<
   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] d49f600edafd
node_scaled_dot_product_attention_11_wo_t FLOAT[1024,1024] ee4ddad61956
node_scaled_dot_product_attention_12_wo_t FLOAT[1024,1024] 082c256cc5f0
node_scaled_dot_product_attention_13_wo_t FLOAT[1024,1024] 37eae04d89c0
node_scaled_dot_product_attention_14_wo_t FLOAT[1024,1024] 5a9ab9ec0de9
node_scaled_dot_product_attention_15_wo_t FLOAT[1024,1024] 145b983500d1
node_scaled_dot_product_attention_16_wo_t FLOAT[1024,1024] faab46783c70
node_scaled_dot_product_attention_17_wo_t FLOAT[1024,1024] e5f6f7daf2e9
node_scaled_dot_product_attention_18_wo_t FLOAT[1024,1024] 0355efa20ee1
node_scaled_dot_product_attention_19_wo_t FLOAT[1024,1024] 410258fc639a
node_scaled_dot_product_attention_1_wo_t FLOAT[1024,1024] 62edc6abae3f
node_scaled_dot_product_attention_20_wo_t FLOAT[1024,1024] 63c1cc2501ed
node_scaled_dot_product_attention_21_wo_t FLOAT[1024,1024] 6e18a32aa68a
node_scaled_dot_product_attention_22_wo_t FLOAT[1024,1024] af8ea5d0c9a7
node_scaled_dot_product_attention_23_wo_t FLOAT[1024,1024] 85f53c18e6d3
node_scaled_dot_product_attention_2_wo_t FLOAT[1024,1024] d8a9e7d544d0
node_scaled_dot_product_attention_3_wo_t FLOAT[1024,1024] fe358230100a
node_scaled_dot_product_attention_4_wo_t FLOAT[1024,1024] 2fbf6532535f
node_scaled_dot_product_attention_5_wo_t FLOAT[1024,1024] 946ddf0841ed
node_scaled_dot_product_attention_6_wo_t FLOAT[1024,1024] 504c1b4287ad
node_scaled_dot_product_attention_7_wo_t FLOAT[1024,1024] 58da44f1bac2
node_scaled_dot_product_attention_8_wo_t FLOAT[1024,1024] efc313fbb91d
node_scaled_dot_product_attention_9_wo_t FLOAT[1024,1024] f0e0708d9a0e
node_scaled_dot_product_attention_wo_t FLOAT[1024,1024] ab7a475ae1a3
text.ln_final.bias FLOAT[1024] 87e708b8b211
text.ln_final.weight FLOAT[1024] c157b39dbc38
text.positional_embedding FLOAT[64,1024] 0f2dbc09ed0d
text.text_projection.bias FLOAT[1024] b9e5c3b6ec22
text.text_projection.weight FLOAT[1024,1024] e3ceb35f863b
text.token_embedding.weight_fp16 FLOAT16[32000,1024] 2af418e12a46
text.transformer.resblocks.0.attn.in_proj_bias FLOAT[3072] 178cf8dd4fca
text.transformer.resblocks.0.attn.out_proj.bias FLOAT[1024] 508ffd188a96
text.transformer.resblocks.0.ln_1.bias FLOAT[1024] c3870fe24b67
text.transformer.resblocks.0.ln_1.weight FLOAT[1024] 260ce5ee914a
text.transformer.resblocks.0.ln_2.bias FLOAT[1024] 9b683b9c0a83
text.transformer.resblocks.0.ln_2.weight FLOAT[1024] a93ed718ad65
text.transformer.resblocks.0.mlp.c_fc.bias FLOAT[4096] ef128fbf847d
text.transformer.resblocks.0.mlp.c_proj.bias FLOAT[1024] 0069745b4ee0
