Hugging Face's logo

zhaohb
/
chatglm_6b_onnx

ONNX
Model card Files
xet
Community
2
zhaohb commited on
Commit
080e0a1
·
1 Parent(s): 68eafd2

add onnx trt model

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +344 -0
  2. model6b_onnx_pkv/_transformer_layers.0_attention_rotary_emb_Constant_5_attr__value +3 -0
  3. model6b_onnx_pkv/_transformer_layers.0_attention_rotary_emb_Constant_attr__value +3 -0
  4. model6b_onnx_pkv/model.onnx +3 -0
  5. model6b_onnx_pkv/onnx__MatMul_10597 +3 -0
  6. model6b_onnx_pkv/onnx__MatMul_10628 +3 -0
  7. model6b_onnx_pkv/onnx__MatMul_10629 +3 -0
  8. model6b_onnx_pkv/onnx__MatMul_10630 +3 -0
  9. model6b_onnx_pkv/onnx__MatMul_10631 +3 -0
  10. model6b_onnx_pkv/onnx__MatMul_10658 +3 -0
  11. model6b_onnx_pkv/onnx__MatMul_10659 +3 -0
  12. model6b_onnx_pkv/onnx__MatMul_10660 +3 -0
  13. model6b_onnx_pkv/onnx__MatMul_10661 +3 -0
  14. model6b_onnx_pkv/onnx__MatMul_10688 +3 -0
  15. model6b_onnx_pkv/onnx__MatMul_10689 +3 -0
  16. model6b_onnx_pkv/onnx__MatMul_10690 +3 -0
  17. model6b_onnx_pkv/onnx__MatMul_10691 +3 -0
  18. model6b_onnx_pkv/onnx__MatMul_10718 +3 -0
  19. model6b_onnx_pkv/onnx__MatMul_10719 +3 -0
  20. model6b_onnx_pkv/onnx__MatMul_10720 +3 -0
  21. model6b_onnx_pkv/onnx__MatMul_10721 +3 -0
  22. model6b_onnx_pkv/onnx__MatMul_10748 +3 -0
  23. model6b_onnx_pkv/onnx__MatMul_10749 +3 -0
  24. model6b_onnx_pkv/onnx__MatMul_10750 +3 -0
  25. model6b_onnx_pkv/onnx__MatMul_10751 +3 -0
  26. model6b_onnx_pkv/onnx__MatMul_10778 +3 -0
  27. model6b_onnx_pkv/onnx__MatMul_10779 +3 -0
  28. model6b_onnx_pkv/onnx__MatMul_10780 +3 -0
  29. model6b_onnx_pkv/onnx__MatMul_10781 +3 -0
  30. model6b_onnx_pkv/onnx__MatMul_10808 +3 -0
  31. model6b_onnx_pkv/onnx__MatMul_10809 +3 -0
  32. model6b_onnx_pkv/onnx__MatMul_10810 +3 -0
  33. model6b_onnx_pkv/onnx__MatMul_10811 +3 -0
  34. model6b_onnx_pkv/onnx__MatMul_10838 +3 -0
  35. model6b_onnx_pkv/onnx__MatMul_10839 +3 -0
  36. model6b_onnx_pkv/onnx__MatMul_10840 +3 -0
  37. model6b_onnx_pkv/onnx__MatMul_10841 +3 -0
  38. model6b_onnx_pkv/onnx__MatMul_10868 +3 -0
  39. model6b_onnx_pkv/onnx__MatMul_10869 +3 -0
  40. model6b_onnx_pkv/onnx__MatMul_10870 +3 -0
  41. model6b_onnx_pkv/onnx__MatMul_10871 +3 -0
  42. model6b_onnx_pkv/onnx__MatMul_10898 +3 -0
  43. model6b_onnx_pkv/onnx__MatMul_10899 +3 -0
  44. model6b_onnx_pkv/onnx__MatMul_10900 +3 -0
  45. model6b_onnx_pkv/onnx__MatMul_10901 +3 -0
  46. model6b_onnx_pkv/onnx__MatMul_10928 +3 -0
  47. model6b_onnx_pkv/onnx__MatMul_10929 +3 -0
  48. model6b_onnx_pkv/onnx__MatMul_10930 +3 -0
  49. model6b_onnx_pkv/onnx__MatMul_10931 +3 -0
  50. model6b_onnx_pkv/onnx__MatMul_10958 +3 -0
.gitattributes CHANGED
@@ -32,3 +32,347 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ model6b_onnx_pkv/transformer.layers.5.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
36
+ model6b_onnx_pkv/transformer.layers.8.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
37
+ model6b_onnx_pkv/onnx__MatMul_10689 filter=lfs diff=lfs merge=lfs -text
38
+ model6b_onnx_pkv/onnx__MatMul_10868 filter=lfs diff=lfs merge=lfs -text
39
+ model6b_onnx_pkv/onnx__MatMul_11411 filter=lfs diff=lfs merge=lfs -text
40
+ model6b_onnx_pkv/transformer.layers.14.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
41
+ model6b_onnx_pkv/transformer.layers.15.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
42
+ model6b_onnx_pkv/transformer.layers.6.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
43
+ model6b_onnx_pkv/transformer.layers.7.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
44
+ model6b_onnx_pkv/transformer.layers.9.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
45
+ model6b_onnx_pkv/transformer.layers.11.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
46
+ model6b_onnx_pkv/transformer.layers.13.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
47
+ model6b_onnx_pkv/transformer.layers.16.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
48
+ model6b_onnx_pkv/transformer.layers.16.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
49
+ model6b_onnx_pkv/transformer.layers.25.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
50
+ model6b_onnx_pkv/onnx__MatMul_10900 filter=lfs diff=lfs merge=lfs -text
51
+ model6b_onnx_pkv/onnx__MatMul_11228 filter=lfs diff=lfs merge=lfs -text
52
+ model6b_onnx_pkv/transformer.layers.10.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
53
+ model6b_onnx_pkv/transformer.layers.17.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
54
+ model6b_onnx_pkv/transformer.layers.12.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
55
+ model6b_onnx_pkv/transformer.layers.15.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
56
+ model6b_onnx_pkv/transformer.layers.2.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
57
+ model6b_onnx_pkv/onnx__MatMul_11081 filter=lfs diff=lfs merge=lfs -text
58
+ model6b_onnx_pkv/onnx__MatMul_11198 filter=lfs diff=lfs merge=lfs -text
59
+ model6b_onnx_pkv/onnx__MatMul_11258 filter=lfs diff=lfs merge=lfs -text
60
+ model6b_onnx_pkv/onnx__MatMul_11319 filter=lfs diff=lfs merge=lfs -text
61
+ model6b_onnx_pkv/transformer.layers.0.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
62
+ model6b_onnx_pkv/transformer.layers.24.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
63
+ model6b_onnx_pkv/onnx__MatMul_11231 filter=lfs diff=lfs merge=lfs -text
