbf846781
val_60 FLOAT[1024,3072] 34a94fa22c6f
val_61 FLOAT[1024,4096] c361a0b19467
val_62 FLOAT[4096,1024] f063947aa35b
val_63 FLOAT[1024,3072] 47023d3cc744
val_64 FLOAT[1024,4096] f5a4689bcbc5
val_65 FLOAT[4096,1024] 9f47b2217e02
val_66 FLOAT[1024,3072] 9e67e013444c
val_67 FLOAT[1024,4096] 2711ef6e548c
val_68 FLOAT[4096,1024] e25d195958d9
val_69 FLOAT[1024,3072] d61b4c2aff8e
val_7 FLOAT[1024,4096] 79001c2085ff
val_70 FLOAT[1024,4096] 9b1359d04273
val_71 FLOAT[4096,1024] fc3bacca54f6
val_72 FLOAT[1024,3072] 6118ad1e58d5
val_73 FLOAT[1024,4096] 9854368e3a94
val_74 FLOAT[4096,1024] 2f86fa8f0f23
val_75 FLOAT[1024,3072] a8d9aaa9ea10
val_76 FLOAT[1024,4096] 0dc7facdcfe7
val_77 FLOAT[4096,1024] e0e51b1788df
val_78 FLOAT[1,257,1024] 2bee5c417b74
val_8 FLOAT[4096,1024] 8e79e21439ad
val_9 FLOAT[1024,3072] c07ead075ce3
view_target INT64[3] 3f85cfe8397f
visual.conv1.weight FLOAT[1024,3,14,14] 905278f3f30c
visual.ln_post.bias FLOAT[1024] 8b73004833a3
visual.ln_post.weight FLOAT[1024] a54d0c75da32
visual.ln_pre.bias FLOAT[1024] 4cab22fdecf2
visual.ln_pre.weight FLOAT[1024] 8a466c1899d5
visual.proj FLOAT[1024,768] a4b4affdb3ed
visual.transformer.resblocks.0.attn.in_proj_bias FLOAT[3072] adad3895d4ed
visual.transformer.resblocks.0.attn.out_proj.bias FLOAT[1024] 07852acf9e16
visual.transformer.resblocks.0.ln_1.bias FLOAT[1024] 8bc56b324887
visual.transformer.resblocks.0.ln_1.weight FLOAT[1024] 93a4946ac02f
visual.transformer.resblocks.0.ln_2.bias FLOAT[1024] ce4636cd6fab
visual.transformer.resblocks.0.ln_2.weight FLOAT[1024] 5632c41e1a82
visual.transformer.resblocks.0.mlp.c_fc.bias FLOAT[4096] 2b2b275b9458
visual.transformer.resblocks.0.mlp.c_proj.bias FLOAT[1024] d8de62ebb88a
visual.transformer.resblocks.1.attn.in_proj_bias FLOAT[3072] 2ab8812ba1a2
visual.transformer.resblocks.1.attn.out_proj.bias FLOAT[1024] 28fd013ccbd3
visual.transformer.resblocks.1.ln_1.bias FLOAT[1024] 300599f3c988
visual.transformer.resblocks.1.ln_1.weight FLOAT[1024] e5f82919dd02
visual.transformer.resblocks.1.ln_2.bias FLOAT[1024] 01c293874420
visual.transformer.resblocks.1.ln_2.weight FLOAT[1024] 4f226cafcf22
visual.transformer.resblocks.1.mlp.c_fc.bias FLOAT[4096] be9d96f548fd
visual.transformer.resblocks.1.mlp.c_proj.bias FLOAT[1024] d6404bb9e121
visual.transformer.resblocks.10.attn.in_proj_bias FLOAT[3072] a88acd56086d
visual.transformer.resblocks.10.attn.out_proj.bias FLOAT[1024] 6e0e744cad81
visual.transformer.resblocks.10.ln_1.bias FLOAT[1024] 9870540934e7
visual.transformer.resblocks.10.ln_1.weight FLOAT[1024] bdbe9f14196a
visual.transformer.resblocks.10.ln_2.bias FLOAT[1024] ca64896ebdb7
visual.transformer.resblocks.10.ln_2.weight FLOAT[1024] 7bda09baf9a0
visual.transformer.resblocks.10.mlp.c_fc.bias FLOAT[4096] 87d058f612f7
visual.transformer.resblocks.10.mlp.c_proj.bias FLOAT[1024] c2f00cd2a3d2
visual.transformer.resblocks.11.attn.in_proj_bias FLOAT[3072] 78e03a25f0fa
visual.transformer.resblocks.11.attn.out_proj.bias FLOAT[1024] 2a32dc15a36c