text.transformer.resblocks.1.attn.in_proj_bias FLOAT[3072] 9bb29433c633
text.transformer.resblocks.1.attn.out_proj.bias FLOAT[1024] 5a42370f9c34
text.transformer.resblocks.1.ln_1.bias FLOAT[1024] ede23f7a9080
text.transformer.resblocks.1.ln_1.weight FLOAT[1024] d9fee77421ad
text.transformer.resblocks.1.ln_2.bias FLOAT[1024] 146e6b61cf9e
text.transformer.resblocks.1.ln_2.weight FLOAT[1024] 2d810931e5d1
text.transformer.resblocks.1.mlp.c_fc.bias FLOAT[4096] 96ed50009783
text.transformer.resblocks.1.mlp.c_proj.bias FLOAT[1024] 5ad2b3e1ed1d
text.transformer.resblocks.10.attn.in_proj_bias FLOAT[3072] 40135c5cbb4e
text.transformer.resblocks.10.attn.out_proj.bias FLOAT[1024] 8a59971dcb41
text.transformer.resblocks.10.ln_1.bias FLOAT[1024] b2631c3c81e6
text.transformer.resblocks.10.ln_1.weight FLOAT[1024] a8c5b5665acb
text.transformer.resblocks.10.ln_2.bias FLOAT[1024] 5d9e1c89d56e
text.transformer.resblocks.10.ln_2.weight FLOAT[1024] d1e7482171c8
text.transformer.resblocks.10.mlp.c_fc.bias FLOAT[4096] 9f3fbf54859c
text.transformer.resblocks.10.mlp.c_proj.bias FLOAT[1024] e262bf7df3fa
text.transformer.resblocks.11.attn.in_proj_bias FLOAT[3072] c4dd122859d9
text.transformer.resblocks.11.attn.out_proj.bias FLOAT[1024] 1f51b4355bb7
text.transformer.resblocks.11.ln_1.bias FLOAT[1024] dd6e90ca941b
text.transformer.resblocks.11.ln_1.weight FLOAT[1024] d8ffb17c5999
text.transformer.resblocks.11.ln_2.bias FLOAT[1024] 387462400cca
text.transformer.resblocks.11.ln_2.weight FLOAT[1024] 4ad7de1f488e
text.transformer.resblocks.11.mlp.c_fc.bias FLOAT[4096] 88e1274f5c4b
text.transformer.resblocks.11.mlp.c_proj.bias FLOAT[1024] 20e7ec9d19e2
text.transformer.resblocks.12.attn.in_proj_bias FLOAT[3072] f3204ae9e9ae
text.transformer.resblocks.12.attn.out_proj.bias FLOAT[1024] 02bfa6955852
text.transformer.resblocks.12.ln_1.bias FLOAT[1024] a755d504cca3
text.transformer.resblocks.12.ln_1.weight FLOAT[1024] 7e0abb3cf9fa
text.transformer.resblocks.12.ln_2.bias FLOAT[1024] c433dc86852a
text.transformer.resblocks.12.ln_2.weight FLOAT[1024] a2580e7c63f3
text.transformer.resblocks.12.mlp.c_fc.bias FLOAT[4096] 88b9defc2748
text.transformer.resblocks.12.mlp.c_proj.bias FLOAT[1024] 115f1cb3f31c
text.transformer.resblocks.13.attn.in_proj_bias FLOAT[3072] 8a25380b5f54
text.transformer.resblocks.13.attn.out_proj.bias FLOAT[1024] d88139a8bef2
text.transformer.resblocks.13.ln_1.bias FLOAT[1024] 79be4150a0f4
text.transformer.resblocks.13.ln_1.weight FLOAT[1024] be394b56c6e4
text.transformer.resblocks.13.ln_2.bias FLOAT[1024] da3b995dc1f6