64
+ model6b_onnx_pkv/transformer.layers.11.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
65
+ model6b_onnx_pkv/transformer.layers.4.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
66
+ model6b_onnx_pkv/transformer.layers.9.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
67
+ model6b_onnx_pkv/onnx__MatMul_10959 filter=lfs diff=lfs merge=lfs -text
68
+ model6b_onnx_pkv/onnx__MatMul_11348 filter=lfs diff=lfs merge=lfs -text
69
+ model6b_onnx_pkv/transformer.layers.1.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
70
+ model6b_onnx_pkv/transformer.layers.15.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
71
+ model6b_onnx_pkv/transformer.layers.24.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
72
+ model6b_onnx_pkv/transformer.layers.17.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
73
+ model6b_onnx_pkv/onnx__MatMul_10779 filter=lfs diff=lfs merge=lfs -text
74
+ model6b_onnx_pkv/onnx__MatMul_10960 filter=lfs diff=lfs merge=lfs -text
75
+ model6b_onnx_pkv/onnx__MatMul_10988 filter=lfs diff=lfs merge=lfs -text
76
+ model6b_onnx_pkv/onnx__MatMul_11051 filter=lfs diff=lfs merge=lfs -text
77
+ model6b_onnx_pkv/transformer.layers.16.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
78
+ model6b_onnx_pkv/onnx__MatMul_11409 filter=lfs diff=lfs merge=lfs -text
79
+ model6b_onnx_pkv/transformer.layers.1.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
80
+ model6b_onnx_pkv/transformer.layers.18.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
81
+ model6b_onnx_pkv/transformer.layers.19.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
82
+ model6b_onnx_pkv/transformer.layers.9.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
83
+ model6b_onnx_pkv/transformer.layers.22.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
84
+ model6b_onnx_pkv/transformer.layers.27.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
85
+ model6b_onnx_pkv/transformer.layers.5.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
86
+ model6b_onnx_pkv/transformer.layers.8.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
87
+ model6b_onnx_pkv/transformer.layers.8.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
88
+ model6b_onnx_pkv/onnx__MatMul_11109 filter=lfs diff=lfs merge=lfs -text
89
+ model6b_onnx_pkv/transformer.layers.2.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
90
+ model6b_onnx_pkv/transformer.layers.22.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
91
+ model6b_onnx_pkv/onnx__MatMul_10718 filter=lfs diff=lfs merge=lfs -text
92
+ model6b_onnx_pkv/transformer.layers.16.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
93
+ model6b_onnx_pkv/transformer.layers.21.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
94
+ model6b_onnx_pkv/transformer.layers.3.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
95
+ model6b_onnx_pkv/transformer.layers.4.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
96
+ model6b_onnx_pkv/onnx__MatMul_10958 filter=lfs diff=lfs merge=lfs -text
97
+ model6b_onnx_pkv/onnx__MatMul_11230 filter=lfs diff=lfs merge=lfs -text
98
+ model6b_onnx_pkv/transformer.layers.25.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
99
+ model6b_onnx_pkv/transformer.layers.3.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
100
+ model6b_onnx_pkv/transformer.layers.19.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
101
+ model6b_onnx_pkv/transformer.layers.25.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
102
+ model6b_onnx_pkv/transformer.layers.26.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
103
+ model6b_onnx_pkv/_transformer_layers.0_attention_rotary_emb_Constant_5_attr__value filter=lfs diff=lfs merge=lfs -text
104
+ model6b_onnx_pkv/onnx__MatMul_10658 filter=lfs diff=lfs merge=lfs -text
105
+ model6b_onnx_pkv/onnx__MatMul_11110 filter=lfs diff=lfs merge=lfs -text
106
+ model6b_onnx_pkv/onnx__MatMul_11170 filter=lfs diff=lfs merge=lfs -text
107
+ model6b_onnx_pkv/transformer.layers.12.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
108
+ model6b_onnx_pkv/transformer.layers.27.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
109
+ model6b_onnx_pkv/transformer.layers.6.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
110
+ model6b_onnx_pkv/transformer.layers.8.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
111
+ model6b_onnx_pkv/onnx__MatMul_11139 filter=lfs diff=lfs merge=lfs -text
112
+ model6b_onnx_pkv/transformer.layers.1.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
113
+ model6b_onnx_pkv/transformer.layers.1.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
114
+ model6b_onnx_pkv/transformer.layers.17.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
115
+ model6b_onnx_pkv/transformer.layers.2.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
116
+ model6b_onnx_pkv/onnx__MatMul_10630 filter=lfs diff=lfs merge=lfs -text
117
+ model6b_onnx_pkv/transformer.layers.10.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
118
+ model6b_onnx_pkv/transformer.layers.19.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
119
+ model6b_onnx_pkv/transformer.layers.3.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
120
+ model6b_onnx_pkv/transformer.layers.7.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
121
+ model6b_onnx_pkv/onnx__MatMul_10901 filter=lfs diff=lfs merge=lfs -text