visual.transformer.resblocks.11.ln_1.bias FLOAT[1024] 16c608ea77f5
visual.transformer.resblocks.11.ln_1.weight FLOAT[1024] 8bd326339f01
visual.transformer.resblocks.11.ln_2.bias FLOAT[1024] 850be4653450
visual.transformer.resblocks.11.ln_2.weight FLOAT[1024] 5bcdef6b0c5f
visual.transformer.resblocks.11.mlp.c_fc.bias FLOAT[4096] 3d183d1f980b
visual.transformer.resblocks.11.mlp.c_proj.bias FLOAT[1024] 79ab9c00a877
visual.transformer.resblocks.12.attn.in_proj_bias FLOAT[3072] 8bd2519b9499
visual.transformer.resblocks.12.attn.out_proj.bias FLOAT[1024] 8e9e772175dc
visual.transformer.resblocks.12.ln_1.bias FLOAT[1024] aeca7f8457cb
visual.transformer.resblocks.12.ln_1.weight FLOAT[1024] d5e474c1da5d
visual.transformer.resblocks.12.ln_2.bias FLOAT[1024] e8a3b754773f
visual.transformer.resblocks.12.ln_2.weight FLOAT[1024] 0b5d183a860c
visual.transformer.resblocks.12.mlp.c_fc.bias FLOAT[4096] 4ac6b8d5fc16
visual.transformer.resblocks.12.mlp.c_proj.bias FLOAT[1024] ea94c7084fb7
visual.transformer.resblocks.13.attn.in_proj_bias FLOAT[3072] e61114327d2d
visual.transformer.resblocks.13.attn.out_proj.bias FLOAT[1024] 90a1e79b2804
visual.transformer.resblocks.13.ln_1.bias FLOAT[1024] 4d91e20dc20d
visual.transformer.resblocks.13.ln_1.weight FLOAT[1024] cdb4d18797c9
visual.transformer.resblocks.13.ln_2.bias FLOAT[1024] 59163c44b7a5
visual.transformer.resblocks.13.ln_2.weight FLOAT[1024] 9b67ef88dbc9
visual.transformer.resblocks.13.mlp.c_fc.bias FLOAT[4096] 3e3013e4178f
visual.transformer.resblocks.13.mlp.c_proj.bias FLOAT[1024] 6b9cf02d118f
visual.transformer.resblocks.14.attn.in_proj_bias FLOAT[3072] 80cb6b723490
visual.transformer.resblocks.14.attn.out_proj.bias FLOAT[1024] c54c3b6c9a3a
visual.transformer.resblocks.14.ln_1.bias FLOAT[1024] 8cfb33e8d932
visual.transformer.resblocks.14.ln_1.weight FLOAT[1024] 38da506797a4
visual.transformer.resblocks.14.ln_2.bias FLOAT[1024] b71a47bd1207
visual.transformer.resblocks.14.ln_2.weight FLOAT[1024] 7523992cabec
visual.transformer.resblocks.14.mlp.c_fc.bias FLOAT[4096] cf453419a09f
visual.transformer.resblocks.14.mlp.c_proj.bias FLOAT[1024] ad5a559160c1
visual.transformer.resblocks.15.attn.in_proj_bias FLOAT[3072] 1dd8a3a8abf0
visual.transformer.resblocks.15.attn.out_proj.bias FLOAT[1024] 197cfca49099
visual.transformer.resblocks.15.ln_1.bias FLOAT[1024] da5796ef40c6
visual.transformer.resblocks.15.ln_1.weight FLOAT[1024] 1a450a12fa95
visual.transformer.resblocks.15.ln_2.bias FLOAT[1024] c7f51d66df9f
visual.transformer.resblocks.15.ln_2.weight FLOAT[1024] 3c4813b93fcb
visual.transformer.resblocks.15.mlp.c_fc.bias FLOAT[4096] 644c929a0989
visual.transformer.resblocks.15.mlp.c_proj.bias FLOAT[1024] 712131cd06a8
visual.transformer.resblocks.16.attn.in_proj_bias FLOAT[3072] d55e8358d8e3
visual.transformer.resblocks.16.attn.out_proj.bias FLOAT[1024] 6ff8c2bd1423
visual.transformer.resblocks.16.ln_1.bias FLOAT[1024] a1a59db54bab