text.transformer.resblocks.13.ln_2.weight FLOAT[1024] bd7784db9a6a
text.transformer.resblocks.13.mlp.c_fc.bias FLOAT[4096] 2dad3b0af3d1
text.transformer.resblocks.13.mlp.c_proj.bias FLOAT[1024] 93d8ca504d53
text.transformer.resblocks.14.attn.in_proj_bias FLOAT[3072] ef1c5d9dba56
text.transformer.resblocks.14.attn.out_proj.bias FLOAT[1024] a6b02d81cb33
text.transformer.resblocks.14.ln_1.bias FLOAT[1024] dc49f74e5fbe
text.transformer.resblocks.14.ln_1.weight FLOAT[1024] 41a72f626c26
text.transformer.resblocks.14.ln_2.bias FLOAT[1024] f196bf95a1c0
text.transformer.resblocks.14.ln_2.weight FLOAT[1024] c491ac3a4045
text.transformer.resblocks.14.mlp.c_fc.bias FLOAT[4096] b783d91858ee
text.transformer.resblocks.14.mlp.c_proj.bias FLOAT[1024] 977270e2309a
text.transformer.resblocks.15.attn.in_proj_bias FLOAT[3072] 2d9f01951f3a
text.transformer.resblocks.15.attn.out_proj.bias FLOAT[1024] 3443cd36c51a
text.transformer.resblocks.15.ln_1.bias FLOAT[1024] cec09211c4de
text.transformer.resblocks.15.ln_1.weight FLOAT[1024] 2ec45f308114
text.transformer.resblocks.15.ln_2.bias FLOAT[1024] fe6bcb8e7d76
text.transformer.resblocks.15.ln_2.weight FLOAT[1024] 38f040c3a4ff
text.transformer.resblocks.15.mlp.c_fc.bias FLOAT[4096] 1f1bc4328e32
text.transformer.resblocks.15.mlp.c_proj.bias FLOAT[1024] 1af61e2d94c7
text.transformer.resblocks.16.attn.in_proj_bias FLOAT[3072] b9913469514d
text.transformer.resblocks.16.attn.out_proj.bias FLOAT[1024] c18d3d919579
text.transformer.resblocks.16.ln_1.bias FLOAT[1024] aba30598caad
text.transformer.resblocks.16.ln_1.weight FLOAT[1024] 57ef8fededdb
text.transformer.resblocks.16.ln_2.bias FLOAT[1024] 69e3c7828b5f
text.transformer.resblocks.16.ln_2.weight FLOAT[1024] 843ebb1dc4f6
text.transformer.resblocks.16.mlp.c_fc.bias FLOAT[4096] ee4f37906304
text.transformer.resblocks.16.mlp.c_proj.bias FLOAT[1024] bd49e8ffa66e
text.transformer.resblocks.17.attn.in_proj_bias FLOAT[3072] f418f0f89bcd
text.transformer.resblocks.17.attn.out_proj.bias FLOAT[1024] 76563d8ba804
text.transformer.resblocks.17.ln_1.bias FLOAT[1024] cf60f8d6649b
text.transformer.resblocks.17.ln_1.weight FLOAT[1024] ebdc29f2b12a
text.transformer.resblocks.17.ln_2.bias FLOAT[1024] 3a5469bcafe6
text.transformer.resblocks.17.ln_2.weight FLOAT[1024] 205dc38e6754
text.transformer.resblocks.17.mlp.c_fc.bias FLOAT[4096] 3b744bd5fad4
text.transformer.resblocks.17.mlp.c_proj.bias FLOAT[1024] b7b107204420
text.transformer.resblocks.18.attn.in_proj_bias FLOAT[3072] f1e6933ec23c
text.transformer.resblocks.18.attn.out_proj.bias FLOAT[1024] d3e06577a404
