<
   ir_version: 10,
   opset_import: ["" : 23],
   producer_name: "pytorch"
>
main_graph (int32[batch,64] text) => (float[batch,1024] text_embedding) 
   <
      float[batch,64,1024] add_1071
      float[batch,64,1024] add_1092
      float[batch,64,1024] add_119
      float[batch,64,1024] add_1207
      float[batch,64,1024] add_1228
      float[batch,64,1024] add_1343
      float[batch,64,1024] add_1364
      float[batch,64,1024] add_140
      float[batch,64,1024] add_1479
      float[batch,64,1024] add_1500
      float[batch,64,1024] add_1615
      float[batch,64,1024] add_1636
      float[batch,64,1024] add_1751
      float[batch,64,1024] add_1772
      float[batch,64,1024] add_1887
      float[batch,64,1024] add_1908
      float[batch,64,1024] add_2023
      float[batch,64,1024] add_2044
      float[batch,64,1024] add_2159
      float[batch,64,1024] add_2180
      float[batch,64,1024] add_2295
      float[batch,64,1024] add_2316
      float[batch,64,1024] add_2431
      float[batch,64,1024] add_2452
      float[batch,64,1024] add_255
      float[batch,64,1024] add_2567
      float[batch,64,1024] add_2588
      float[batch,64,1024] add_2703
      float[batch,64,1024] add_2724
      float[batch,64,1024] add_276
      float[batch,64,1024] add_2839
      float[batch,64,1024] add_2860
      float[batch,64,1024] add_2975
      float[batch,64,1024] add_2996
      float[batch,64,1024] add_3111
      float[batch,64,1024] add_3132
      float[batch,1,1024] add_3132_pooled
      float[batch,1,1024] add_3247
      float[batch,1,1024] add_3268
      float[batch,64,1024] add_391
      float[batch,64,1024] add_4
      float[batch,64,1024] add_412
      float[batch,64,1024] add_527
      float[batch,64,1024] add_548
      float[batch,64,1024] add_663
      float[batch,64,1024] add_684
      float[batch,64,1024] add_799
      float[batch,64,1024] add_820
      float[batch,64,1024] add_935
      float[batch,64,1024] add_956
      float[batch,1] clamp_min
      float[batch,64,1024] embedding
      float[batch,64,4096] gelu
      float[batch,64,4096] gelu_1
      float[batch,64,4096] gelu_10
      float[batch,64,4096] gelu_11
      float[batch,64,4096] gelu_12
      float[batch,64,4096] gelu_13
      float[batch,64,4096] gelu_14
      float[batch,64,4096] gelu_15
      float[batch,64,4096] gelu_16
      float[batch,64,4096] gelu_17
      float[batch,64,4096] gelu_18
      float[batch,64,4096] gelu_19
      float[batch,64,4096] gelu_2
      float[batch,64,4096] gelu_20
      float[batch,64,4096] gelu_21
      float[batch,64,4096] gelu_22
      float[batch,1,4096] gelu_23
      float[batch,64,4096] gelu_3
      float[batch,64,4096] gelu_4
      float[batch,64,4096] gelu_5
      float[batch,64,4096] gelu_6
      float[batch,64,4096] gelu_7
      float[batch,64,4096] gelu_8
      float[batch,64,4096] gelu_9
      float[batch,64,1024] layer_norm
      float[batch,64,1024] layer_norm_1
      float[batch,64,1024] layer_norm_10
      float[batch,64,1024] layer_norm_11
      float[batch,64,1024] layer_norm_12
      float[batch,64,1024] layer_norm_13
      float[batch,64,1024] layer_norm_14
      float[batch,64,1024] layer_norm_15
      float[batch,64,1024] layer_norm_16
      float[batch,64,1024] layer_norm_17
      float[batch,64,1024] layer_norm_18
      float[batch,64,1024] layer_norm_19
      float[batch,64,1024] layer_norm_2
      float[batch,64,1024] layer_norm_20
      float[batch,64,1024] layer_norm_21
      float[batch,64,1024] layer_norm_22
      float[batch,64,1024] layer_norm_23
      float[batch,64,1024] layer_norm_24
      float[batch,64,1024] layer_norm_25
      float[batch,64,1024] layer_norm_26
      float[batch,64,1024] layer_norm_27
      float[batch,64,1024] layer_norm_28
      float[batch,64,1024] layer_norm_29
      float[batch,64,1024] layer_norm_3
      float[batch,64,1024] layer_norm_30
      float[batch,64,1024] layer_norm_31
      float[batch,64,1024] layer_norm_32
      float[batch,64,1024] layer_norm_33
      float[batch,64,1024] layer_norm_34
      float[batch,64,1024] layer_norm_35
      float[batch,64,1024] layer_norm_36
      float[batch,64,1024] layer_norm_37
      float[batch,64,1024] layer_norm_38
      float[batch,64,1024] layer_norm_39
      float[batch,64,1024] layer_norm_4
      float[batch,64,1024] layer_norm_40
      float[batch,64,1024] layer_norm_41
      float[batch,64,1024] layer_norm_42
      float[batch,64,1024] layer_norm_43
      float[batch,64,1024] layer_norm_44
      float[batch,64,1024] layer_norm_45
      float[batch,64,1024] layer_norm_46
      float[batch,1,1024] layer_norm_47
      float[batch,64,1024] layer_norm_5
      float[batch,64,1024] layer_norm_6
      float[batch,64,1024] layer_norm_7
      float[batch,64,1024] layer_norm_8
      float[batch,64,1024] layer_norm_9
      float[batch,1] linalg_vector_norm
      float[batch,64,4096] linear_10
      float[batch,64,1024] linear_11
      float[batch,64,4096] linear_14
      float[batch,64,1024] linear_15
      float[batch,64,4096] linear_18
      float[batch,64,1024] linear_19
      float[batch,64,4096] linear_2
      float[batch,64,4096] linear_22
      float[batch,64,1024] linear_23
      float[batch,64,4096] linear_26
      float[batch,64,1024] linear_27
      float[batch,64,1024] linear_3
      float[batch,64,4096] linear_30
      float[batch,64,1024] linear_31
      float[batch,64,4096] linear_34
      float[batch,64,1024] linear_35
      float[batch,64,4096] linear_38
      float[batch,64,1024] linear_39
      float[batch,64,4096] linear_42
      float[batch,64,1024] linear_43
      float[batch,64,4096] linear_46
      float[batch,64,1024] linear_47
      float[batch,64,4096] linear_50
      float[batch,64,1024] linear_51
      float[batch,64,4096] linear_54
      float[batch,64,1024] linear_55
      float[batch,64,4096] linear_58
      float[batch,64,1024] linear_59
      float[batch,64,4096] linear_6
      float[batch,64,4096] linear_62
      float[batch,64,1024] linear_63
      float[batch,64,4096] linear_66
      float[batch,64,1024] linear_67
      float[batch,64,1024] linear_7
      float[batch,64,4096] linear_70
      float[batch,64,1024] linear_71
      float[batch,64,4096] linear_74
      float[batch,64,1024] linear_75
      float[batch,64,4096] linear_78
      float[batch,64,1024] linear_79
      float[batch,64,4096] linear_82
      float[batch,64,1024] linear_83
      float[batch,64,4096] linear_86
      float[batch,64,1024] linear_87
      float[batch,64,4096] linear_90
      float[batch,64,1024] linear_91
      float[batch,1,4096] linear_94
      float[batch,1,1024] linear_95
      float[batch,1024] linear_96
      float[batch,64,1024] node_scaled_dot_product_attention_10_k
      float[batch,64,1024] node_scaled_dot_product_attention_10_out
      float[batch,64,1024] node_scaled_dot_product_attention_10_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_10_q
      float[batch,64,3072] node_scaled_dot_product_attention_10_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_10_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_10_v
      float[batch,64,1024] node_scaled_dot_product_attention_11_k
      float[batch,64,1024] node_scaled_dot_product_attention_11_out
      float[batch,64,1024] node_scaled_dot_product_attention_11_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_11_q
      float[batch,64,3072] node_scaled_dot_product_attention_11_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_11_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_11_v
      float[batch,64,1024] node_scaled_dot_product_attention_12_k
      float[batch,64,1024] node_scaled_dot_product_attention_12_out