visual.transformer.resblocks.16.ln_1.weight FLOAT[1024] c0c6210ad15f
visual.transformer.resblocks.16.ln_2.bias FLOAT[1024] de54dbfe5d24
visual.transformer.resblocks.16.ln_2.weight FLOAT[1024] cc3df40e0837
visual.transformer.resblocks.16.mlp.c_fc.bias FLOAT[4096] 126a05aff705
visual.transformer.resblocks.16.mlp.c_proj.bias FLOAT[1024] bd2a9fa557a7
visual.transformer.resblocks.17.attn.in_proj_bias FLOAT[3072] 76ebfe82fac2
visual.transformer.resblocks.17.attn.out_proj.bias FLOAT[1024] 10e42b846d48
visual.transformer.resblocks.17.ln_1.bias FLOAT[1024] b9dd86d4c183
visual.transformer.resblocks.17.ln_1.weight FLOAT[1024] 2109219d0995
visual.transformer.resblocks.17.ln_2.bias FLOAT[1024] 078cd99dc4d1
visual.transformer.resblocks.17.ln_2.weight FLOAT[1024] 71ae900ede4a
visual.transformer.resblocks.17.mlp.c_fc.bias FLOAT[4096] a624d19805ea
visual.transformer.resblocks.17.mlp.c_proj.bias FLOAT[1024] 7dc5695d9265
visual.transformer.resblocks.18.attn.in_proj_bias FLOAT[3072] 0a5beefaf1d0
visual.transformer.resblocks.18.attn.out_proj.bias FLOAT[1024] ddde16d114d0
visual.transformer.resblocks.18.ln_1.bias FLOAT[1024] 30123ad5e979
visual.transformer.resblocks.18.ln_1.weight FLOAT[1024] 28606eee510d
visual.transformer.resblocks.18.ln_2.bias FLOAT[1024] 82e7a1b455db
visual.transformer.resblocks.18.ln_2.weight FLOAT[1024] 97e59948b7d7
visual.transformer.resblocks.18.mlp.c_fc.bias FLOAT[4096] 3a608d781538
visual.transformer.resblocks.18.mlp.c_proj.bias FLOAT[1024] 5046d1464d9c
visual.transformer.resblocks.19.attn.in_proj_bias FLOAT[3072] 0d57feacdde8
visual.transformer.resblocks.19.attn.out_proj.bias FLOAT[1024] 4db1b8786035
visual.transformer.resblocks.19.ln_1.bias FLOAT[1024] 185a9cff8fc9
visual.transformer.resblocks.19.ln_1.weight FLOAT[1024] c39c7333ce35
visual.transformer.resblocks.19.ln_2.bias FLOAT[1024] 94582edb2829
visual.transformer.resblocks.19.ln_2.weight FLOAT[1024] f061fd8e5874
visual.transformer.resblocks.19.mlp.c_fc.bias FLOAT[4096] fbda0f33691f
visual.transformer.resblocks.19.mlp.c_proj.bias FLOAT[1024] 464d717dfa0b
visual.transformer.resblocks.2.attn.in_proj_bias FLOAT[3072] 3efdf088d932
visual.transformer.resblocks.2.attn.out_proj.bias FLOAT[1024] 3658266678e2
visual.transformer.resblocks.2.ln_1.bias FLOAT[1024] 22354aad9ed0
visual.transformer.resblocks.2.ln_1.weight FLOAT[1024] ecb19fd307ef
visual.transformer.resblocks.2.ln_2.bias FLOAT[1024] e397c6bfda3a
visual.transformer.resblocks.2.ln_2.weight FLOAT[1024] ad8e830e2afd
visual.transformer.resblocks.2.mlp.c_fc.bias FLOAT[4096] bf78406b18f0
visual.transformer.resblocks.2.mlp.c_proj.bias FLOAT[1024] ec437ccb78f9
visual.transformer.resblocks.20.attn.in_proj_bias FLOAT[3072] 5496b72b8d87
visual.transformer.resblocks.20.attn.out_proj.bias FLOAT[1024] 0a01d8e7c221
visual.transformer.resblocks.20.ln_1.bias FLOAT[1024] 1d3a110ac8d8
visual.transformer.resblocks.20.ln_1.weight FLOAT[1024] 1377f2ba7558