122
+ model6b_onnx_pkv/transformer.layers.16.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
123
+ model6b_onnx_pkv/transformer.layers.21.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
124
+ model6b_onnx_pkv/transformer.layers.23.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
125
+ model6b_onnx_pkv/transformer.layers.24.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
126
+ model6b_onnx_pkv/transformer.layers.8.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
127
+ model6b_onnx_pkv/onnx__MatMul_10929 filter=lfs diff=lfs merge=lfs -text
128
+ model6b_onnx_pkv/onnx__MatMul_10931 filter=lfs diff=lfs merge=lfs -text
129
+ model6b_onnx_pkv/transformer.layers.16.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
130
+ model6b_onnx_pkv/transformer.layers.21.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
131
+ model6b_onnx_pkv/transformer.layers.4.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
132
+ model6b_onnx_pkv/transformer.layers.17.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
133
+ model6b_onnx_pkv/transformer.layers.23.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
134
+ model6b_onnx_pkv/transformer.layers.23.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
135
+ model6b_onnx_pkv/onnx__MatMul_10809 filter=lfs diff=lfs merge=lfs -text
136
+ model6b_onnx_pkv/onnx__MatMul_11438 filter=lfs diff=lfs merge=lfs -text
137
+ model6b_onnx_pkv/transformer.final_layernorm.weight filter=lfs diff=lfs merge=lfs -text
138
+ model6b_onnx_pkv/transformer.layers.0.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
139
+ model6b_onnx_pkv/transformer.layers.1.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
140
+ model6b_onnx_pkv/transformer.layers.12.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
141
+ model6b_onnx_pkv/transformer.layers.12.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
142
+ model6b_onnx_pkv/transformer.layers.14.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
143
+ model6b_onnx_pkv/onnx__MatMul_10840 filter=lfs diff=lfs merge=lfs -text
144
+ model6b_onnx_pkv/onnx__MatMul_11049 filter=lfs diff=lfs merge=lfs -text
145
+ model6b_onnx_pkv/onnx__MatMul_11080 filter=lfs diff=lfs merge=lfs -text
146
+ model6b_onnx_pkv/onnx__MatMul_11259 filter=lfs diff=lfs merge=lfs -text
147
+ model6b_onnx_pkv/onnx__MatMul_11351 filter=lfs diff=lfs merge=lfs -text
148
+ model6b_onnx_pkv/transformer.layers.22.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
149
+ model6b_onnx_pkv/transformer.layers.8.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
150
+ model6b_onnx_pkv/onnx__MatMul_10631 filter=lfs diff=lfs merge=lfs -text
151
+ model6b_onnx_pkv/onnx__MatMul_11020 filter=lfs diff=lfs merge=lfs -text
152
+ model6b_onnx_pkv/onnx__MatMul_11111 filter=lfs diff=lfs merge=lfs -text
153
+ model6b_onnx_pkv/transformer.layers.20.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
154
+ model6b_onnx_pkv/transformer.layers.25.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
155
+ model6b_onnx_pkv/transformer.layers.26.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
156
+ model6b_onnx_pkv/transformer.layers.3.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
157
+ model6b_onnx_pkv/transformer.layers.4.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
158
+ model6b_onnx_pkv/onnx__MatMul_10721 filter=lfs diff=lfs merge=lfs -text
159
+ model6b_onnx_pkv/onnx__MatMul_11381 filter=lfs diff=lfs merge=lfs -text
160
+ model6b_onnx_pkv/transformer.layers.1.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
161
+ model6b_onnx_pkv/transformer.layers.24.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
162
+ model6b_onnx_pkv/transformer.layers.26.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
163
+ model6b_onnx_pkv/transformer.layers.5.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
164
+ model6b_onnx_pkv/transformer.layers.22.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
165
+ model6b_onnx_pkv/transformer.layers.3.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
166
+ model6b_onnx_pkv/transformer.word_embeddings.weight filter=lfs diff=lfs merge=lfs -text
167
+ model6b_onnx_pkv/onnx__MatMul_10660 filter=lfs diff=lfs merge=lfs -text
168
+ model6b_onnx_pkv/onnx__MatMul_11138 filter=lfs diff=lfs merge=lfs -text
169
+ model6b_onnx_pkv/onnx__MatMul_11441 filter=lfs diff=lfs merge=lfs -text
170
+ model6b_onnx_pkv/transformer.layers.13.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
171
+ model6b_onnx_pkv/transformer.layers.20.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
172
+ model6b_onnx_pkv/_transformer_layers.0_attention_rotary_emb_Constant_attr__value filter=lfs diff=lfs merge=lfs -text
173
+ model6b_onnx_pkv/onnx__MatMul_10898 filter=lfs diff=lfs merge=lfs -text
174
+ model6b_onnx_pkv/onnx__MatMul_10989 filter=lfs diff=lfs merge=lfs -text
175
+ model6b_onnx_pkv/transformer.layers.0.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
176
+ model6b_onnx_pkv/transformer.layers.24.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
177
+ model6b_onnx_pkv/onnx__MatMul_10871 filter=lfs diff=lfs merge=lfs -text
178
+ model6b_onnx_pkv/transformer.layers.11.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
179
+ model6b_onnx_pkv/transformer.layers.21.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
180
