erfanzar commited on
Commit
c71f6a2
·
verified ·
1 Parent(s): 5d768bf

Adding EasyDeL Checkpoints

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 +905 -0
  2. README.md +159 -0
  3. chat_template.jinja +109 -0
  4. checkpoint_metadata.json +6 -0
  5. config.json +167 -0
  6. generation_config.json +13 -0
  7. model/lm_head/kernel/.zarray +1 -0
  8. model/lm_head/kernel/0.0 +3 -0
  9. model/lm_head/kernel/1.0 +3 -0
  10. model/lm_head/kernel/2.0 +3 -0
  11. model/lm_head/kernel/3.0 +3 -0
  12. model/model/embed_tokens/embedding/.zarray +1 -0
  13. model/model/embed_tokens/embedding/0.0 +3 -0
  14. model/model/embed_tokens/embedding/1.0 +3 -0
  15. model/model/embed_tokens/embedding/2.0 +3 -0
  16. model/model/embed_tokens/embedding/3.0 +3 -0
  17. model/model/layers/0/input_layernorm/kernel/.zarray +1 -0
  18. model/model/layers/0/input_layernorm/kernel/0 +0 -0
  19. model/model/layers/0/mlp/down_proj/kernel/.zarray +1 -0
  20. model/model/layers/0/mlp/down_proj/kernel/0.0 +3 -0
  21. model/model/layers/0/mlp/down_proj/kernel/0.1 +3 -0
  22. model/model/layers/0/mlp/down_proj/kernel/0.2 +3 -0
  23. model/model/layers/0/mlp/down_proj/kernel/0.3 +3 -0
  24. model/model/layers/0/mlp/gate_proj/kernel/.zarray +1 -0
  25. model/model/layers/0/mlp/gate_proj/kernel/0.0 +3 -0
  26. model/model/layers/0/mlp/gate_proj/kernel/1.0 +3 -0
  27. model/model/layers/0/mlp/gate_proj/kernel/2.0 +3 -0
  28. model/model/layers/0/mlp/gate_proj/kernel/3.0 +3 -0
  29. model/model/layers/0/mlp/up_proj/kernel/.zarray +1 -0
  30. model/model/layers/0/mlp/up_proj/kernel/0.0 +3 -0
  31. model/model/layers/0/mlp/up_proj/kernel/1.0 +3 -0
  32. model/model/layers/0/mlp/up_proj/kernel/2.0 +3 -0
  33. model/model/layers/0/mlp/up_proj/kernel/3.0 +3 -0
  34. model/model/layers/0/post_attention_layernorm/kernel/.zarray +1 -0
  35. model/model/layers/0/post_attention_layernorm/kernel/0 +0 -0
  36. model/model/layers/0/self_attn/k_proj/kernel/.zarray +1 -0
  37. model/model/layers/0/self_attn/k_proj/kernel/0.0 +3 -0
  38. model/model/layers/0/self_attn/k_proj/kernel/1.0 +3 -0
  39. model/model/layers/0/self_attn/k_proj/kernel/2.0 +3 -0
  40. model/model/layers/0/self_attn/k_proj/kernel/3.0 +3 -0
  41. model/model/layers/0/self_attn/o_proj/kernel/.zarray +1 -0
  42. model/model/layers/0/self_attn/o_proj/kernel/0.0 +3 -0
  43. model/model/layers/0/self_attn/o_proj/kernel/0.1 +3 -0
  44. model/model/layers/0/self_attn/o_proj/kernel/0.2 +3 -0
  45. model/model/layers/0/self_attn/o_proj/kernel/0.3 +3 -0
  46. model/model/layers/0/self_attn/q_proj/kernel/.zarray +1 -0
  47. model/model/layers/0/self_attn/q_proj/kernel/0.0 +3 -0
  48. model/model/layers/0/self_attn/q_proj/kernel/1.0 +3 -0
  49. model/model/layers/0/self_attn/q_proj/kernel/2.0 +3 -0
  50. model/model/layers/0/self_attn/q_proj/kernel/3.0 +3 -0
.gitattributes CHANGED
@@ -33,3 +33,908 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model/lm_head/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
37
+ model/lm_head/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
38
+ model/lm_head/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
39
+ model/lm_head/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
40
+ model/model/embed_tokens/embedding/0.0 filter=lfs diff=lfs merge=lfs -text
41
+ model/model/embed_tokens/embedding/1.0 filter=lfs diff=lfs merge=lfs -text
42
+ model/model/embed_tokens/embedding/2.0 filter=lfs diff=lfs merge=lfs -text
43
+ model/model/embed_tokens/embedding/3.0 filter=lfs diff=lfs merge=lfs -text
44
+ model/model/layers/0/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
45
+ model/model/layers/0/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
46
+ model/model/layers/0/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
47
+ model/model/layers/0/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
48
+ model/model/layers/0/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
49
+ model/model/layers/0/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
50
+ model/model/layers/0/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
51
+ model/model/layers/0/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
52
+ model/model/layers/0/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
53
+ model/model/layers/0/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
54
+ model/model/layers/0/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
55
+ model/model/layers/0/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
56
+ model/model/layers/0/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
57
+ model/model/layers/0/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
58
+ model/model/layers/0/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
59
+ model/model/layers/0/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
60
+ model/model/layers/0/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
61
+ model/model/layers/0/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
62
+ model/model/layers/0/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
63
+ model/model/layers/0/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
64
+ model/model/layers/0/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
65
+ model/model/layers/0/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
66
+ model/model/layers/0/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
67
+ model/model/layers/0/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
68
+ model/model/layers/0/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
69
+ model/model/layers/0/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
70
+ model/model/layers/0/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
71
+ model/model/layers/0/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
72
+ model/model/layers/1/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
73
+ model/model/layers/1/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
74
+ model/model/layers/1/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
75
+ model/model/layers/1/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
76
+ model/model/layers/1/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
77
+ model/model/layers/1/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
78
+ model/model/layers/1/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
79
+ model/model/layers/1/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
80
+ model/model/layers/1/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
81
+ model/model/layers/1/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
82
+ model/model/layers/1/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
83
+ model/model/layers/1/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
84
+ model/model/layers/1/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
85
+ model/model/layers/1/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
86
+ model/model/layers/1/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
87
+ model/model/layers/1/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
88
+ model/model/layers/1/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
89
+ model/model/layers/1/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
90
+ model/model/layers/1/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
91
+ model/model/layers/1/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
92
+ model/model/layers/1/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
93
+ model/model/layers/1/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
94
+ model/model/layers/1/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