visual.transformer.resblocks.20.ln_2.bias FLOAT[1024] adb620038cfc
visual.transformer.resblocks.20.ln_2.weight FLOAT[1024] 17110049282f
visual.transformer.resblocks.20.mlp.c_fc.bias FLOAT[4096] d69c2e597ba0
visual.transformer.resblocks.20.mlp.c_proj.bias FLOAT[1024] 8ec0246c034f
visual.transformer.resblocks.21.attn.in_proj_bias FLOAT[3072] a215916cfa6e
visual.transformer.resblocks.21.attn.out_proj.bias FLOAT[1024] 13381a629226
visual.transformer.resblocks.21.ln_1.bias FLOAT[1024] 2d52d8b02362
visual.transformer.resblocks.21.ln_1.weight FLOAT[1024] 6fbd4f935148
visual.transformer.resblocks.21.ln_2.bias FLOAT[1024] de66f2f5cc4c
visual.transformer.resblocks.21.ln_2.weight FLOAT[1024] 2fee3e61132a
visual.transformer.resblocks.21.mlp.c_fc.bias FLOAT[4096] e157334bfa97
visual.transformer.resblocks.21.mlp.c_proj.bias FLOAT[1024] 4a78f7394338
visual.transformer.resblocks.22.attn.in_proj_bias FLOAT[3072] 3f8259425db7
visual.transformer.resblocks.22.attn.out_proj.bias FLOAT[1024] 4a44a7021536
visual.transformer.resblocks.22.ln_1.bias FLOAT[1024] 0fbb9c5391d0
visual.transformer.resblocks.22.ln_1.weight FLOAT[1024] 7de9c66c8b0d
visual.transformer.resblocks.22.ln_2.bias FLOAT[1024] 2bab5345bb9f
visual.transformer.resblocks.22.ln_2.weight FLOAT[1024] 9686f590a556
visual.transformer.resblocks.22.mlp.c_fc.bias FLOAT[4096] 87232e10852e
visual.transformer.resblocks.22.mlp.c_proj.bias FLOAT[1024] e93727fdcf21
visual.transformer.resblocks.23.attn.in_proj_bias FLOAT[3072] 25795a3d2d89
visual.transformer.resblocks.23.attn.out_proj.bias FLOAT[1024] ca3c52288f30
visual.transformer.resblocks.23.ln_1.bias FLOAT[1024] 194a335b16ca
visual.transformer.resblocks.23.ln_1.weight FLOAT[1024] b4dcf7346a23
visual.transformer.resblocks.23.ln_2.bias FLOAT[1024] 0227c9adb0f4
visual.transformer.resblocks.23.ln_2.weight FLOAT[1024] 8faab0f78820
visual.transformer.resblocks.23.mlp.c_fc.bias FLOAT[4096] 4c8d89b1e9dd
visual.transformer.resblocks.23.mlp.c_proj.bias FLOAT[1024] f585a4694208
visual.transformer.resblocks.3.attn.in_proj_bias FLOAT[3072] a16f43d4b1a4
visual.transformer.resblocks.3.attn.out_proj.bias FLOAT[1024] e45b7e19e0e3
visual.transformer.resblocks.3.ln_1.bias FLOAT[1024] 1cd159cfc29e
visual.transformer.resblocks.3.ln_1.weight FLOAT[1024] 09acf1951bda
visual.transformer.resblocks.3.ln_2.bias FLOAT[1024] 4ebc624c8d5b
visual.transformer.resblocks.3.ln_2.weight FLOAT[1024] 84d5409916af
visual.transformer.resblocks.3.mlp.c_fc.bias FLOAT[4096] 8a3c1c10b1fc
visual.transformer.resblocks.3.mlp.c_proj.bias FLOAT[1024] 6ac82c601b04
visual.transformer.resblocks.4.attn.in_proj_bias FLOAT[3072] 986b40e58dac
visual.transformer.resblocks.4.attn.out_proj.bias FLOAT[1024] 5d6071802eaf
visual.transformer.resblocks.4.ln_1.bias FLOAT[1024] 11aac7547fee
visual.transformer.resblocks.4.ln_1.weight FLOAT[1024] 17357d706365
visual.transformer.resblocks.4.ln_2.bias FLOAT[1024] ce171ebece13
visual.transformer.resblocks.4.ln_2.weight FLOAT[1024] 30885606bc72