text.transformer.resblocks.18.ln_1.bias FLOAT[1024] b7814c9d585a
text.transformer.resblocks.18.ln_1.weight FLOAT[1024] 7e8fd9d6e270
text.transformer.resblocks.18.ln_2.bias FLOAT[1024] fd5a961c04a2
text.transformer.resblocks.18.ln_2.weight FLOAT[1024] 6b2134fe3fa4
text.transformer.resblocks.18.mlp.c_fc.bias FLOAT[4096] 1e33bf66cbd8
text.transformer.resblocks.18.mlp.c_proj.bias FLOAT[1024] e6558c5485f2
text.transformer.resblocks.19.attn.in_proj_bias FLOAT[3072] ee84409a67ea
text.transformer.resblocks.19.attn.out_proj.bias FLOAT[1024] bb290ae72110
text.transformer.resblocks.19.ln_1.bias FLOAT[1024] 88d293148e56
text.transformer.resblocks.19.ln_1.weight FLOAT[1024] cae9bf844a97
text.transformer.resblocks.19.ln_2.bias FLOAT[1024] e24e128a4e19
text.transformer.resblocks.19.ln_2.weight FLOAT[1024] 70551fd7856b
text.transformer.resblocks.19.mlp.c_fc.bias FLOAT[4096] 4a92d850ea45
text.transformer.resblocks.19.mlp.c_proj.bias FLOAT[1024] f75f92a4e0b3
text.transformer.resblocks.2.attn.in_proj_bias FLOAT[3072] 9aec0f5b77bc
text.transformer.resblocks.2.attn.out_proj.bias FLOAT[1024] f99e41a773da
text.transformer.resblocks.2.ln_1.bias FLOAT[1024] 97a587ae4705
text.transformer.resblocks.2.ln_1.weight FLOAT[1024] c666258d22a5
text.transformer.resblocks.2.ln_2.bias FLOAT[1024] ccea9f2fe914
text.transformer.resblocks.2.ln_2.weight FLOAT[1024] ca8bc783a0e2
text.transformer.resblocks.2.mlp.c_fc.bias FLOAT[4096] 668095017b93
text.transformer.resblocks.2.mlp.c_proj.bias FLOAT[1024] 6d4441f11a52
text.transformer.resblocks.20.attn.in_proj_bias FLOAT[3072] 1bab114ead6a
text.transformer.resblocks.20.attn.out_proj.bias FLOAT[1024] f4c13f612f9f
text.transformer.resblocks.20.ln_1.bias FLOAT[1024] 2b7df9638059
text.transformer.resblocks.20.ln_1.weight FLOAT[1024] 80e8d851a7d1
text.transformer.resblocks.20.ln_2.bias FLOAT[1024] e62dbe1240c0
text.transformer.resblocks.20.ln_2.weight FLOAT[1024] 1519afc39ad8
text.transformer.resblocks.20.mlp.c_fc.bias FLOAT[4096] 97bb3973ad48
text.transformer.resblocks.20.mlp.c_proj.bias FLOAT[1024] e90e5d216a34
text.transformer.resblocks.21.attn.in_proj_bias FLOAT[3072] 5f1343434bd0
text.transformer.resblocks.21.attn.out_proj.bias FLOAT[1024] 25db1b368683
text.transformer.resblocks.21.ln_1.bias FLOAT[1024] 366f48db9663
text.transformer.resblocks.21.ln_1.weight FLOAT[1024] a5332e0c9699
text.transformer.resblocks.21.ln_2.bias FLOAT[1024] ca72976629ee
text.transformer.resblocks.21.ln_2.weight FLOAT[1024] 2c0c7b0e2d5d
text.transformer.resblocks.21.mlp.c_fc.bias FLOAT[4096] 1c288d1bdcbd
text.transformer.resblocks.21.mlp.c_proj.bias FLOAT[1024] 5046f401d4c4