95
+ model/model/layers/1/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
96
+ model/model/layers/1/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
97
+ model/model/layers/1/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
98
+ model/model/layers/1/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
99
+ model/model/layers/1/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
100
+ model/model/layers/10/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
101
+ model/model/layers/10/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
102
+ model/model/layers/10/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
103
+ model/model/layers/10/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
104
+ model/model/layers/10/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
105
+ model/model/layers/10/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
106
+ model/model/layers/10/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
107
+ model/model/layers/10/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
108
+ model/model/layers/10/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
109
+ model/model/layers/10/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
110
+ model/model/layers/10/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
111
+ model/model/layers/10/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
112
+ model/model/layers/10/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
113
+ model/model/layers/10/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
114
+ model/model/layers/10/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
115
+ model/model/layers/10/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
116
+ model/model/layers/10/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
117
+ model/model/layers/10/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
118
+ model/model/layers/10/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
119
+ model/model/layers/10/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
120
+ model/model/layers/10/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
121
+ model/model/layers/10/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
122
+ model/model/layers/10/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
123
+ model/model/layers/10/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
124
+ model/model/layers/10/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
125
+ model/model/layers/10/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
126
+ model/model/layers/10/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
127
+ model/model/layers/10/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
128
+ model/model/layers/11/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
129
+ model/model/layers/11/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
130
+ model/model/layers/11/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
131
+ model/model/layers/11/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
132
+ model/model/layers/11/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
133
+ model/model/layers/11/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
134
+ model/model/layers/11/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
135
+ model/model/layers/11/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
136
+ model/model/layers/11/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
137
+ model/model/layers/11/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
138
+ model/model/layers/11/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
139
+ model/model/layers/11/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
140
+ model/model/layers/11/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
141
+ model/model/layers/11/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
142
+ model/model/layers/11/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
143
+ model/model/layers/11/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
144
+ model/model/layers/11/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
145
+ model/model/layers/11/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
146
+ model/model/layers/11/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
147
+ model/model/layers/11/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
148
+ model/model/layers/11/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
149
+ model/model/layers/11/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
150
+ model/model/layers/11/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
151
+ model/model/layers/11/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
152
+ model/model/layers/11/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
153
+ model/model/layers/11/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
154
+ model/model/layers/11/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
155
+ model/model/layers/11/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
156
+ model/model/layers/12/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
157
+ model/model/layers/12/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
158
+ model/model/layers/12/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
159
+ model/model/layers/12/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
160
+ model/model/layers/12/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
161
+ model/model/layers/12/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
162
+ model/model/layers/12/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
163
+ model/model/layers/12/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
164
+ model/model/layers/12/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
165
+ model/model/layers/12/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
166
+ model/model/layers/12/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
167
+ model/model/layers/12/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
168
+ model/model/layers/12/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
169
+ model/model/layers/12/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
170
+ model/model/layers/12/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
171
+ model/model/layers/12/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
172
+ model/model/layers/12/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
173
+ model/model/layers/12/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
174
+ model/model/layers/12/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
175
+ model/model/layers/12/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
176
+ model/model/layers/12/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
177
+ model/model/layers/12/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
178
+ model/model/layers/12/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
179
+ model/model/layers/12/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
180
+ model/model/layers/12/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
181
+ model/model/layers/12/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
182
+ model/model/layers/12/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
183
+ model/model/layers/12/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
184
+ model/model/layers/13/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
185
+ model/model/layers/13/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
186
+ model/model/layers/13/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
187