+ model6b_onnx_pkv/transformer.layers.4.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
181
+ model6b_onnx_pkv/transformer.layers.7.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
182
+ model6b_onnx_pkv/transformer.layers.5.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
183
+ model6b_onnx_pkv/onnx__MatMul_11019 filter=lfs diff=lfs merge=lfs -text
184
+ model6b_onnx_pkv/onnx__MatMul_11439 filter=lfs diff=lfs merge=lfs -text
185
+ model6b_onnx_pkv/transformer.layers.14.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
186
+ model6b_onnx_pkv/transformer.layers.15.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
187
+ model6b_onnx_pkv/transformer.layers.23.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
188
+ model6b_onnx_pkv/onnx__MatMul_10780 filter=lfs diff=lfs merge=lfs -text
189
+ model6b_onnx_pkv/onnx__MatMul_11169 filter=lfs diff=lfs merge=lfs -text
190
+ model6b_onnx_pkv/transformer.layers.26.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
191
+ model6b_onnx_pkv/transformer.layers.26.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
192
+ model6b_onnx_pkv/transformer.layers.7.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
193
+ model6b_onnx_pkv/transformer.layers.11.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
194
+ model6b_onnx_pkv/transformer.layers.16.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
195
+ model6b_onnx_pkv/transformer.layers.25.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
196
+ model6b_onnx_pkv/transformer.layers.6.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
197
+ model6b_onnx_pkv/onnx__MatMul_11289 filter=lfs diff=lfs merge=lfs -text
198
+ model6b_onnx_pkv/transformer.layers.22.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
199
+ model6b_onnx_pkv/onnx__MatMul_10811 filter=lfs diff=lfs merge=lfs -text
200
+ model6b_onnx_pkv/transformer.layers.17.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
201
+ model6b_onnx_pkv/transformer.layers.18.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
202
+ model6b_onnx_pkv/transformer.layers.5.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
203
+ model6b_onnx_pkv/transformer.layers.10.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
204
+ model6b_onnx_pkv/onnx__MatMul_10628 filter=lfs diff=lfs merge=lfs -text
205
+ model6b_onnx_pkv/onnx__MatMul_11349 filter=lfs diff=lfs merge=lfs -text
206
+ model6b_onnx_pkv/transformer.layers.18.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
207
+ model6b_onnx_pkv/transformer.layers.6.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
208
+ model6b_onnx_pkv/transformer.layers.14.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
209
+ model6b_onnx_pkv/transformer.layers.18.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
210
+ model6b_onnx_pkv/transformer.layers.27.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
211
+ model6b_onnx_pkv/onnx__MatMul_10720 filter=lfs diff=lfs merge=lfs -text
212
+ model6b_onnx_pkv/onnx__MatMul_10778 filter=lfs diff=lfs merge=lfs -text
213
+ model6b_onnx_pkv/onnx__MatMul_11048 filter=lfs diff=lfs merge=lfs -text
214
+ model6b_onnx_pkv/onnx__MatMul_11290 filter=lfs diff=lfs merge=lfs -text
215
+ model6b_onnx_pkv/transformer.layers.12.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
216
+ model6b_onnx_pkv/transformer.layers.7.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
217
+ model6b_onnx_pkv/transformer.layers.19.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
218
+ model6b_onnx_pkv/transformer.layers.20.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
219
+ model6b_onnx_pkv/transformer.layers.20.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
220
+ model6b_onnx_pkv/onnx__MatMul_10597 filter=lfs diff=lfs merge=lfs -text
221
+ model6b_onnx_pkv/onnx__MatMul_10869 filter=lfs diff=lfs merge=lfs -text
222
+ model6b_onnx_pkv/onnx__MatMul_10961 filter=lfs diff=lfs merge=lfs -text
223
+ model6b_onnx_pkv/onnx__MatMul_11171 filter=lfs diff=lfs merge=lfs -text
224
+ model6b_onnx_pkv/transformer.layers.13.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
225
+ model6b_onnx_pkv/transformer.layers.22.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
226
+ model6b_onnx_pkv/transformer.layers.22.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
227
+ model6b_onnx_pkv/transformer.layers.5.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
228
+ model6b_onnx_pkv/onnx__MatMul_10661 filter=lfs diff=lfs merge=lfs -text
229
+ model6b_onnx_pkv/onnx__MatMul_10691 filter=lfs diff=lfs merge=lfs -text
230
+ model6b_onnx_pkv/onnx__MatMul_10750 filter=lfs diff=lfs merge=lfs -text
231
+ model6b_onnx_pkv/onnx__MatMul_10810 filter=lfs diff=lfs merge=lfs -text
232
+ model6b_onnx_pkv/onnx__MatMul_10839 filter=lfs diff=lfs merge=lfs -text
233
+ model6b_onnx_pkv/onnx__MatMul_11021 filter=lfs diff=lfs merge=lfs -text
234
+ model6b_onnx_pkv/transformer.layers.13.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
235
+ model6b_onnx_pkv/model.onnx filter=lfs diff=lfs merge=lfs -text
236
+ model6b_onnx_pkv/onnx__MatMul_11079 filter=lfs diff=lfs merge=lfs -text
237
+ model6b_onnx_pkv/transformer.layers.6.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
238
+ model6b_onnx_pkv/transformer.layers.9.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
239
+ model6b_onnx_pkv/transformer.layers.20.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