      float[batch,64,1024] node_scaled_dot_product_attention_12_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_12_q
      float[batch,64,3072] node_scaled_dot_product_attention_12_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_12_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_12_v
      float[batch,64,1024] node_scaled_dot_product_attention_13_k
      float[batch,64,1024] node_scaled_dot_product_attention_13_out
      float[batch,64,1024] node_scaled_dot_product_attention_13_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_13_q
      float[batch,64,3072] node_scaled_dot_product_attention_13_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_13_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_13_v
      float[batch,64,1024] node_scaled_dot_product_attention_14_k
      float[batch,64,1024] node_scaled_dot_product_attention_14_out
      float[batch,64,1024] node_scaled_dot_product_attention_14_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_14_q
      float[batch,64,3072] node_scaled_dot_product_attention_14_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_14_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_14_v
      float[batch,64,1024] node_scaled_dot_product_attention_15_k
      float[batch,64,1024] node_scaled_dot_product_attention_15_out
      float[batch,64,1024] node_scaled_dot_product_attention_15_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_15_q
      float[batch,64,3072] node_scaled_dot_product_attention_15_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_15_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_15_v
      float[batch,64,1024] node_scaled_dot_product_attention_16_k
      float[batch,64,1024] node_scaled_dot_product_attention_16_out
      float[batch,64,1024] node_scaled_dot_product_attention_16_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_16_q
      float[batch,64,3072] node_scaled_dot_product_attention_16_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_16_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_16_v
      float[batch,64,1024] node_scaled_dot_product_attention_17_k
      float[batch,64,1024] node_scaled_dot_product_attention_17_out
      float[batch,64,1024] node_scaled_dot_product_attention_17_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_17_q
      float[batch,64,3072] node_scaled_dot_product_attention_17_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_17_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_17_v
      float[batch,64,1024] node_scaled_dot_product_attention_18_k
      float[batch,64,1024] node_scaled_dot_product_attention_18_out
      float[batch,64,1024] node_scaled_dot_product_attention_18_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_18_q
      float[batch,64,3072] node_scaled_dot_product_attention_18_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_18_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_18_v
      float[batch,64,1024] node_scaled_dot_product_attention_19_k
      float[batch,64,1024] node_scaled_dot_product_attention_19_out
      float[batch,64,1024] node_scaled_dot_product_attention_19_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_19_q
      float[batch,64,3072] node_scaled_dot_product_attention_19_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_19_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_19_v
      float[batch,64,1024] node_scaled_dot_product_attention_1_k
      float[batch,64,1024] node_scaled_dot_product_attention_1_out
      float[batch,64,1024] node_scaled_dot_product_attention_1_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_1_q
      float[batch,64,3072] node_scaled_dot_product_attention_1_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_1_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_1_v
      float[batch,64,1024] node_scaled_dot_product_attention_20_k
      float[batch,64,1024] node_scaled_dot_product_attention_20_out
      float[batch,64,1024] node_scaled_dot_product_attention_20_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_20_q
      float[batch,64,3072] node_scaled_dot_product_attention_20_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_20_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_20_v
      float[batch,64,1024] node_scaled_dot_product_attention_21_k
      float[batch,64,1024] node_scaled_dot_product_attention_21_out
      float[batch,64,1024] node_scaled_dot_product_attention_21_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_21_q
      float[batch,64,3072] node_scaled_dot_product_attention_21_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_21_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_21_v
      float[batch,64,1024] node_scaled_dot_product_attention_22_k
      float[batch,64,1024] node_scaled_dot_product_attention_22_out
      float[batch,64,1024] node_scaled_dot_product_attention_22_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_22_q
      float[batch,64,3072] node_scaled_dot_product_attention_22_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_22_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_22_v
      float[batch,64,1024] 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,64,1024] node_scaled_dot_product_attention_23_q
      float[batch,1,1024] node_scaled_dot_product_attention_23_q_pooled
      float[batch,64,3072] node_scaled_dot_product_attention_23_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_23_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_23_v
      float[batch,64,1024] node_scaled_dot_product_attention_2_k
      float[batch,64,1024] node_scaled_dot_product_attention_2_out
      float[batch,64,1024] node_scaled_dot_product_attention_2_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_2_q
      float[batch,64,3072] node_scaled_dot_product_attention_2_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_2_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_2_v
      float[batch,64,1024] node_scaled_dot_product_attention_3_k
      float[batch,64,1024] node_scaled_dot_product_attention_3_out
      float[batch,64,1024] node_scaled_dot_product_attention_3_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_3_q
      float[batch,64,3072] node_scaled_dot_product_attention_3_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_3_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_3_v
      float[batch,64,1024] node_scaled_dot_product_attention_4_k
      float[batch,64,1024] node_scaled_dot_product_attention_4_out
      float[batch,64,1024] node_scaled_dot_product_attention_4_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_4_q
      float[batch,64,3072] node_scaled_dot_product_attention_4_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_4_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_4_v
      float[batch,64,1024] node_scaled_dot_product_attention_5_k
      float[batch,64,1024] node_scaled_dot_product_attention_5_out
      float[batch,64,1024] node_scaled_dot_product_attention_5_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_5_q
      float[batch,64,3072] node_scaled_dot_product_attention_5_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_5_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_5_v
      float[batch,64,1024] node_scaled_dot_product_attention_6_k
      float[batch,64,1024] node_scaled_dot_product_attention_6_out
      float[batch,64,1024] node_scaled_dot_product_attention_6_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_6_q
      float[batch,64,3072] node_scaled_dot_product_attention_6_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_6_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_6_v
      float[batch,64,1024] node_scaled_dot_product_attention_7_k
      float[batch,64,1024] node_scaled_dot_product_attention_7_out