+ model/model/layers/13/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
188
+ model/model/layers/13/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
189
+ model/model/layers/13/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
190
+ model/model/layers/13/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
191
+ model/model/layers/13/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
192
+ model/model/layers/13/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
193
+ model/model/layers/13/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
194
+ model/model/layers/13/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
195
+ model/model/layers/13/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
196
+ model/model/layers/13/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
197
+ model/model/layers/13/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
198
+ model/model/layers/13/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
199
+ model/model/layers/13/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
200
+ model/model/layers/13/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
201
+ model/model/layers/13/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
202
+ model/model/layers/13/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
203
+ model/model/layers/13/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
204
+ model/model/layers/13/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
205
+ model/model/layers/13/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
206
+ model/model/layers/13/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
207
+ model/model/layers/13/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
208
+ model/model/layers/13/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
209
+ model/model/layers/13/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
210
+ model/model/layers/13/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
211
+ model/model/layers/13/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
212
+ model/model/layers/14/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
213
+ model/model/layers/14/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
214
+ model/model/layers/14/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
215
+ model/model/layers/14/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
216
+ model/model/layers/14/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
217
+ model/model/layers/14/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
218
+ model/model/layers/14/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
219
+ model/model/layers/14/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
220
+ model/model/layers/14/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
221
+ model/model/layers/14/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
222
+ model/model/layers/14/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
223
+ model/model/layers/14/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
224
+ model/model/layers/14/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
225
+ model/model/layers/14/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
226
+ model/model/layers/14/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
227
+ model/model/layers/14/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
228
+ model/model/layers/14/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
229
+ model/model/layers/14/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
230
+ model/model/layers/14/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
231
+ model/model/layers/14/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
232
+ model/model/layers/14/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
233
+ model/model/layers/14/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
234
+ model/model/layers/14/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
235
+ model/model/layers/14/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
236
+ model/model/layers/14/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
237
+ model/model/layers/14/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
238
+ model/model/layers/14/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
239
+ model/model/layers/14/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
240
+ model/model/layers/15/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
241
+ model/model/layers/15/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
242
+ model/model/layers/15/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
243
+ model/model/layers/15/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
244
+ model/model/layers/15/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
245
+ model/model/layers/15/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
246
+ model/model/layers/15/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
247
+ model/model/layers/15/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
248
+ model/model/layers/15/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
249
+ model/model/layers/15/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
250
+ model/model/layers/15/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
251
+ model/model/layers/15/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
252
+ model/model/layers/15/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
253
+ model/model/layers/15/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
254
+ model/model/layers/15/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
255
+ model/model/layers/15/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
256
+ model/model/layers/15/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
257
+ model/model/layers/15/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
258
+ model/model/layers/15/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
259
+ model/model/layers/15/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
260
+ model/model/layers/15/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
261
+ model/model/layers/15/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
262
+ model/model/layers/15/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
263
+ model/model/layers/15/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
264
+ model/model/layers/15/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
265
+ model/model/layers/15/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
266
+ model/model/layers/15/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
267
+ model/model/layers/15/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
268
+ model/model/layers/16/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
269
+ model/model/layers/16/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
270
+ model/model/layers/16/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
271
+ model/model/layers/16/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
272
+ model/model/layers/16/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
273
+ model/model/layers/16/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
274
+ model/model/layers/16/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
275
+ model/model/layers/16/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
276
+ model/model/layers/16/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
277
+ model/model/layers/16/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
278
+ model/model/layers/16/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
279
+ model/model/layers/16/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