240
+ model6b_onnx_pkv/transformer.layers.26.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
241
+ model6b_onnx_pkv/transformer.layers.27.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
242
+ model6b_onnx_pkv/onnx__MatMul_10749 filter=lfs diff=lfs merge=lfs -text
243
+ model6b_onnx_pkv/transformer.layers.12.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
244
+ model6b_onnx_pkv/transformer.layers.13.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
245
+ model6b_onnx_pkv/transformer.layers.2.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
246
+ model6b_onnx_pkv/transformer.layers.20.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
247
+ model6b_onnx_pkv/onnx__MatMul_11018 filter=lfs diff=lfs merge=lfs -text
248
+ model6b_onnx_pkv/transformer.layers.25.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
249
+ model6b_onnx_pkv/transformer.layers.6.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
250
+ model6b_onnx_pkv/onnx__MatMul_10899 filter=lfs diff=lfs merge=lfs -text
251
+ model6b_onnx_pkv/onnx__MatMul_11408 filter=lfs diff=lfs merge=lfs -text
252
+ model6b_onnx_pkv/transformer.layers.11.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
253
+ model6b_onnx_pkv/transformer.layers.14.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
254
+ model6b_onnx_pkv/transformer.layers.23.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
255
+ model6b_onnx_pkv/transformer.layers.13.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
256
+ model6b_onnx_pkv/transformer.layers.2.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
257
+ model6b_onnx_pkv/transformer.layers.21.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
258
+ model6b_onnx_pkv/onnx__MatMul_10719 filter=lfs diff=lfs merge=lfs -text
259
+ model6b_onnx_pkv/onnx__MatMul_11199 filter=lfs diff=lfs merge=lfs -text
260
+ model6b_onnx_pkv/onnx__MatMul_11288 filter=lfs diff=lfs merge=lfs -text
261
+ model6b_onnx_pkv/onnx__MatMul_11380 filter=lfs diff=lfs merge=lfs -text
262
+ model6b_onnx_pkv/transformer.layers.10.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
263
+ model6b_onnx_pkv/transformer.layers.25.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
264
+ model6b_onnx_pkv/transformer.layers.3.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
265
+ model6b_onnx_pkv/transformer.layers.6.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
266
+ model6b_onnx_pkv/onnx__MatMul_11378 filter=lfs diff=lfs merge=lfs -text
267
+ model6b_onnx_pkv/transformer.layers.13.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
268
+ model6b_onnx_pkv/transformer.layers.20.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
269
+ model6b_onnx_pkv/onnx__MatMul_10841 filter=lfs diff=lfs merge=lfs -text
270
+ model6b_onnx_pkv/onnx__MatMul_10870 filter=lfs diff=lfs merge=lfs -text
271
+ model6b_onnx_pkv/onnx__MatMul_10991 filter=lfs diff=lfs merge=lfs -text
272
+ model6b_onnx_pkv/onnx__MatMul_11201 filter=lfs diff=lfs merge=lfs -text
273
+ model6b_onnx_pkv/onnx__MatMul_11291 filter=lfs diff=lfs merge=lfs -text
274
+ model6b_onnx_pkv/transformer.layers.7.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
275
+ model6b_onnx_pkv/transformer.layers.5.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
276
+ model6b_onnx_pkv/transformer.layers.9.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
277
+ model6b_onnx_pkv/transformer.layers.13.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
278
+ model6b_onnx_pkv/transformer.layers.15.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
279
+ model6b_onnx_pkv/transformer.layers.18.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
280
+ model6b_onnx_pkv/transformer.layers.26.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
281
+ model6b_onnx_pkv/transformer.layers.27.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
282
+ model6b_onnx_pkv/transformer.layers.19.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
283
+ model6b_onnx_pkv/transformer.layers.7.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
284
+ model6b_onnx_pkv/onnx__MatMul_10808 filter=lfs diff=lfs merge=lfs -text
285
+ model6b_onnx_pkv/onnx__MatMul_11260 filter=lfs diff=lfs merge=lfs -text
286
+ model6b_onnx_pkv/onnx__MatMul_11440 filter=lfs diff=lfs merge=lfs -text
287
+ model6b_onnx_pkv/transformer.layers.14.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
288
+ model6b_onnx_pkv/transformer.layers.17.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
289
+ model6b_onnx_pkv/transformer.layers.4.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
290
+ model6b_onnx_pkv/transformer.layers.4.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
291
+ model6b_onnx_pkv/onnx__MatMul_10690 filter=lfs diff=lfs merge=lfs -text
292
+ model6b_onnx_pkv/transformer.layers.0.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
293
+ model6b_onnx_pkv/transformer.layers.1.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
294
+ model6b_onnx_pkv/transformer.layers.19.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
295
+ model6b_onnx_pkv/transformer.layers.26.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
296
+ model6b_onnx_pkv/transformer.layers.18.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
297
+ model6b_onnx_pkv/transformer.layers.20.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