      float[batch,64,1024] node_scaled_dot_product_attention_7_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_7_q
      float[batch,64,3072] node_scaled_dot_product_attention_7_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_7_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_7_v
      float[batch,64,1024] node_scaled_dot_product_attention_8_k
      float[batch,64,1024] node_scaled_dot_product_attention_8_out
      float[batch,64,1024] node_scaled_dot_product_attention_8_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_8_q
      float[batch,64,3072] node_scaled_dot_product_attention_8_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_8_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_8_v
      float[batch,64,1024] node_scaled_dot_product_attention_9_k
      float[batch,64,1024] node_scaled_dot_product_attention_9_out
      float[batch,64,1024] node_scaled_dot_product_attention_9_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_9_q
      float[batch,64,3072] node_scaled_dot_product_attention_9_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_9_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_9_v
      float[batch,64,1024] node_scaled_dot_product_attention_k
      float[batch,64,1024] node_scaled_dot_product_attention_out
      float[batch,64,1024] node_scaled_dot_product_attention_out_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_q
      float[batch,64,3072] node_scaled_dot_product_attention_qkv
      float[batch,64,3072] node_scaled_dot_product_attention_qkv_mm_out
      float[batch,64,1024] node_scaled_dot_product_attention_v
      float[batch,64,1024] scaled_dot_product_attention
      float[batch,64,1024] scaled_dot_product_attention_1
      float[batch,64,1024] scaled_dot_product_attention_10
      float[batch,64,1024] scaled_dot_product_attention_11
      float[batch,64,1024] scaled_dot_product_attention_12
      float[batch,64,1024] scaled_dot_product_attention_13
      float[batch,64,1024] scaled_dot_product_attention_14
      float[batch,64,1024] scaled_dot_product_attention_15
      float[batch,64,1024] scaled_dot_product_attention_16
      float[batch,64,1024] scaled_dot_product_attention_17
      float[batch,64,1024] scaled_dot_product_attention_18
      float[batch,64,1024] scaled_dot_product_attention_19
      float[batch,64,1024] scaled_dot_product_attention_2
      float[batch,64,1024] scaled_dot_product_attention_20
      float[batch,64,1024] scaled_dot_product_attention_21
      float[batch,64,1024] scaled_dot_product_attention_22
      float[batch,1,1024] scaled_dot_product_attention_23
      float[batch,64,1024] scaled_dot_product_attention_3
      float[batch,64,1024] scaled_dot_product_attention_4
      float[batch,64,1024] scaled_dot_product_attention_5
      float[batch,64,1024] scaled_dot_product_attention_6
      float[batch,64,1024] scaled_dot_product_attention_7
      float[batch,64,1024] scaled_dot_product_attention_8
      float[batch,64,1024] scaled_dot_product_attention_9
      float[batch,1024] select_72
      float[batch,64,1024] val_100
      float[batch,64,4096] val_101
      float[batch,64,1024] val_102
      float[batch,64,4096] val_103
      float[batch,64,1024] val_104
      float[batch,64,4096] val_105
      float[batch,64,1024] val_106
      float[batch,64,4096] val_107
      float[batch,64,1024] val_108
      float[batch,64,4096] val_109
      float[batch,64,1024] val_110
      float[batch,64,4096] val_111
      float[batch,64,1024] val_112
      float[batch,64,4096] val_113
      float[batch,64,1024] val_114
      float[batch,64,4096] val_115
      float[batch,64,1024] val_116
      float[batch,64,4096] val_117
      float[batch,64,1024] val_118
      float[batch,64,4096] val_119
      float[batch,64,1024] val_120
      float[batch,64,4096] val_121
      float[batch,64,1024] val_122
      float[batch,1,4096] val_123
      float[batch,1,1024] val_124
      float[batch,1024] val_125
      float[batch,64,4096] val_77
      float[batch,64,1024] val_78
      float[batch,64,4096] val_79
      float[batch,64,1024] val_80
      float[batch,64,4096] val_81
      float[batch,64,1024] val_82
      float[batch,64,4096] val_83
      float[batch,64,1024] val_84
      float[batch,64,4096] val_85
      float[batch,64,1024] val_86
      float[batch,64,4096] val_87
      float[batch,64,1024] val_88
      float[batch,64,4096] val_89
      float[batch,64,1024] val_90
      float[batch,64,4096] val_91
      float[batch,64,1024] val_92
      float[batch,64,4096] val_93
      float[batch,64,1024] val_94
      float[batch,64,4096] val_95
      float[batch,64,1024] val_96
      float[batch,64,4096] val_97
      float[batch,64,1024] val_98
      float[batch,64,4096] val_99
   >
{
   val_76 = Gather <axis: int = 0> ("text.token_embedding.weight_fp16", text)
   embedding = Cast <to: int = 1> (val_76)
   add_4 = Add (embedding, "text.positional_embedding")
   [node_layer_norm] layer_norm = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_4, "text.transformer.resblocks.0.ln_1.weight", "text.transformer.resblocks.0.ln_1.bias")
   [node_scaled_dot_product_attention_qkv_mm] node_scaled_dot_product_attention_qkv_mm_out = MatMul (layer_norm, val_4)
   [node_scaled_dot_product_attention_qkv_bias] node_scaled_dot_product_attention_qkv = Add (node_scaled_dot_product_attention_qkv_mm_out, "text.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, "text.transformer.resblocks.0.attn.out_proj.bias")
   add_119 = Add (add_4, node_scaled_dot_product_attention_out)
   layer_norm_1 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_119, "text.transformer.resblocks.0.ln_2.weight", "text.transformer.resblocks.0.ln_2.bias")
   val_77 = MatMul (layer_norm_1, val_5)
   linear_2 = Add (val_77, "text.transformer.resblocks.0.mlp.c_fc.bias")
   [node_gelu] gelu = Gelu <approximate: string = "none"> (linear_2)
   val_78 = MatMul (gelu, val_6)
   linear_3 = Add (val_78, "text.transformer.resblocks.0.mlp.c_proj.bias")
   add_140 = Add (add_119, linear_3)
   layer_norm_2 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_140, "text.transformer.resblocks.1.ln_1.weight", "text.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_2, val_7)
   [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, "text.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, "text.transformer.resblocks.1.attn.out_proj.bias")
   add_255 = Add (add_140, node_scaled_dot_product_attention_1_out)
   layer_norm_3 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_255, "text.transformer.resblocks.1.ln_2.weight", "text.transformer.resblocks.1.ln_2.bias")
   val_79 = MatMul (layer_norm_3, val_8)
   linear_6 = Add (val_79, "text.transformer.resblocks.1.mlp.c_fc.bias")
   gelu_1 = Gelu <approximate: string = "none"> (linear_6)
   val_80 = MatMul (gelu_1, val_9)
   linear_7 = Add (val_80, "text.transformer.resblocks.1.mlp.c_proj.bias")
   add_276 = Add (add_255, linear_7)
   layer_norm_4 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_276, "text.transformer.resblocks.2.ln_1.weight", "text.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_4, val_10)
   [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, "text.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, "text.transformer.resblocks.2.attn.out_proj.bias")
   add_391 = Add (add_276, node_scaled_dot_product_attention_2_out)
   layer_norm_5 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_391, "text.transformer.resblocks.2.ln_2.weight", "text.transformer.resblocks.2.ln_2.bias")
   val_81 = MatMul (layer_norm_5, val_11)
   linear_10 = Add (val_81, "text.transformer.resblocks.2.mlp.c_fc.bias")
   gelu_2 = Gelu <approximate: string = "none"> (linear_10)