280
+ model/model/layers/16/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
281
+ model/model/layers/16/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
282
+ model/model/layers/16/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
283
+ model/model/layers/16/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
284
+ model/model/layers/16/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
285
+ model/model/layers/16/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
286
+ model/model/layers/16/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
287
+ model/model/layers/16/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
288
+ model/model/layers/16/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
289
+ model/model/layers/16/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
290
+ model/model/layers/16/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
291
+ model/model/layers/16/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
292
+ model/model/layers/16/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
293
+ model/model/layers/16/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
294
+ model/model/layers/16/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
295
+ model/model/layers/16/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
296
+ model/model/layers/17/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
297
+ model/model/layers/17/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
298
+ model/model/layers/17/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
299
+ model/model/layers/17/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
300
+ model/model/layers/17/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
301
+ model/model/layers/17/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
302
+ model/model/layers/17/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
303
+ model/model/layers/17/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
304
+ model/model/layers/17/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
305
+ model/model/layers/17/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
306
+ model/model/layers/17/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
307
+ model/model/layers/17/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
308
+ model/model/layers/17/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
309
+ model/model/layers/17/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
310
+ model/model/layers/17/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
311
+ model/model/layers/17/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
312
+ model/model/layers/17/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
313
+ model/model/layers/17/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
314
+ model/model/layers/17/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
315
+ model/model/layers/17/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
316
+ model/model/layers/17/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
317
+ model/model/layers/17/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
318
+ model/model/layers/17/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
319
+ model/model/layers/17/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
320
+ model/model/layers/17/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
321
+ model/model/layers/17/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
322
+ model/model/layers/17/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
323
+ model/model/layers/17/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
324
+ model/model/layers/18/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
325
+ model/model/layers/18/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
326
+ model/model/layers/18/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
327
+ model/model/layers/18/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
328
+ model/model/layers/18/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
329
+ model/model/layers/18/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
330
+ model/model/layers/18/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
331
+ model/model/layers/18/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
332
+ model/model/layers/18/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
333
+ model/model/layers/18/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
334
+ model/model/layers/18/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
335
+ model/model/layers/18/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
336
+ model/model/layers/18/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
337
+ model/model/layers/18/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
338
+ model/model/layers/18/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
339
+ model/model/layers/18/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
340
+ model/model/layers/18/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
341
+ model/model/layers/18/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
342
+ model/model/layers/18/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
343
+ model/model/layers/18/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
344
+ model/model/layers/18/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
345
+ model/model/layers/18/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
346
+ model/model/layers/18/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
347
+ model/model/layers/18/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
348
+ model/model/layers/18/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
349
+ model/model/layers/18/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
350
+ model/model/layers/18/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
351
+ model/model/layers/18/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
352
+ model/model/layers/19/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
353
+ model/model/layers/19/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
354
+ model/model/layers/19/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
355
+ model/model/layers/19/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
356
+ model/model/layers/19/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
357
+ model/model/layers/19/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
358
+ model/model/layers/19/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
359
+ model/model/layers/19/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
360
+ model/model/layers/19/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
361
+ model/model/layers/19/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
362
+ model/model/layers/19/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
363
+ model/model/layers/19/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
364
+ model/model/layers/19/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
365
+ model/model/layers/19/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
366
+ model/model/layers/19/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
367
+ model/model/layers/19/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
368
+ model/model/layers/19/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
369
+ model/model/layers/19/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
370
+ model/model/layers/19/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
371
+ model/model/layers/19/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