298
+ model6b_onnx_pkv/transformer.layers.23.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
299
+ model6b_onnx_pkv/onnx__MatMul_11050 filter=lfs diff=lfs merge=lfs -text
300
+ model6b_onnx_pkv/onnx__MatMul_11229 filter=lfs diff=lfs merge=lfs -text
301
+ model6b_onnx_pkv/onnx__MatMul_11320 filter=lfs diff=lfs merge=lfs -text
302
+ model6b_onnx_pkv/transformer.layers.0.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
303
+ model6b_onnx_pkv/transformer.layers.15.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
304
+ model6b_onnx_pkv/transformer.layers.9.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
305
+ model6b_onnx_pkv/transformer.layers.27.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
306
+ model6b_onnx_pkv/onnx__MatMul_10688 filter=lfs diff=lfs merge=lfs -text
307
+ model6b_onnx_pkv/onnx__MatMul_11200 filter=lfs diff=lfs merge=lfs -text
308
+ model6b_onnx_pkv/transformer.layers.10.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
309
+ model6b_onnx_pkv/transformer.layers.14.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
310
+ model6b_onnx_pkv/transformer.layers.21.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
311
+ model6b_onnx_pkv/transformer.layers.3.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
312
+ model6b_onnx_pkv/transformer.layers.8.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
313
+ model6b_onnx_pkv/onnx__MatMul_10629 filter=lfs diff=lfs merge=lfs -text
314
+ model6b_onnx_pkv/transformer.layers.11.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
315
+ model6b_onnx_pkv/transformer.layers.14.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
316
+ model6b_onnx_pkv/transformer.layers.21.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
317
+ model6b_onnx_pkv/transformer.layers.27.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
318
+ model6b_onnx_pkv/transformer.layers.23.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
319
+ model6b_onnx_pkv/transformer.layers.8.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
320
+ model6b_onnx_pkv/transformer.layers.1.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
321
+ model6b_onnx_pkv/transformer.layers.18.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
322
+ model6b_onnx_pkv/transformer.layers.18.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
323
+ model6b_onnx_pkv/transformer.layers.24.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
324
+ model6b_onnx_pkv/transformer.layers.5.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
325
+ model6b_onnx_pkv/transformer.layers.2.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
326
+ model6b_onnx_pkv/transformer.layers.25.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
327
+ model6b_onnx_pkv/onnx__MatMul_10748 filter=lfs diff=lfs merge=lfs -text
328
+ model6b_onnx_pkv/onnx__MatMul_10781 filter=lfs diff=lfs merge=lfs -text
329
+ model6b_onnx_pkv/onnx__MatMul_11141 filter=lfs diff=lfs merge=lfs -text
330
+ model6b_onnx_pkv/onnx__MatMul_11410 filter=lfs diff=lfs merge=lfs -text
331
+ model6b_onnx_pkv/transformer.layers.0.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
332
+ model6b_onnx_pkv/transformer.layers.10.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
333
+ model6b_onnx_pkv/transformer.layers.22.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
334
+ model6b_onnx_pkv/transformer.layers.23.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
335
+ model6b_onnx_pkv/transformer.layers.4.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
336
+ model6b_onnx_pkv/onnx__MatMul_11318 filter=lfs diff=lfs merge=lfs -text
337
+ model6b_onnx_pkv/transformer.layers.16.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
338
+ model6b_onnx_pkv/transformer.layers.17.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
339
+ model6b_onnx_pkv/onnx__MatMul_11078 filter=lfs diff=lfs merge=lfs -text
340
+ model6b_onnx_pkv/transformer.layers.10.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
341
+ model6b_onnx_pkv/transformer.layers.9.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
342
+ model6b_onnx_pkv/onnx__MatMul_11261 filter=lfs diff=lfs merge=lfs -text
343
+ model6b_onnx_pkv/transformer.layers.0.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
344
+ model6b_onnx_pkv/transformer.layers.10.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
345
+ model6b_onnx_pkv/transformer.layers.15.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
346
+ model6b_onnx_pkv/transformer.layers.7.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
347
+ model6b_onnx_pkv/transformer.layers.12.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
348
+ model6b_onnx_pkv/transformer.layers.17.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
349
+ model6b_onnx_pkv/transformer.layers.24.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
350
+ model6b_onnx_pkv/transformer.layers.24.post_attention_layernorm.bias filter=lfs diff=lfs merge=lfs -text
351
+ model6b_onnx_pkv/transformer.layers.3.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
352
+ model6b_onnx_pkv/onnx__MatMul_10930 filter=lfs diff=lfs merge=lfs -text
353
+ model6b_onnx_pkv/onnx__MatMul_10990 filter=lfs diff=lfs merge=lfs -text
354
+ model6b_onnx_pkv/onnx__MatMul_11168 filter=lfs diff=lfs merge=lfs -text
355