   val_82 = MatMul (gelu_2, val_12)
   linear_11 = Add (val_82, "text.transformer.resblocks.2.mlp.c_proj.bias")
   add_412 = Add (add_391, linear_11)
   layer_norm_6 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_412, "text.transformer.resblocks.3.ln_1.weight", "text.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_6, val_13)
   [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, "text.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, "text.transformer.resblocks.3.attn.out_proj.bias")
   add_527 = Add (add_412, node_scaled_dot_product_attention_3_out)
   layer_norm_7 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_527, "text.transformer.resblocks.3.ln_2.weight", "text.transformer.resblocks.3.ln_2.bias")
   val_83 = MatMul (layer_norm_7, val_14)
   linear_14 = Add (val_83, "text.transformer.resblocks.3.mlp.c_fc.bias")
   gelu_3 = Gelu <approximate: string = "none"> (linear_14)
   val_84 = MatMul (gelu_3, val_15)
   linear_15 = Add (val_84, "text.transformer.resblocks.3.mlp.c_proj.bias")
   add_548 = Add (add_527, linear_15)
   layer_norm_8 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_548, "text.transformer.resblocks.4.ln_1.weight", "text.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_8, val_16)
   [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, "text.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, "text.transformer.resblocks.4.attn.out_proj.bias")
   add_663 = Add (add_548, node_scaled_dot_product_attention_4_out)
   layer_norm_9 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_663, "text.transformer.resblocks.4.ln_2.weight", "text.transformer.resblocks.4.ln_2.bias")
   val_85 = MatMul (layer_norm_9, val_17)
   linear_18 = Add (val_85, "text.transformer.resblocks.4.mlp.c_fc.bias")
   gelu_4 = Gelu <approximate: string = "none"> (linear_18)
   val_86 = MatMul (gelu_4, val_18)
   linear_19 = Add (val_86, "text.transformer.resblocks.4.mlp.c_proj.bias")
   add_684 = Add (add_663, linear_19)
   layer_norm_10 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_684, "text.transformer.resblocks.5.ln_1.weight", "text.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_10, val_19)
   [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, "text.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, "text.transformer.resblocks.5.attn.out_proj.bias")
   add_799 = Add (add_684, node_scaled_dot_product_attention_5_out)
   layer_norm_11 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_799, "text.transformer.resblocks.5.ln_2.weight", "text.transformer.resblocks.5.ln_2.bias")
   val_87 = MatMul (layer_norm_11, val_20)
   linear_22 = Add (val_87, "text.transformer.resblocks.5.mlp.c_fc.bias")
   gelu_5 = Gelu <approximate: string = "none"> (linear_22)
   val_88 = MatMul (gelu_5, val_21)
   linear_23 = Add (val_88, "text.transformer.resblocks.5.mlp.c_proj.bias")
   add_820 = Add (add_799, linear_23)
   layer_norm_12 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_820, "text.transformer.resblocks.6.ln_1.weight", "text.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_12, val_22)
   [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, "text.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, "text.transformer.resblocks.6.attn.out_proj.bias")
   add_935 = Add (add_820, node_scaled_dot_product_attention_6_out)
   layer_norm_13 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_935, "text.transformer.resblocks.6.ln_2.weight", "text.transformer.resblocks.6.ln_2.bias")
   val_89 = MatMul (layer_norm_13, val_23)
   linear_26 = Add (val_89, "text.transformer.resblocks.6.mlp.c_fc.bias")
   gelu_6 = Gelu <approximate: string = "none"> (linear_26)
   val_90 = MatMul (gelu_6, val_24)
   linear_27 = Add (val_90, "text.transformer.resblocks.6.mlp.c_proj.bias")
   add_956 = Add (add_935, linear_27)
   layer_norm_14 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_956, "text.transformer.resblocks.7.ln_1.weight", "text.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_14, val_25)
   [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, "text.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, "text.transformer.resblocks.7.attn.out_proj.bias")
   add_1071 = Add (add_956, node_scaled_dot_product_attention_7_out)
   layer_norm_15 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1071, "text.transformer.resblocks.7.ln_2.weight", "text.transformer.resblocks.7.ln_2.bias")
   val_91 = MatMul (layer_norm_15, val_26)
   linear_30 = Add (val_91, "text.transformer.resblocks.7.mlp.c_fc.bias")
   gelu_7 = Gelu <approximate: string = "none"> (linear_30)
   val_92 = MatMul (gelu_7, val_27)
   linear_31 = Add (val_92, "text.transformer.resblocks.7.mlp.c_proj.bias")
   add_1092 = Add (add_1071, linear_31)
   layer_norm_16 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1092, "text.transformer.resblocks.8.ln_1.weight", "text.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_16, val_28)
   [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, "text.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, "text.transformer.resblocks.8.attn.out_proj.bias")
   add_1207 = Add (add_1092, node_scaled_dot_product_attention_8_out)
   layer_norm_17 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1207, "text.transformer.resblocks.8.ln_2.weight", "text.transformer.resblocks.8.ln_2.bias")
   val_93 = MatMul (layer_norm_17, val_29)
   linear_34 = Add (val_93, "text.transformer.resblocks.8.mlp.c_fc.bias")
   gelu_8 = Gelu <approximate: string = "none"> (linear_34)
   val_94 = MatMul (gelu_8, val_30)
   linear_35 = Add (val_94, "text.transformer.resblocks.8.mlp.c_proj.bias")
   add_1228 = Add (add_1207, linear_35)
   layer_norm_18 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1228, "text.transformer.resblocks.9.ln_1.weight", "text.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_18, val_31)
   [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, "text.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, "text.transformer.resblocks.9.attn.out_proj.bias")
   add_1343 = Add (add_1228, node_scaled_dot_product_attention_9_out)
   layer_norm_19 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1343, "text.transformer.resblocks.9.ln_2.weight", "text.transformer.resblocks.9.ln_2.bias")
   val_95 = MatMul (layer_norm_19, val_32)
   linear_38 = Add (val_95, "text.transformer.resblocks.9.mlp.c_fc.bias")
   gelu_9 = Gelu <approximate: string = "none"> (linear_38)
   val_96 = MatMul (gelu_9, val_33)
   linear_39 = Add (val_96, "text.transformer.resblocks.9.mlp.c_proj.bias")
   add_1364 = Add (add_1343, linear_39)
   layer_norm_20 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1364, "text.transformer.resblocks.10.ln_1.weight", "text.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_20, val_34)
   [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, "text.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, "text.transformer.resblocks.10.attn.out_proj.bias")
   add_1479 = Add (add_1364, node_scaled_dot_product_attention_10_out)
   layer_norm_21 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1479, "text.transformer.resblocks.10.ln_2.weight", "text.transformer.resblocks.10.ln_2.bias")
   val_97 = MatMul (layer_norm_21, val_35)
   linear_42 = Add (val_97, "text.transformer.resblocks.10.mlp.c_fc.bias")
   gelu_10 = Gelu <approximate: string = "none"> (linear_42)
   val_98 = MatMul (gelu_10, val_36)
   linear_43 = Add (val_98, "text.transformer.resblocks.10.mlp.c_proj.bias")
   add_1500 = Add (add_1479, linear_43)
   layer_norm_22 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1500, "text.transformer.resblocks.11.ln_1.weight", "text.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_22, val_37)