372
+ model/model/layers/19/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
373
+ model/model/layers/19/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
374
+ model/model/layers/19/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
375
+ model/model/layers/19/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
376
+ model/model/layers/19/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
377
+ model/model/layers/19/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
378
+ model/model/layers/19/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
379
+ model/model/layers/19/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
380
+ model/model/layers/2/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
381
+ model/model/layers/2/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
382
+ model/model/layers/2/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
383
+ model/model/layers/2/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
384
+ model/model/layers/2/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
385
+ model/model/layers/2/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
386
+ model/model/layers/2/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
387
+ model/model/layers/2/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
388
+ model/model/layers/2/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
389
+ model/model/layers/2/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
390
+ model/model/layers/2/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
391
+ model/model/layers/2/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
392
+ model/model/layers/2/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
393
+ model/model/layers/2/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
394
+ model/model/layers/2/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
395
+ model/model/layers/2/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
396
+ model/model/layers/2/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
397
+ model/model/layers/2/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
398
+ model/model/layers/2/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
399
+ model/model/layers/2/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
400
+ model/model/layers/2/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
401
+ model/model/layers/2/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
402
+ model/model/layers/2/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
403
+ model/model/layers/2/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
404
+ model/model/layers/2/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
405
+ model/model/layers/2/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
406
+ model/model/layers/2/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
407
+ model/model/layers/2/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
408
+ model/model/layers/20/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
409
+ model/model/layers/20/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
410
+ model/model/layers/20/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
411
+ model/model/layers/20/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
412
+ model/model/layers/20/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
413
+ model/model/layers/20/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
414
+ model/model/layers/20/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
415
+ model/model/layers/20/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
416
+ model/model/layers/20/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
417
+ model/model/layers/20/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
418
+ model/model/layers/20/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
419
+ model/model/layers/20/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
420
+ model/model/layers/20/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
421
+ model/model/layers/20/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
422
+ model/model/layers/20/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
423
+ model/model/layers/20/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
424
+ model/model/layers/20/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
425
+ model/model/layers/20/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
426
+ model/model/layers/20/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
427
+ model/model/layers/20/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
428
+ model/model/layers/20/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
429
+ model/model/layers/20/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
430
+ model/model/layers/20/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
431
+ model/model/layers/20/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
432
+ model/model/layers/20/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
433
+ model/model/layers/20/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
434
+ model/model/layers/20/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
435
+ model/model/layers/20/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
436
+ model/model/layers/21/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
437
+ model/model/layers/21/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
438
+ model/model/layers/21/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
439
+ model/model/layers/21/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
440
+ model/model/layers/21/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
441
+ model/model/layers/21/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
442
+ model/model/layers/21/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
443
+ model/model/layers/21/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
444
+ model/model/layers/21/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
445
+ model/model/layers/21/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
446
+ model/model/layers/21/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
447
+ model/model/layers/21/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
448
+ model/model/layers/21/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
449
+ model/model/layers/21/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
450
+ model/model/layers/21/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
451
+ model/model/layers/21/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
452
+ model/model/layers/21/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
453
+ model/model/layers/21/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
454
+ model/model/layers/21/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
455
+ model/model/layers/21/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
456
+ model/model/layers/21/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
457
+ model/model/layers/21/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
458
+ model/model/layers/21/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
459
+ model/model/layers/21/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
460
+ model/model/layers/21/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
461
+ model/model/layers/21/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
462
+ model/model/layers/21/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
463
+ model/model/layers/21/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
464
+ model/model/layers/22/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