+ model6b_onnx_pkv/transformer.layers.11.post_attention_layernorm.weight filter=lfs diff=lfs merge=lfs -text
356
+ model6b_onnx_pkv/transformer.layers.15.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
357
+ model6b_onnx_pkv/transformer.layers.21.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
358
+ model6b_onnx_pkv/transformer.layers.11.input_layernorm.bias filter=lfs diff=lfs merge=lfs -text
359
+ model6b_onnx_pkv/transformer.layers.19.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
360
+ model6b_onnx_pkv/transformer.layers.2.attention.query_key_value.bias filter=lfs diff=lfs merge=lfs -text
361
+ model6b_onnx_pkv/onnx__MatMul_11350 filter=lfs diff=lfs merge=lfs -text
362
+ model6b_onnx_pkv/transformer.layers.6.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
363
+ model6b_onnx_pkv/transformer.layers.9.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
364
+ model6b_onnx_pkv/onnx__MatMul_10659 filter=lfs diff=lfs merge=lfs -text
365
+ model6b_onnx_pkv/onnx__MatMul_10751 filter=lfs diff=lfs merge=lfs -text
366
+ model6b_onnx_pkv/onnx__MatMul_10838 filter=lfs diff=lfs merge=lfs -text
367
+ model6b_onnx_pkv/onnx__MatMul_11108 filter=lfs diff=lfs merge=lfs -text
368
+ model6b_onnx_pkv/onnx__MatMul_11321 filter=lfs diff=lfs merge=lfs -text
369
+ model6b_onnx_pkv/onnx__MatMul_11140 filter=lfs diff=lfs merge=lfs -text
370
+ model6b_onnx_pkv/onnx__MatMul_11379 filter=lfs diff=lfs merge=lfs -text
371
+ model6b_onnx_pkv/transformer.layers.0.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
372
+ model6b_onnx_pkv/transformer.layers.27.input_layernorm.weight filter=lfs diff=lfs merge=lfs -text
373
+ model6b_onnx_pkv/onnx__MatMul_10928 filter=lfs diff=lfs merge=lfs -text
374
+ model6b_onnx_pkv/transformer.final_layernorm.bias filter=lfs diff=lfs merge=lfs -text
375
+ model6b_onnx_pkv/transformer.layers.12.mlp.dense_h_to_4h.bias filter=lfs diff=lfs merge=lfs -text
376
+ model6b_onnx_pkv/transformer.layers.19.attention.dense.bias filter=lfs diff=lfs merge=lfs -text
377
+ model6b_onnx_pkv/transformer.layers.2.mlp.dense_4h_to_h.bias filter=lfs diff=lfs merge=lfs -text
378
+ model6b_trt_pkv/out.engine filter=lfs diff=lfs merge=lfs -text
model6b_onnx_pkv/_transformer_layers.0_attention_rotary_emb_Constant_5_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e0f14ad394ea897982fdc1465ad8e08dfb4cec16822163355919b16cb5d370
3
+ size 6912
model6b_onnx_pkv/_transformer_layers.0_attention_rotary_emb_Constant_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c91b1342a80e65450d50881f51862e12782ec10ef6c0a8b81e5ed9f1161496e7
3
+ size 6912
model6b_onnx_pkv/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f6a68127538037731fd50c223bf74d34849110bd7cd8f959b1d5db95c21dcf
3
+ size 1437255
model6b_onnx_pkv/onnx__MatMul_10597 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b3b9d53e703004356713a88a610de9290200fdafee144acd7d711b2474cb40c
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10628 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a23eaf2051e272d7f1069490e5347347dd6e9125f2745d9c54309229b79c1a
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10629 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff458786910365967cc0be5582564c027c0f8b77c74fd0fee8dcf5914e96cd6
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10630 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3899424c89549d0776ce8296dcf50500f71f56b9c0ea68d4ec9e8836c0169b3c
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10631 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa69d25cd66fb8ba7e134d535323f1666b49d6d6d495ef044336ca8e5afd9c9
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10658 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d03feeef1dd8a1a26596015d29e9f65b3ac4ddeac7e681e96c6c07d41cbbb1d2
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10659 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a64bd600358cbab4b9d2884112e7f16b60ef1ca1d0952f3458332c374b5b359
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10660 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f697f53be2eb8f7aa10aad39ce829f997625e96c019fdc777782cb3aebc699
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10661 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0aa683ec3d4c69aad1998919b5f798dbf935477a179553b713f18f11d3a7b63
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10688 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd536bdcac8bd44e93212fbee13bd8a39b1508d6d2252d9474124cc8dcd51797
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10689 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c2b7f2d503014e81b87a141f3519c68d86be7ae7e69f2ccc5c60ed48c4dde5
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10690 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8202a994e1ff5f01d67c25ad117edb352061c4c3a0b4acb6ba56af70868c7d6f
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10691 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:977fdeb543c98d0284d1e472b71895944d2634b2ad85732e80460abfe00d7953
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10718 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f711e9caa7c6be3774a3c72313b995018de37d93fc05a04b7a6de6c9b0bb319f
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10719 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b3612fd4a3692cb6bfe685733141fe44bb92ac5159941f589173ce2f109f11