text.transformer.resblocks.22.attn.in_proj_bias FLOAT[3072] 5b81b4967da8
text.transformer.resblocks.22.attn.out_proj.bias FLOAT[1024] 1bf5ba0c074f
text.transformer.resblocks.22.ln_1.bias FLOAT[1024] 222d342e7384
text.transformer.resblocks.22.ln_1.weight FLOAT[1024] 60ce59e472cb
text.transformer.resblocks.22.ln_2.bias FLOAT[1024] 8722d4ecaafd
text.transformer.resblocks.22.ln_2.weight FLOAT[1024] dcadaf9e1eb4
text.transformer.resblocks.22.mlp.c_fc.bias FLOAT[4096] f4ef69c95f90
text.transformer.resblocks.22.mlp.c_proj.bias FLOAT[1024] 5ead3367d4c8
text.transformer.resblocks.23.attn.in_proj_bias FLOAT[3072] d1d726f292ab
text.transformer.resblocks.23.attn.out_proj.bias FLOAT[1024] 82c4b9cf2494
text.transformer.resblocks.23.ln_1.bias FLOAT[1024] 34879dc4a97c
text.transformer.resblocks.23.ln_1.weight FLOAT[1024] 7fe016200db2
text.transformer.resblocks.23.ln_2.bias FLOAT[1024] a7eb30d5e45b
text.transformer.resblocks.23.ln_2.weight FLOAT[1024] 42ff549be628
text.transformer.resblocks.23.mlp.c_fc.bias FLOAT[4096] 9e799f98aa22
text.transformer.resblocks.23.mlp.c_proj.bias FLOAT[1024] ed5555ba48da
text.transformer.resblocks.3.attn.in_proj_bias FLOAT[3072] ae80634940d4
text.transformer.resblocks.3.attn.out_proj.bias FLOAT[1024] a6a6a5d99eed
text.transformer.resblocks.3.ln_1.bias FLOAT[1024] 2403aa35ba65
text.transformer.resblocks.3.ln_1.weight FLOAT[1024] ab2464befb70
text.transformer.resblocks.3.ln_2.bias FLOAT[1024] 8abef8ba5c57
text.transformer.resblocks.3.ln_2.weight FLOAT[1024] 52d8d07b0230
text.transformer.resblocks.3.mlp.c_fc.bias FLOAT[4096] 65200c834aa8
text.transformer.resblocks.3.mlp.c_proj.bias FLOAT[1024] b70e8e3304c8
text.transformer.resblocks.4.attn.in_proj_bias FLOAT[3072] ea9c9143906c
text.transformer.resblocks.4.attn.out_proj.bias FLOAT[1024] a6b970de25d2
text.transformer.resblocks.4.ln_1.bias FLOAT[1024] 4d7fb3c90857
text.transformer.resblocks.4.ln_1.weight FLOAT[1024] 6d073605f044
text.transformer.resblocks.4.ln_2.bias FLOAT[1024] 7971ac47c9fa
text.transformer.resblocks.4.ln_2.weight FLOAT[1024] 105ee6c14d46
text.transformer.resblocks.4.mlp.c_fc.bias FLOAT[4096] 01533a4591ac
text.transformer.resblocks.4.mlp.c_proj.bias FLOAT[1024] f8c670aec358
text.transformer.resblocks.5.attn.in_proj_bias FLOAT[3072] 9e51eb5c87e9
text.transformer.resblocks.5.attn.out_proj.bias FLOAT[1024] 3704a3f5c4a4
text.transformer.resblocks.5.ln_1.bias FLOAT[1024] d69a3234352d
text.transformer.resblocks.5.ln_1.weight FLOAT[1024] a664e7b2a840
text.transformer.resblocks.5.ln_2.bias FLOAT[1024] df9531ea8af6