465
+ model/model/layers/22/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
466
+ model/model/layers/22/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
467
+ model/model/layers/22/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
468
+ model/model/layers/22/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
469
+ model/model/layers/22/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
470
+ model/model/layers/22/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
471
+ model/model/layers/22/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
472
+ model/model/layers/22/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
473
+ model/model/layers/22/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
474
+ model/model/layers/22/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
475
+ model/model/layers/22/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
476
+ model/model/layers/22/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
477
+ model/model/layers/22/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
478
+ model/model/layers/22/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
479
+ model/model/layers/22/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
480
+ model/model/layers/22/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
481
+ model/model/layers/22/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
482
+ model/model/layers/22/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
483
+ model/model/layers/22/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
484
+ model/model/layers/22/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
485
+ model/model/layers/22/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
486
+ model/model/layers/22/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
487
+ model/model/layers/22/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
488
+ model/model/layers/22/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
489
+ model/model/layers/22/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
490
+ model/model/layers/22/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
491
+ model/model/layers/22/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
492
+ model/model/layers/23/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
493
+ model/model/layers/23/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
494
+ model/model/layers/23/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
495
+ model/model/layers/23/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
496
+ model/model/layers/23/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
497
+ model/model/layers/23/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
498
+ model/model/layers/23/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
499
+ model/model/layers/23/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
500
+ model/model/layers/23/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
501
+ model/model/layers/23/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
502
+ model/model/layers/23/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
503
+ model/model/layers/23/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
504
+ model/model/layers/23/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
505
+ model/model/layers/23/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
506
+ model/model/layers/23/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
507
+ model/model/layers/23/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
508
+ model/model/layers/23/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
509
+ model/model/layers/23/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
510
+ model/model/layers/23/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
511
+ model/model/layers/23/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
512
+ model/model/layers/23/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
513
+ model/model/layers/23/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
514
+ model/model/layers/23/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
515
+ model/model/layers/23/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
516
+ model/model/layers/23/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
517
+ model/model/layers/23/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
518
+ model/model/layers/23/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
519
+ model/model/layers/23/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
520
+ model/model/layers/24/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
521
+ model/model/layers/24/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
522
+ model/model/layers/24/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
523
+ model/model/layers/24/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
524
+ model/model/layers/24/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
525
+ model/model/layers/24/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
526
+ model/model/layers/24/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
527
+ model/model/layers/24/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
528
+ model/model/layers/24/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
529
+ model/model/layers/24/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
530
+ model/model/layers/24/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
531
+ model/model/layers/24/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
532
+ model/model/layers/24/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
533
+ model/model/layers/24/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
534
+ model/model/layers/24/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
535
+ model/model/layers/24/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
536
+ model/model/layers/24/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
537
+ model/model/layers/24/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
538
+ model/model/layers/24/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
539
+ model/model/layers/24/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
540
+ model/model/layers/24/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
541
+ model/model/layers/24/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
542
+ model/model/layers/24/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
543
+ model/model/layers/24/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
544
+ model/model/layers/24/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
545
+ model/model/layers/24/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
546
+ model/model/layers/24/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
547
+ model/model/layers/24/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
548
+ model/model/layers/25/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
549
+ model/model/layers/25/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
550
+ model/model/layers/25/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
551
+ model/model/layers/25/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
552
+ model/model/layers/25/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
553
+ model/model/layers/25/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
554
+ model/model/layers/25/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
555
+ model/model/layers/25/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
556
+ model/model/layers/25/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