visual.transformer.resblocks.4.mlp.c_fc.bias FLOAT[4096] 7be43ccbb45c
visual.transformer.resblocks.4.mlp.c_proj.bias FLOAT[1024] aa040465c775
visual.transformer.resblocks.5.attn.in_proj_bias FLOAT[3072] fbf2fb12b5fb
visual.transformer.resblocks.5.attn.out_proj.bias FLOAT[1024] b0cf77ffe8cc
visual.transformer.resblocks.5.ln_1.bias FLOAT[1024] 4c57e9ed3076
visual.transformer.resblocks.5.ln_1.weight FLOAT[1024] 80cca3b1344a
visual.transformer.resblocks.5.ln_2.bias FLOAT[1024] e8ae4b33dd62
visual.transformer.resblocks.5.ln_2.weight FLOAT[1024] 8af21da37dd7
visual.transformer.resblocks.5.mlp.c_fc.bias FLOAT[4096] 00786b0ce2e8
visual.transformer.resblocks.5.mlp.c_proj.bias FLOAT[1024] 0639d32561db
visual.transformer.resblocks.6.attn.in_proj_bias FLOAT[3072] 2ee5e9da9d38
visual.transformer.resblocks.6.attn.out_proj.bias FLOAT[1024] d076ebdf7529
visual.transformer.resblocks.6.ln_1.bias FLOAT[1024] 3cf1dfc2e06e
visual.transformer.resblocks.6.ln_1.weight FLOAT[1024] dd58aa5ea2a6
visual.transformer.resblocks.6.ln_2.bias FLOAT[1024] 3577d80928a8
visual.transformer.resblocks.6.ln_2.weight FLOAT[1024] 8eeb5159f9a5
visual.transformer.resblocks.6.mlp.c_fc.bias FLOAT[4096] b369718a3ce3
visual.transformer.resblocks.6.mlp.c_proj.bias FLOAT[1024] 6a3dc7e9eeb6
visual.transformer.resblocks.7.attn.in_proj_bias FLOAT[3072] 063bdfd4c081
visual.transformer.resblocks.7.attn.out_proj.bias FLOAT[1024] 405fb500515e
visual.transformer.resblocks.7.ln_1.bias FLOAT[1024] 998b2cabb2b6
visual.transformer.resblocks.7.ln_1.weight FLOAT[1024] 7573a3de2d91
visual.transformer.resblocks.7.ln_2.bias FLOAT[1024] 9285fadfb24c
visual.transformer.resblocks.7.ln_2.weight FLOAT[1024] 37cd63c2038f
visual.transformer.resblocks.7.mlp.c_fc.bias FLOAT[4096] 91090c1b6cd3
visual.transformer.resblocks.7.mlp.c_proj.bias FLOAT[1024] e835ea63b517
visual.transformer.resblocks.8.attn.in_proj_bias FLOAT[3072] 36b9083811dd
visual.transformer.resblocks.8.attn.out_proj.bias FLOAT[1024] 72c987ba3121
visual.transformer.resblocks.8.ln_1.bias FLOAT[1024] 41fcf89f156e
visual.transformer.resblocks.8.ln_1.weight FLOAT[1024] eff59c5860b9
visual.transformer.resblocks.8.ln_2.bias FLOAT[1024] 181f76f7a179
visual.transformer.resblocks.8.ln_2.weight FLOAT[1024] 8cea8efe9afd
visual.transformer.resblocks.8.mlp.c_fc.bias FLOAT[4096] 62bbbd2efa22
visual.transformer.resblocks.8.mlp.c_proj.bias FLOAT[1024] 43a33be88eeb
visual.transformer.resblocks.9.attn.in_proj_bias FLOAT[3072] bf79de908e3f
visual.transformer.resblocks.9.attn.out_proj.bias FLOAT[1024] 226a74c75da2
visual.transformer.resblocks.9.ln_1.bias FLOAT[1024] d3a35f54c648
visual.transformer.resblocks.9.ln_1.weight FLOAT[1024] be122f60ad4f
visual.transformer.resblocks.9.ln_2.bias FLOAT[1024] 362f0f85edc5
visual.transformer.resblocks.9.ln_2.weight FLOAT[1024] 486884c069c6
visual.transformer.resblocks.9.mlp.c_fc.bias FLOAT[4096] 82c8d3b0358f
visual.transformer.resblocks.9.mlp.c_proj.bias FLOAT[1024] 95f0cefb677d