   [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, "text.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, "text.transformer.resblocks.11.attn.out_proj.bias")
   add_1615 = Add (add_1500, node_scaled_dot_product_attention_11_out)
   layer_norm_23 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1615, "text.transformer.resblocks.11.ln_2.weight", "text.transformer.resblocks.11.ln_2.bias")
   val_99 = MatMul (layer_norm_23, val_38)
   linear_46 = Add (val_99, "text.transformer.resblocks.11.mlp.c_fc.bias")
   gelu_11 = Gelu <approximate: string = "none"> (linear_46)
   val_100 = MatMul (gelu_11, val_39)
   linear_47 = Add (val_100, "text.transformer.resblocks.11.mlp.c_proj.bias")
   add_1636 = Add (add_1615, linear_47)
   layer_norm_24 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1636, "text.transformer.resblocks.12.ln_1.weight", "text.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_24, val_40)
   [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, "text.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, "text.transformer.resblocks.12.attn.out_proj.bias")
   add_1751 = Add (add_1636, node_scaled_dot_product_attention_12_out)
   layer_norm_25 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1751, "text.transformer.resblocks.12.ln_2.weight", "text.transformer.resblocks.12.ln_2.bias")
   val_101 = MatMul (layer_norm_25, val_41)
   linear_50 = Add (val_101, "text.transformer.resblocks.12.mlp.c_fc.bias")
   gelu_12 = Gelu <approximate: string = "none"> (linear_50)
   val_102 = MatMul (gelu_12, val_42)
   linear_51 = Add (val_102, "text.transformer.resblocks.12.mlp.c_proj.bias")
   add_1772 = Add (add_1751, linear_51)
   layer_norm_26 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1772, "text.transformer.resblocks.13.ln_1.weight", "text.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_26, val_43)
   [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, "text.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, "text.transformer.resblocks.13.attn.out_proj.bias")
   add_1887 = Add (add_1772, node_scaled_dot_product_attention_13_out)
   layer_norm_27 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1887, "text.transformer.resblocks.13.ln_2.weight", "text.transformer.resblocks.13.ln_2.bias")
   val_103 = MatMul (layer_norm_27, val_44)
   linear_54 = Add (val_103, "text.transformer.resblocks.13.mlp.c_fc.bias")
   gelu_13 = Gelu <approximate: string = "none"> (linear_54)
   val_104 = MatMul (gelu_13, val_45)
   linear_55 = Add (val_104, "text.transformer.resblocks.13.mlp.c_proj.bias")
   add_1908 = Add (add_1887, linear_55)
   layer_norm_28 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_1908, "text.transformer.resblocks.14.ln_1.weight", "text.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_28, val_46)
   [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, "text.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, "text.transformer.resblocks.14.attn.out_proj.bias")
   add_2023 = Add (add_1908, node_scaled_dot_product_attention_14_out)
   layer_norm_29 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2023, "text.transformer.resblocks.14.ln_2.weight", "text.transformer.resblocks.14.ln_2.bias")
   val_105 = MatMul (layer_norm_29, val_47)
   linear_58 = Add (val_105, "text.transformer.resblocks.14.mlp.c_fc.bias")
   gelu_14 = Gelu <approximate: string = "none"> (linear_58)
   val_106 = MatMul (gelu_14, val_48)
   linear_59 = Add (val_106, "text.transformer.resblocks.14.mlp.c_proj.bias")
   add_2044 = Add (add_2023, linear_59)
   layer_norm_30 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2044, "text.transformer.resblocks.15.ln_1.weight", "text.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_30, val_49)
   [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, "text.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, "text.transformer.resblocks.15.attn.out_proj.bias")
   add_2159 = Add (add_2044, node_scaled_dot_product_attention_15_out)
   layer_norm_31 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2159, "text.transformer.resblocks.15.ln_2.weight", "text.transformer.resblocks.15.ln_2.bias")
   val_107 = MatMul (layer_norm_31, val_50)
   linear_62 = Add (val_107, "text.transformer.resblocks.15.mlp.c_fc.bias")
   gelu_15 = Gelu <approximate: string = "none"> (linear_62)
   val_108 = MatMul (gelu_15, val_51)
   linear_63 = Add (val_108, "text.transformer.resblocks.15.mlp.c_proj.bias")
   add_2180 = Add (add_2159, linear_63)
   layer_norm_32 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2180, "text.transformer.resblocks.16.ln_1.weight", "text.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_32, val_52)
   [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, "text.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, "text.transformer.resblocks.16.attn.out_proj.bias")
   add_2295 = Add (add_2180, node_scaled_dot_product_attention_16_out)
   layer_norm_33 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2295, "text.transformer.resblocks.16.ln_2.weight", "text.transformer.resblocks.16.ln_2.bias")
   val_109 = MatMul (layer_norm_33, val_53)
   linear_66 = Add (val_109, "text.transformer.resblocks.16.mlp.c_fc.bias")
   gelu_16 = Gelu <approximate: string = "none"> (linear_66)
   val_110 = MatMul (gelu_16, val_54)
   linear_67 = Add (val_110, "text.transformer.resblocks.16.mlp.c_proj.bias")
   add_2316 = Add (add_2295, linear_67)
   layer_norm_34 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2316, "text.transformer.resblocks.17.ln_1.weight", "text.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_34, val_55)
   [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, "text.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, "text.transformer.resblocks.17.attn.out_proj.bias")
   add_2431 = Add (add_2316, node_scaled_dot_product_attention_17_out)
   layer_norm_35 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2431, "text.transformer.resblocks.17.ln_2.weight", "text.transformer.resblocks.17.ln_2.bias")
   val_111 = MatMul (layer_norm_35, val_56)
   linear_70 = Add (val_111, "text.transformer.resblocks.17.mlp.c_fc.bias")
   gelu_17 = Gelu <approximate: string = "none"> (linear_70)
   val_112 = MatMul (gelu_17, val_57)
   linear_71 = Add (val_112, "text.transformer.resblocks.17.mlp.c_proj.bias")
   add_2452 = Add (add_2431, linear_71)
   layer_norm_36 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2452, "text.transformer.resblocks.18.ln_1.weight", "text.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_36, val_58)
   [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, "text.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, "text.transformer.resblocks.18.attn.out_proj.bias")
   add_2567 = Add (add_2452, node_scaled_dot_product_attention_18_out)
   layer_norm_37 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2567, "text.transformer.resblocks.18.ln_2.weight", "text.transformer.resblocks.18.ln_2.bias")
   val_113 = MatMul (layer_norm_37, val_59)
   linear_74 = Add (val_113, "text.transformer.resblocks.18.mlp.c_fc.bias")
   gelu_18 = Gelu <approximate: string = "none"> (linear_74)
   val_114 = MatMul (gelu_18, val_60)
   linear_75 = Add (val_114, "text.transformer.resblocks.18.mlp.c_proj.bias")
   add_2588 = Add (add_2567, linear_75)
   layer_norm_38 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2588, "text.transformer.resblocks.19.ln_1.weight", "text.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_38, val_61)
   [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, "text.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, "text.transformer.resblocks.19.attn.out_proj.bias")