text.transformer.resblocks.5.ln_2.weight FLOAT[1024] 0a60fc5aea31
text.transformer.resblocks.5.mlp.c_fc.bias FLOAT[4096] 4bf63561b2a9
text.transformer.resblocks.5.mlp.c_proj.bias FLOAT[1024] a073a65a03e9
text.transformer.resblocks.6.attn.in_proj_bias FLOAT[3072] 1b82d08b89d1
text.transformer.resblocks.6.attn.out_proj.bias FLOAT[1024] 2e1a3065345c
text.transformer.resblocks.6.ln_1.bias FLOAT[1024] 9152fdb7cee7
text.transformer.resblocks.6.ln_1.weight FLOAT[1024] 96109c841a42
text.transformer.resblocks.6.ln_2.bias FLOAT[1024] 2b2601a670b8
text.transformer.resblocks.6.ln_2.weight FLOAT[1024] f92db9e28c0a
text.transformer.resblocks.6.mlp.c_fc.bias FLOAT[4096] 4357a0899657
text.transformer.resblocks.6.mlp.c_proj.bias FLOAT[1024] 5978955d4001
text.transformer.resblocks.7.attn.in_proj_bias FLOAT[3072] 9cf1c5441873
text.transformer.resblocks.7.attn.out_proj.bias FLOAT[1024] 417eee7fc055
text.transformer.resblocks.7.ln_1.bias FLOAT[1024] 34e49f8a2ccb
text.transformer.resblocks.7.ln_1.weight FLOAT[1024] b79acb4b141e
text.transformer.resblocks.7.ln_2.bias FLOAT[1024] df0be8539e84
text.transformer.resblocks.7.ln_2.weight FLOAT[1024] 62ede5ab5173
text.transformer.resblocks.7.mlp.c_fc.bias FLOAT[4096] 3575703d9fcc
text.transformer.resblocks.7.mlp.c_proj.bias FLOAT[1024] d8beae816621
text.transformer.resblocks.8.attn.in_proj_bias FLOAT[3072] b68b7081a7e2
text.transformer.resblocks.8.attn.out_proj.bias FLOAT[1024] 0471542600f9
text.transformer.resblocks.8.ln_1.bias FLOAT[1024] 5028a81699c6
text.transformer.resblocks.8.ln_1.weight FLOAT[1024] 2e121ef46ede
text.transformer.resblocks.8.ln_2.bias FLOAT[1024] af1b50c79ee9
text.transformer.resblocks.8.ln_2.weight FLOAT[1024] 6aa142515aa4
text.transformer.resblocks.8.mlp.c_fc.bias FLOAT[4096] 7e295c411750
text.transformer.resblocks.8.mlp.c_proj.bias FLOAT[1024] e8e8d23360db
text.transformer.resblocks.9.attn.in_proj_bias FLOAT[3072] e7a81a6edfbe
text.transformer.resblocks.9.attn.out_proj.bias FLOAT[1024] 61c36f7b0197
text.transformer.resblocks.9.ln_1.bias FLOAT[1024] ee54a81b1dd0
text.transformer.resblocks.9.ln_1.weight FLOAT[1024] 215267d5313e
text.transformer.resblocks.9.ln_2.bias FLOAT[1024] e6392a39c524
text.transformer.resblocks.9.ln_2.weight FLOAT[1024] 8fcf59bb003b
text.transformer.resblocks.9.mlp.c_fc.bias FLOAT[4096] f63d6b264771
text.transformer.resblocks.9.mlp.c_proj.bias FLOAT[1024] 8edf9c4a1a2b
val_0 INT64[1] 12a3ae445661
val_1 FLOAT[] 6708d9be4956
val_10 FLOAT[1024,3072] 2f6c38ec077e
val_11 FLOAT[1024,4096] 884a8ee2c462
val_12 FLOAT[4096,1024] 7697a7e34d39
val_13 FLOAT[1024,3072] 7e3fc97b3935