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10720 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a3b7e259524f56f8cbc9b8bb2a96d01df5849f0ca3473ea282fdfd74e35af2f
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10721 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9be72cbc37007b72130ac13c62d7deaf11c33a6bdff8cbe76be373b43fcf0e8
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10748 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f03e15bb6930eab1c5621636126d282ba3fcf563be280a1b9c9d0a3f2d25a8
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10749 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d62674e5adb60e9af1950908df6812fa967af36c809a24c6a8cac943d76fe63
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10750 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9020a52b93b94fa96639b453c8a1a55e690bef268de5b1da004d594aa9f5983a
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10751 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84375e83fce8928b5c01aff17b40063d9bdc5855cf0bbb4712ce08cf01696ff
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10778 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb18a26aade32b19b76e0df1d9e2d6fddd14288d2bf4ee83ff29315f1e5e6c70
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10779 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd26de944ed862c3f6931d10d91352a297793ece2721e4898993203b55491f58
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10780 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151919232dc8642d5189ae744e8e8219a6b0111d3e2c7336d9d71c3eb851bd8e
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10781 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99606f89f9bdddbbe10ff0a37def1b3502ccd2a81909f386f0eb11129ca0822b
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10808 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e62f32e6c1e4a0e1256a507c8f5ce140ef516808706f0baf38c4342702f8c5
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10809 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3bf30e608ef1390eb10f53167e1f115df21687fb0d14cca5d015a1e4dd4bf59
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10810 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c2c1b5222b63f0dcb802ae86340d5be4416eab8e32510887829239f62ee435
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10811 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609b82711fc4eade2dbf706167f60ad39d38306400bbd8b2473d6cafafa2d254
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10838 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77cf94df5dee24c8652c6dd875d5e7a69a6327347533d9de521814024cef914c
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10839 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bffa8a5c7e149e733a8795a88bcd3686e7c05612878744a18e14090527b820b
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10840 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4490ace34bb4862e110fb25183510818655cbb454fa316ca76c7892d335a37
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10841 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d83314b5a68408975e99cfc6bd80df5d1cbf9c40b173f251a5e930e4da1325
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10868 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ac64ab4dd68f8cd7b33b058e37ce4599e87f91f8c19ce6a6181679de8c19ff
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10869 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94d94f231901c12b8e1ea004aa659df781318cb8313750b4d383a8c5ec67f95
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10870 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0433813cfd54491fdb1fc4978ab9095304583bcc8dcd9d7aa6dec9bb25eb330b
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10871 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80c4d40193c129e230e40f7d308f8e2663f198a9078467960832a15606c5969f
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10898 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ffaf99a1ef84d88107a5455c6dbd5434b0ea87aee6316dd002398e6cd4ae72
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10899 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be8a577d6b8bc0a0ac556109febc8cc2e46a199c12d3a305ff1b86aa0c73c7b
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc8796f657d7572e24b742cba5cc548a93fbed168bce40ffba2ae50d61eff95
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10901 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e530bcb247ec9f5ddd119fe9918794304c198b24ba91f580f601d70cd8e5dd
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10928 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017f1224338a7390e3865376d8a872be4aac068ae39e00092fe4dd53b2727e90
3
+ size 67108864
model6b_onnx_pkv/onnx__MatMul_10929 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335a2d06004ea8036fcaf756fa96d332ac2e3397fb236b02e8b5d27439401c64
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10930 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54155314ea1ddded01b8b1ae8e589ba346e48988eed21ad4c790c1653f7dd424
3
+ size 268435456
model6b_onnx_pkv/onnx__MatMul_10931 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a046d96b975dd4557a06aa288fb1540785cfef8d622eb311549a821ac06966
3
+ size 201326592
model6b_onnx_pkv/onnx__MatMul_10958 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3539a984e81650c01937f655c193972bb59e13af033ca1390686c8812c911b36
3
+ size 67108864