   add_2703 = Add (add_2588, node_scaled_dot_product_attention_19_out)
   layer_norm_39 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2703, "text.transformer.resblocks.19.ln_2.weight", "text.transformer.resblocks.19.ln_2.bias")
   val_115 = MatMul (layer_norm_39, val_62)
   linear_78 = Add (val_115, "text.transformer.resblocks.19.mlp.c_fc.bias")
   gelu_19 = Gelu <approximate: string = "none"> (linear_78)
   val_116 = MatMul (gelu_19, val_63)
   linear_79 = Add (val_116, "text.transformer.resblocks.19.mlp.c_proj.bias")
   add_2724 = Add (add_2703, linear_79)
   layer_norm_40 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2724, "text.transformer.resblocks.20.ln_1.weight", "text.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_40, val_64)
   [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, "text.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, "text.transformer.resblocks.20.attn.out_proj.bias")
   add_2839 = Add (add_2724, node_scaled_dot_product_attention_20_out)
   layer_norm_41 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2839, "text.transformer.resblocks.20.ln_2.weight", "text.transformer.resblocks.20.ln_2.bias")
   val_117 = MatMul (layer_norm_41, val_65)
   linear_82 = Add (val_117, "text.transformer.resblocks.20.mlp.c_fc.bias")
   gelu_20 = Gelu <approximate: string = "none"> (linear_82)
   val_118 = MatMul (gelu_20, val_66)
   linear_83 = Add (val_118, "text.transformer.resblocks.20.mlp.c_proj.bias")
   add_2860 = Add (add_2839, linear_83)
   layer_norm_42 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2860, "text.transformer.resblocks.21.ln_1.weight", "text.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_42, val_67)
   [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, "text.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, "text.transformer.resblocks.21.attn.out_proj.bias")
   add_2975 = Add (add_2860, node_scaled_dot_product_attention_21_out)
   layer_norm_43 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2975, "text.transformer.resblocks.21.ln_2.weight", "text.transformer.resblocks.21.ln_2.bias")
   val_119 = MatMul (layer_norm_43, val_68)
   linear_86 = Add (val_119, "text.transformer.resblocks.21.mlp.c_fc.bias")
   gelu_21 = Gelu <approximate: string = "none"> (linear_86)
   val_120 = MatMul (gelu_21, val_69)
   linear_87 = Add (val_120, "text.transformer.resblocks.21.mlp.c_proj.bias")
   add_2996 = Add (add_2975, linear_87)
   layer_norm_44 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_2996, "text.transformer.resblocks.22.ln_1.weight", "text.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_44, val_70)
   [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, "text.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, "text.transformer.resblocks.22.attn.out_proj.bias")
   add_3111 = Add (add_2996, node_scaled_dot_product_attention_22_out)
   layer_norm_45 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_3111, "text.transformer.resblocks.22.ln_2.weight", "text.transformer.resblocks.22.ln_2.bias")
   val_121 = MatMul (layer_norm_45, val_71)
   linear_90 = Add (val_121, "text.transformer.resblocks.22.mlp.c_fc.bias")
   gelu_22 = Gelu <approximate: string = "none"> (linear_90)
   val_122 = MatMul (gelu_22, val_72)
   linear_91 = Add (val_122, "text.transformer.resblocks.22.mlp.c_proj.bias")
   add_3132 = Add (add_3111, linear_91)
   layer_norm_46 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_3132, "text.transformer.resblocks.23.ln_1.weight", "text.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_46, val_73)
   [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, "text.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_0, val_3, val_2)
   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, "text.transformer.resblocks.23.attn.out_proj.bias")
   [pool_hoist_add_3132] add_3132_pooled = Slice (add_3132, val_0, val_3, val_2)
   add_3247 = Add (add_3132_pooled, node_scaled_dot_product_attention_23_out)
   layer_norm_47 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (add_3247, "text.transformer.resblocks.23.ln_2.weight", "text.transformer.resblocks.23.ln_2.bias")
   val_123 = MatMul (layer_norm_47, val_74)
   linear_94 = Add (val_123, "text.transformer.resblocks.23.mlp.c_fc.bias")
   gelu_23 = Gelu <approximate: string = "none"> (linear_94)
   val_124 = MatMul (gelu_23, val_75)
   linear_95 = Add (val_124, "text.transformer.resblocks.23.mlp.c_proj.bias")
   add_3268 = Add (add_3247, linear_95)
   val_125 = Squeeze (add_3268, val_2)
   select_72 = LayerNormalization <axis: int = -1, epsilon: float = 1e-06, stash_type: int = 1> (val_125, "text.ln_final.weight", "text.ln_final.bias")
   linear_96 = Gemm <alpha: float = 1, beta: float = 1, transA: int = 0, transB: int = 1> (select_72, "text.text_projection.weight", "text.text_projection.bias")
   [node_linalg_vector_norm] linalg_vector_norm = ReduceL2 <keepdims: int = 1, noop_with_empty_axes: int = 0> (linear_96, val_0)
   [node_clamp_min] clamp_min = Clip (linalg_vector_norm, val_1)
   [node_div] text_embedding = Div (linear_96, clamp_min)
}

weights:
attn3d_split_3x1024 INT64[3] 0ec6f5651fd5
node_scaled_dot_product_attention_10_wo_t FLOAT[1024,1024] c2df758a91fe
node_scaled_dot_product_attention_11_wo_t FLOAT[1024,1024] 512c0bb006a0
node_scaled_dot_product_attention_12_wo_t FLOAT[1024,1024] 8c99f9832dca
node_scaled_dot_product_attention_13_wo_t FLOAT[1024,1024] 61139e935c0d
node_scaled_dot_product_attention_14_wo_t FLOAT[1024,1024] 1d78db47e3e0
node_scaled_dot_product_attention_15_wo_t FLOAT[1024,1024] 8eb9fe5f76e9
node_scaled_dot_product_attention_16_wo_t FLOAT[1024,1024] 5c6d3b6fa401
node_scaled_dot_product_attention_17_wo_t FLOAT[1024,1024] 1f815f65d2f5
node_scaled_dot_product_attention_18_wo_t FLOAT[1024,1024] e0c5e1286c01
node_scaled_dot_product_attention_19_wo_t FLOAT[1024,1024] b1a080869baf
node_scaled_dot_product_attention_1_wo_t FLOAT[1024,1024] e3539f07aa89
node_scaled_dot_product_attention_20_wo_t FLOAT[1024,1024] a96d43200057
node_scaled_dot_product_attention_21_wo_t FLOAT[1024,1024] f0edc7fb6860
node_scaled_dot_product_attention_22_wo_t FLOAT[1024,1024] 63a285842e5f
node_scaled_dot_product_attention_23_wo_t FLOAT[1024,1024] 38b86b318a92
node_scaled_dot_product_attention_2_wo_t FLOAT[1024,1024] f8cc93790abb
node_scaled_dot_product_attention_3_wo_t FLOAT[1024,1024] a041d1cf9b47
node_scaled_dot_product_attention_4_wo_t FLOAT[1024,1024] a4db56c4daba
node_scaled_dot_product_attention_5_wo_t FLOAT[1024,1024] 633c16baace0
node_scaled_dot_product_attention_6_wo_t FLOAT[1024,1024] 0fa66044feb9
node_scaled_dot_product_attention_7_wo_t FLOAT[1024,1024] 1f7777d0940b
node_scaled_dot_product_attention_8_wo_t FLOAT[1024,1024] 702d52532fbe
node_scaled_dot_product_attention_9_wo_t FLOAT[1024,1024] 9598d5b48302
node_scaled_dot_product_attention_wo_t FLOAT[1024,1024] 44b0fd569b17
text.ln_final.bias FLOAT[1024] b239c3bd8e67
text.ln_final.weight FLOAT[1024] 1b0204a478fe
text.positional_embedding FLOAT[64,1024] b223c8e7f21f
text.text_projection.bias FLOAT[1024] 8ab64118aa2b
text.text_projection.weight FLOAT[1024,1024] 4124350116e8
text.token_embedding.weight_fp16 FLOAT16[32000,1024] e37cc4d1cad6
text.transformer.resblocks.0.attn.in_proj_bias FLOAT[3072] ac92837839fc
text.transformer.resblocks.0.attn.out_proj.bias FLOAT[1024] 80edf89fde32
text.transformer.resblocks.0.ln_1.bias FLOAT[1024] 4f444edc3c79
text.transformer.resblocks.0.ln_1.weight FLOAT[1024] 04a5a5e6a430
text.transformer.resblocks.0.ln_2.bias FLOAT[1024] 0e8a8481e201
text.transformer.resblocks.0.ln_2.weight FLOAT[1024] db2092d14c78
text.transformer.resblocks.0.mlp.c_fc.bias FLOAT[4096] f3f3e586879c
text.transformer.resblocks.0.mlp.c_proj.bias FLOAT[1024] 2627eb707365