val_14 FLOAT[1024,4096] 4bc298be1f7a
val_15 FLOAT[4096,1024] 908cd83d6cf6
val_16 FLOAT[1024,3072] 4be258a6b480
val_17 FLOAT[1024,4096] 8248955ab331
val_18 FLOAT[4096,1024] 7d79c1468c23
val_19 FLOAT[1024,3072] 58e5a2675774
val_2 INT64[1] 7c9fa136d441
val_20 FLOAT[1024,4096] 4e5df9a5ab31
val_21 FLOAT[4096,1024] ffe2c64292df
val_22 FLOAT[1024,3072] 73595870abdc
val_23 FLOAT[1024,4096] 41073c800b1c
val_24 FLOAT[4096,1024] d8f492166619
val_25 FLOAT[1024,3072] a6b85236d81a
val_26 FLOAT[1024,4096] da2972108ec0
val_27 FLOAT[4096,1024] 49b6765182a0
val_28 FLOAT[1024,3072] 968643f1572d
val_29 FLOAT[1024,4096] 183e36ee1446
val_3 INT64[1] 6a69a6cc7473
val_30 FLOAT[4096,1024] ad589407dfd7
val_31 FLOAT[1024,3072] e9bdc8e5f838
val_32 FLOAT[1024,4096] a91be89b632a
val_33 FLOAT[4096,1024] f6ee4671a7a8
val_34 FLOAT[1024,3072] 0644efa44583
val_35 FLOAT[1024,4096] 653914a1c284
val_36 FLOAT[4096,1024] ab8086adbf29
val_37 FLOAT[1024,3072] 263245d106d7
val_38 FLOAT[1024,4096] 977cd475510d
val_39 FLOAT[4096,1024] db2974287ae3
val_4 FLOAT[1024,3072] 336b98a2496f
val_40 FLOAT[1024,3072] 3e4f91287840
val_41 FLOAT[1024,4096] bb75a2aef7a4
val_42 FLOAT[4096,1024] abada51f2a61
val_43 FLOAT[1024,3072] 15dea21619e8
val_44 FLOAT[1024,4096] ef67d266f647
val_45 FLOAT[4096,1024] d84e850dc9cb
val_46 FLOAT[1024,3072] d3cebe4115ff
val_47 FLOAT[1024,4096] 363359c4b0ff
val_48 FLOAT[4096,1024] 74cb24bb4920
val_49 FLOAT[1024,3072] 4a909ebdece4
val_5 FLOAT[1024,4096] 70f1ef48d19d
val_50 FLOAT[1024,4096] 6ff999fbff48
val_51 FLOAT[4096,1024] 04b840602661
val_52 FLOAT[1024,3072] 00f46e6966aa
val_53 FLOAT[1024,4096] c741db2171e3
val_54 FLOAT[4096,1024] c4d2d5b2c648
val_55 FLOAT[1024,3072] e9e7e9783b8a
val_56 FLOAT[1024,4096] d7dc9e5246cb
val_57 FLOAT[4096,1024] 00441f4b4318
val_58 FLOAT[1024,3072] 72ca412fd6dd
val_59 FLOAT[1024,4096] 7da74894796f
val_6 FLOAT[4096,1024] 19a8a6a3306e
val_60 FLOAT[4096,1024] 5e8aea25484a
val_61 FLOAT[1024,3072] 483a655fc7ea
val_62 FLOAT[1024,4096] 7b680db819b6
val_63 FLOAT[4096,1024] 6b62432f1a63
val_64 FLOAT[1024,3072] 27bb81ee1d66
val_65 FLOAT[1024,4096] 16b794ee6556
val_66 FLOAT[4096,1024] 1837925190c3
val_67 FLOAT[1024,3072] 45d28e8c05bc
val_68 FLOAT[1024,4096] 13919bbe462b
val_69 FLOAT[4096,1024] 31097ab7706b
val_7 FLOAT[1024,3072] 6910800422f3
val_70 FLOAT[1024,3072] 7002be9d5ed9
val_71 FLOAT[1024,4096] 80e1b2e0a9a2
val_72 FLOAT[4096,1024] a9e61ddcde23
val_73 FLOAT[1024,3072] 7890c200fc38
val_74 FLOAT[1024,4096] 754d191e87d5
val_75 FLOAT[4096,1024] a014a57cfb1e
val_8 FLOAT[1024,4096] 6b450926bf6d
val_9 FLOAT[4096,1024] c51123ef5771