text.transformer.resblocks.1.attn.in_proj_bias FLOAT[3072] c7b56257366c
text.transformer.resblocks.1.attn.out_proj.bias FLOAT[1024] c77406a44cbf
text.transformer.resblocks.1.ln_1.bias FLOAT[1024] db541565f319
text.transformer.resblocks.1.ln_1.weight FLOAT[1024] b51f44cf77f1
text.transformer.resblocks.1.ln_2.bias FLOAT[1024] 09fe22ef09e8
text.transformer.resblocks.1.ln_2.weight FLOAT[1024] 19f93c8244d9
text.transformer.resblocks.1.mlp.c_fc.bias FLOAT[4096] db30093b4b60
text.transformer.resblocks.1.mlp.c_proj.bias FLOAT[1024] a11738f5edd9
text.transformer.resblocks.10.attn.in_proj_bias FLOAT[3072] bafdd7e6a643
text.transformer.resblocks.10.attn.out_proj.bias FLOAT[1024] e606b5c2a8bb
text.transformer.resblocks.10.ln_1.bias FLOAT[1024] 0cb86a532222
text.transformer.resblocks.10.ln_1.weight FLOAT[1024] cca4fb8eb582
text.transformer.resblocks.10.ln_2.bias FLOAT[1024] 57da894610e4
text.transformer.resblocks.10.ln_2.weight FLOAT[1024] 149d5e3a52d9
text.transformer.resblocks.10.mlp.c_fc.bias FLOAT[4096] 9fb8d7db33ee
text.transformer.resblocks.10.mlp.c_proj.bias FLOAT[1024] b4831412c96d
text.transformer.resblocks.11.attn.in_proj_bias FLOAT[3072] 66c7f911bc86
text.transformer.resblocks.11.attn.out_proj.bias FLOAT[1024] 1f2fefcf9c09
text.transformer.resblocks.11.ln_1.bias FLOAT[1024] 7f60e560a3f8
text.transformer.resblocks.11.ln_1.weight FLOAT[1024] 9981e477a1da
text.transformer.resblocks.11.ln_2.bias FLOAT[1024] 1045f68b37f5
text.transformer.resblocks.11.ln_2.weight FLOAT[1024] 189e90595188
text.transformer.resblocks.11.mlp.c_fc.bias FLOAT[4096] f97926c95cf3
text.transformer.resblocks.11.mlp.c_proj.bias FLOAT[1024] 1c385fc4a2f7
text.transformer.resblocks.12.attn.in_proj_bias FLOAT[3072] 80c45a261d1d
text.transformer.resblocks.12.attn.out_proj.bias FLOAT[1024] 8f099a84e1f0
text.transformer.resblocks.12.ln_1.bias FLOAT[1024] 773f404dfe1b
text.transformer.resblocks.12.ln_1.weight FLOAT[1024] 2465b4e1b5db
text.transformer.resblocks.12.ln_2.bias FLOAT[1024] a9b929ca6cd0
text.transformer.resblocks.12.ln_2.weight FLOAT[1024] a31c50db06f0
text.transformer.resblocks.12.mlp.c_fc.bias FLOAT[4096] f163d7b3518d
text.transformer.resblocks.12.mlp.c_proj.bias FLOAT[1024] 9981f3c58b99
text.transformer.resblocks.13.attn.in_proj_bias FLOAT[3072] a1ed1a9018cc
text.transformer.resblocks.13.attn.out_proj.bias FLOAT[1024] 6bbdb6464402
text.transformer.resblocks.13.ln_1.bias FLOAT[1024] 6fd3107802dd
text.transformer.resblocks.13.ln_1.weight FLOAT[1024] a39fa8494506
text.transformer.resblocks.13.ln_2.bias FLOAT[1024] af57cb6e5979
text.transformer.resblocks.13.ln_2.weight FLOAT[1024] bfc163d07cd1
text.transformer.resblocks.13.mlp.c_fc.bias FLOAT[4096] bf28b9562e8b
text.transformer.resblocks.13.mlp.c_proj.bias FLOAT[1024] 04be18ace9a7
text.transformer.resblocks.14.attn.in_proj_bias FLOAT[3072] 959b7fc2eb5f
text.transformer.resblocks.14.attn.out_proj.bias FLOAT[1024] 05b0e91b8dc1
text.transformer.resblocks.14.ln_1.bias FLOAT[1024] 4e69a4484280
text.transformer.resblocks.14.ln_1.weight FLOAT[1024] d61348f9a10d
text.transformer.resblocks.14.ln_2.bias FLOAT[1024] 24decf52fba5
text.transformer.resblocks.14.ln_2.weight FLOAT[1024] 6c070cc75067
text.transformer.resblocks.14.mlp.c_fc.bias FLOAT[4096] 064af1fb3f43
text.transformer.resblocks.14.mlp.c_proj.bias FLOAT[1024] 521b97c4ea5b
text.transformer.resblocks.15.attn.in_proj_bias FLOAT[3072] 7f888f70b884
text.transformer.resblocks.15.attn.out_proj.bias FLOAT[1024] 59eb182bf461
text.transformer.resblocks.15.ln_1.bias FLOAT[1024] 65b6a2a0de6c
text.transformer.resblocks.15.ln_1.weight FLOAT[1024] 18f0ce97a495
text.transformer.resblocks.15.ln_2.bias FLOAT[1024] dcd29a03cfdb
text.transformer.resblocks.15.ln_2.weight FLOAT[1024] 0eaa8e8a9fda
text.transformer.resblocks.15.mlp.c_fc.bias FLOAT[4096] 3fba930fca17
text.transformer.resblocks.15.mlp.c_proj.bias FLOAT[1024] 513854d3c420
text.transformer.resblocks.16.attn.in_proj_bias FLOAT[3072] 553d9e86eba8
text.transformer.resblocks.16.attn.out_proj.bias FLOAT[1024] a6e65768d7b3
text.transformer.resblocks.16.ln_1.bias FLOAT[1024] 7bf2e95c4852
text.transformer.resblocks.16.ln_1.weight FLOAT[1024] fa1e25b746f6
text.transformer.resblocks.16.ln_2.bias FLOAT[1024] 17a837f8201c
text.transformer.resblocks.16.ln_2.weight FLOAT[1024] 8b48b50e9d08
text.transformer.resblocks.16.mlp.c_fc.bias FLOAT[4096] 098a3b18d7cf
text.transformer.resblocks.16.mlp.c_proj.bias FLOAT[1024] ca39694e77d9
text.transformer.resblocks.17.attn.in_proj_bias FLOAT[3072] 1a795df844d7
text.transformer.resblocks.17.attn.out_proj.bias FLOAT[1024] f000ff034b73
text.transformer.resblocks.17.ln_1.bias FLOAT[1024] ede56dc224c7
text.transformer.resblocks.17.ln_1.weight FLOAT[1024] 89173abd4a80
text.transformer.resblocks.17.ln_2.bias FLOAT[1024] b32a123851c4
text.transformer.resblocks.17.ln_2.weight FLOAT[1024] e54d1712cb78
text.transformer.resblocks.17.mlp.c_fc.bias FLOAT[4096] b62996d90a99
text.transformer.resblocks.17.mlp.c_proj.bias FLOAT[1024] 2d23d4a4e375
text.transformer.resblocks.18.attn.in_proj_bias FLOAT[3072] 129c8c0d18a4
text.transformer.resblocks.18.attn.out_proj.bias FLOAT[1024] 536ba05d263d
text.transformer.resblocks.18.ln_1.bias FLOAT[1024] a98b201504ab
text.transformer.resblocks.18.ln_1.weight FLOAT[1024] 01538409b765
text.transformer.resblocks.18.ln_2.bias FLOAT[1024] 033cc8bc037a
text.transformer.resblocks.18.ln_2.weight FLOAT[1024] f884f11fc53e
text.transformer.resblocks.18.mlp.c_fc.bias FLOAT[4096] 66efe5815e6d
text.transformer.resblocks.18.mlp.c_proj.bias FLOAT[1024] dc7bbe8d41be
text.transformer.resblocks.19.attn.in_proj_bias FLOAT[3072] 7e79652a602c
text.transformer.resblocks.19.attn.out_proj.bias FLOAT[1024] f802fe41db6e
text.transformer.resblocks.19.ln_1.bias FLOAT[1024] 66e948929d9b
text.transformer.resblocks.19.ln_1.weight FLOAT[1024] a8cfb6213cf9
text.transformer.resblocks.19.ln_2.bias FLOAT[1024] f828a29f0531
text.transformer.resblocks.19.ln_2.weight FLOAT[1024] e251de102650
text.transformer.resblocks.19.mlp.c_fc.bias FLOAT[4096] 2ddcebc6a086
text.transformer.resblocks.19.mlp.c_proj.bias FLOAT[1024] 1b58c44bcd97
text.transformer.resblocks.2.attn.in_proj_bias FLOAT[3072] f19a2cc80015
text.transformer.resblocks.2.attn.out_proj.bias FLOAT[1024] 6d1cd1223882
text.transformer.resblocks.2.ln_1.bias FLOAT[1024] 23ebf8b94748
text.transformer.resblocks.2.ln_1.weight FLOAT[1024] a63067817b17
text.transformer.resblocks.2.ln_2.bias FLOAT[1024] 279a6b813d6b
text.transformer.resblocks.2.ln_2.weight FLOAT[1024] 71a25c51940f
text.transformer.resblocks.2.mlp.c_fc.bias FLOAT[4096] f9fcc730d407
text.transformer.resblocks.2.mlp.c_proj.bias FLOAT[1024] af0c921fafe6
text.transformer.resblocks.20.attn.in_proj_bias FLOAT[3072] a8ce91b13774
text.transformer.resblocks.20.attn.out_proj.bias FLOAT[1024] 49a5b4e1cd33
text.transformer.resblocks.20.ln_1.bias FLOAT[1024] 2064c618570e
text.transformer.resblocks.20.ln_1.weight FLOAT[1024] da5b9b894430
text.transformer.resblocks.20.ln_2.bias FLOAT[1024] 3664b5236937
text.transformer.resblocks.20.ln_2.weight FLOAT[1024] a61f97125c64
text.transformer.resblocks.20.mlp.c_fc.bias FLOAT[4096] 1d239a418e93
text.transformer.resblocks.20.mlp.c_proj.bias FLOAT[1024] 546976d16f46
text.transformer.resblocks.21.attn.in_proj_bias FLOAT[3072] bcd1ed4e83dc
text.transformer.resblocks.21.attn.out_proj.bias FLOAT[1024] bf533f3c933e
text.transformer.resblocks.21.ln_1.bias FLOAT[1024] 24f6548b8507
text.transformer.resblocks.21.ln_1.weight FLOAT[1024] 5b2f63cece48
text.transformer.resblocks.21.ln_2.bias FLOAT[1024] 6425ee45e9f9
text.transformer.resblocks.21.ln_2.weight FLOAT[1024] 6452dd90176f
text.transformer.resblocks.21.mlp.c_fc.bias FLOAT[4096] f5bbe58625b4
text.transformer.resblocks.21.mlp.c_proj.bias FLOAT[1024] 6e694cc6109e
text.transformer.resblocks.22.attn.in_proj_bias FLOAT[3072] e6472d3d316e
text.transformer.resblocks.22.attn.out_proj.bias FLOAT[1024] 0feedd27ed53
text.transformer.resblocks.22.ln_1.bias FLOAT[1024] 518d030816fa
text.transformer.resblocks.22.ln_1.weight FLOAT[1024] 9c7b37412271
text.transformer.resblocks.22.ln_2.bias FLOAT[1024] fafdf0df0f63
text.transformer.resblocks.22.ln_2.weight FLOAT[1024] 6d1dc99ebec3
text.transformer.resblocks.22.mlp.c_fc.bias FLOAT[4096] b2815e059003
text.transformer.resblocks.22.mlp.c_proj.bias FLOAT[1024] 0d483b1b6163
text.transformer.resblocks.23.attn.in_proj_bias FLOAT[3072] 6abd8ac0a391
text.transformer.resblocks.23.attn.out_proj.bias FLOAT[1024] 7da925df5415
text.transformer.resblocks.23.ln_1.bias FLOAT[1024] 7debc412098c
text.transformer.resblocks.23.ln_1.weight FLOAT[1024] 8bcae7f22369
text.transformer.resblocks.23.ln_2.bias FLOAT[1024] 3044e06be8db
text.transformer.resblocks.23.ln_2.weight FLOAT[1024] 3cfd54bd2633
text.transformer.resblocks.23.mlp.c_fc.bias FLOAT[4096] 66415874e9f7
text.transformer.resblocks.23.mlp.c_proj.bias FLOAT[1024] 81bf7b93e91a
text.transformer.resblocks.3.attn.in_proj_bias FLOAT[3072] d1d2220c47b7
text.transformer.resblocks.3.attn.out_proj.bias FLOAT[1024] 8e90c8ac1704
text.transformer.resblocks.3.ln_1.bias FLOAT[1024] 745c7dba90da
text.transformer.resblocks.3.ln_1.weight FLOAT[1024] 34e7b8e90288
text.transformer.resblocks.3.ln_2.bias FLOAT[1024] d74d60346e22
text.transformer.resblocks.3.ln_2.weight FLOAT[1024] 91efb8792206
text.transformer.resblocks.3.mlp.c_fc.bias FLOAT[4096] d7820d9b1806
text.transformer.resblocks.3.mlp.c_proj.bias FLOAT[1024] 49fb66f3df5a
text.transformer.resblocks.4.attn.in_proj_bias FLOAT[3072] e4a7c1fba9bf
text.transformer.resblocks.4.attn.out_proj.bias FLOAT[1024] 2f21b204a991
text.transformer.resblocks.4.ln_1.bias FLOAT[1024] 373e5b8c2e7f
text.transformer.resblocks.4.ln_1.weight FLOAT[1024] 8ebf2fb327fe
text.transformer.resblocks.4.ln_2.bias FLOAT[1024] 2bf44b241a6c
text.transformer.resblocks.4.ln_2.weight FLOAT[1024] eeedeef84060
text.transformer.resblocks.4.mlp.c_fc.bias FLOAT[4096] 2e5cf5f9a381
text.transformer.resblocks.4.mlp.c_proj.bias FLOAT[1024] 20039ceda75c
text.transformer.resblocks.5.attn.in_proj_bias FLOAT[3072] 3ce984b19a15
text.transformer.resblocks.5.attn.out_proj.bias FLOAT[1024] a66ef6a8bcb8
text.transformer.resblocks.5.ln_1.bias FLOAT[1024] d0d151ab4d2e
text.transformer.resblocks.5.ln_1.weight FLOAT[1024] 120df7ad10f8
text.transformer.resblocks.5.ln_2.bias FLOAT[1024] 82af14efeba9
text.transformer.resblocks.5.ln_2.weight FLOAT[1024] 8d5bf2949641
text.transformer.resblocks.5.mlp.c_fc.bias FLOAT[4096] cc64114c9821
text.transformer.resblocks.5.mlp.c_proj.bias FLOAT[1024] 47e5f39498d0
text.transformer.resblocks.6.attn.in_proj_bias FLOAT[3072] b8ab669dbe10
text.transformer.resblocks.6.attn.out_proj.bias FLOAT[1024] b815ff54d822
text.transformer.resblocks.6.ln_1.bias FLOAT[1024] c961c0253496
text.transformer.resblocks.6.ln_1.weight FLOAT[1024] 6dee98a91060
text.transformer.resblocks.6.ln_2.bias FLOAT[1024] ce6ad2c98354
text.transformer.resblocks.6.ln_2.weight FLOAT[1024] 54e270e41e88
text.transformer.resblocks.6.mlp.c_fc.bias FLOAT[4096] cab78406ea50
text.transformer.resblocks.6.mlp.c_proj.bias FLOAT[1024] 9b2f454823b0
text.transformer.resblocks.7.attn.in_proj_bias FLOAT[3072] febc715b0e51
text.transformer.resblocks.7.attn.out_proj.bias FLOAT[1024] 46e7fd99d906
text.transformer.resblocks.7.ln_1.bias FLOAT[1024] 0c03a8f286a3
text.transformer.resblocks.7.ln_1.weight FLOAT[1024] 3e08e66136e4
text.transformer.resblocks.7.ln_2.bias FLOAT[1024] a6dba9be1441
text.transformer.resblocks.7.ln_2.weight FLOAT[1024] a507d60b6035
text.transformer.resblocks.7.mlp.c_fc.bias FLOAT[4096] d8418b8ed306
text.transformer.resblocks.7.mlp.c_proj.bias FLOAT[1024] f971cf92deb0
text.transformer.resblocks.8.attn.in_proj_bias FLOAT[3072] 76e6431f69c0
text.transformer.resblocks.8.attn.out_proj.bias FLOAT[1024] b1d7b8eb7cdc
text.transformer.resblocks.8.ln_1.bias FLOAT[1024] ffb99fddd5ed
text.transformer.resblocks.8.ln_1.weight FLOAT[1024] ede994904576
text.transformer.resblocks.8.ln_2.bias FLOAT[1024] 839efe85c61a
text.transformer.resblocks.8.ln_2.weight FLOAT[1024] 0f9d9f7ab7f0
text.transformer.resblocks.8.mlp.c_fc.bias FLOAT[4096] bc11d0971325
text.transformer.resblocks.8.mlp.c_proj.bias FLOAT[1024] a81c274c8fcc
text.transformer.resblocks.9.attn.in_proj_bias FLOAT[3072] 569a67e7c034
text.transformer.resblocks.9.attn.out_proj.bias FLOAT[1024] 7cbca2a4fae5
text.transformer.resblocks.9.ln_1.bias FLOAT[1024] ab0320433bd1
text.transformer.resblocks.9.ln_1.weight FLOAT[1024] 5d9a38ed1b49
text.transformer.resblocks.9.ln_2.bias FLOAT[1024] 73045a21b50a
text.transformer.resblocks.9.ln_2.weight FLOAT[1024] 540ab7ae59e9
text.transformer.resblocks.9.mlp.c_fc.bias FLOAT[4096] 520a9d66da8b
text.transformer.resblocks.9.mlp.c_proj.bias FLOAT[1024] ddfb677bec15
val_0 INT64[1] 12a3ae445661
val_1 FLOAT[] 6708d9be4956
val_10 FLOAT[1024,3072] 6fe86b0b7f40
val_11 FLOAT[1024,4096] 8ed45a86ca0b
val_12 FLOAT[4096,1024] a56c2d642f16
val_13 FLOAT[1024,3072] 07b5fc65378f
val_14 FLOAT[1024,4096] 490d43d72573
val_15 FLOAT[4096,1024] 510f833cd59c
val_16 FLOAT[1024,3072] 9fcb4090360b
val_17 FLOAT[1024,4096] 8b366b37add5
val_18 FLOAT[4096,1024] 960de5d40717
val_19 FLOAT[1024,3072] e5a6556727df
val_2 INT64[1] 7c9fa136d441
val_20 FLOAT[1024,4096] 06591869045a
val_21 FLOAT[4096,1024] 0adae4669c86
val_22 FLOAT[1024,3072] d314b903bc98
val_23 FLOAT[1024,4096] cfe10294bdd0
val_24 FLOAT[4096,1024] 259f30e61261
val_25 FLOAT[1024,3072] ed2d23bd82af
val_26 FLOAT[1024,4096] e3e2056f6659
val_27 FLOAT[4096,1024] 0377c0341ed1
val_28 FLOAT[1024,3072] c8ba45e7caff
val_29 FLOAT[1024,4096] 7bf83e350553
val_3 INT64[1] 6a69a6cc7473
val_30 FLOAT[4096,1024] 69c77e7a590d
val_31 FLOAT[1024,3072] 0f0a30e0dcb6
val_32 FLOAT[1024,4096] 2432c5e4cf2a
val_33 FLOAT[4096,1024] 9960a792df2c
val_34 FLOAT[1024,3072] 590b3d06428e
val_35 FLOAT[1024,4096] bc8ab3d1c746
val_36 FLOAT[4096,1024] a22646ca07bd
val_37 FLOAT[1024,3072] 419afc4b9907
val_38 FLOAT[1024,4096] 9a2dfce3869f
val_39 FLOAT[4096,1024] 7e43b804aedb
val_4 FLOAT[1024,3072] 07630c43d3a8
val_40 FLOAT[1024,3072] 5c3b2e2a8931
val_41 FLOAT[1024,4096] bba7546cdaa6
val_42 FLOAT[4096,1024] 7eb9d6343c9d
val_43 FLOAT[1024,3072] a8587e2075f2
val_44 FLOAT[1024,4096] 03f850de0b84
val_45 FLOAT[4096,1024] fadf8892def5
val_46 FLOAT[1024,3072] 300c6e70c116
val_47 FLOAT[1024,4096] d33999321107
val_48 FLOAT[4096,1024] 4e4f34c01f58
val_49 FLOAT[1024,3072] d483bb65da8e
val_5 FLOAT[1024,4096] 5ca2b2d7e5a8
val_50 FLOAT[1024,4096] b20d3901ff40
val_51 FLOAT[4096,1024] e58cf387c962
val_52 FLOAT[1024,3072] 748f335e58bf
val_53 FLOAT[1024,4096] 1212c3e8bcf8
val_54 FLOAT[4096,1024] 890010c1b387
val_55 FLOAT[1024,3072] 8ed2b35fc55a
val_56 FLOAT[1024,4096] dfb94697ca46
val_57 FLOAT[4096,1024] c8c54def1977
val_58 FLOAT[1024,3072] 9cb203a4a874
val_59 FLOAT[1024,4096] a731a43cdc94
val_6 FLOAT[4096,1024] 5146d68b3820
val_60 FLOAT[4096,1024] 34b443694bbb
val_61 FLOAT[1024,3072] 46c2a84599a1
val_62 FLOAT[1024,4096] 29a8f4a4ea4e
val_63 FLOAT[4096,1024] ffc6cd23e291
val_64 FLOAT[1024,3072] 953f64a52fca
val_65 FLOAT[1024,4096] 3c01b1f6484d
val_66 FLOAT[4096,1024] 738e99cd4a88
val_67 FLOAT[1024,3072] ae5688375ffa
val_68 FLOAT[1024,4096] 95645df699d4
val_69 FLOAT[4096,1024] 526ada94ccd2
val_7 FLOAT[1024,3072] c7b1ec2894cc
val_70 FLOAT[1024,3072] d35559f1c20e
val_71 FLOAT[1024,4096] 0034c6dd5e09
val_72 FLOAT[4096,1024] 6ca4f6437720
val_73 FLOAT[1024,3072] 2e098561edd6
val_74 FLOAT[1024,4096] d039fb56e802
val_75 FLOAT[4096,1024] 9799ee327db8
val_8 FLOAT[1024,4096] 641cacdba95e
val_9 FLOAT[4096,1024] 771ef133ff88