557
+ model/model/layers/25/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
558
+ model/model/layers/25/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
559
+ model/model/layers/25/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
560
+ model/model/layers/25/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
561
+ model/model/layers/25/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
562
+ model/model/layers/25/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
563
+ model/model/layers/25/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
564
+ model/model/layers/25/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
565
+ model/model/layers/25/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
566
+ model/model/layers/25/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
567
+ model/model/layers/25/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
568
+ model/model/layers/25/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
569
+ model/model/layers/25/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
570
+ model/model/layers/25/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
571
+ model/model/layers/25/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
572
+ model/model/layers/25/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
573
+ model/model/layers/25/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
574
+ model/model/layers/25/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
575
+ model/model/layers/25/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
576
+ model/model/layers/26/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
577
+ model/model/layers/26/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
578
+ model/model/layers/26/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
579
+ model/model/layers/26/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
580
+ model/model/layers/26/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
581
+ model/model/layers/26/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
582
+ model/model/layers/26/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
583
+ model/model/layers/26/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
584
+ model/model/layers/26/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
585
+ model/model/layers/26/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
586
+ model/model/layers/26/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
587
+ model/model/layers/26/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
588
+ model/model/layers/26/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
589
+ model/model/layers/26/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
590
+ model/model/layers/26/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
591
+ model/model/layers/26/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
592
+ model/model/layers/26/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
593
+ model/model/layers/26/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
594
+ model/model/layers/26/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
595
+ model/model/layers/26/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
596
+ model/model/layers/26/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
597
+ model/model/layers/26/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
598
+ model/model/layers/26/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
599
+ model/model/layers/26/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
600
+ model/model/layers/26/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
601
+ model/model/layers/26/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
602
+ model/model/layers/26/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
603
+ model/model/layers/26/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
604
+ model/model/layers/27/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
605
+ model/model/layers/27/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
606
+ model/model/layers/27/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
607
+ model/model/layers/27/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
608
+ model/model/layers/27/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
609
+ model/model/layers/27/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
610
+ model/model/layers/27/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
611
+ model/model/layers/27/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
612
+ model/model/layers/27/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
613
+ model/model/layers/27/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
614
+ model/model/layers/27/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
615
+ model/model/layers/27/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
616
+ model/model/layers/27/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
617
+ model/model/layers/27/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
618
+ model/model/layers/27/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
619
+ model/model/layers/27/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
620
+ model/model/layers/27/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
621
+ model/model/layers/27/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
622
+ model/model/layers/27/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
623
+ model/model/layers/27/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
624
+ model/model/layers/27/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
625
+ model/model/layers/27/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
626
+ model/model/layers/27/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
627
+ model/model/layers/27/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
628
+ model/model/layers/27/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
629
+ model/model/layers/27/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
630
+ model/model/layers/27/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
631
+ model/model/layers/27/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
632
+ model/model/layers/28/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
633
+ model/model/layers/28/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
634
+ model/model/layers/28/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
635
+ model/model/layers/28/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
636
+ model/model/layers/28/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
637
+ model/model/layers/28/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
638
+ model/model/layers/28/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
639
+ model/model/layers/28/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
640
+ model/model/layers/28/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
641
+ model/model/layers/28/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
642
+ model/model/layers/28/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
643
+ model/model/layers/28/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
644
+ model/model/layers/28/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
645
+ model/model/layers/28/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
646
+ model/model/layers/28/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
647
+ model/model/layers/28/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
648
+ model/model/layers/28/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
649
+ model/model/layers/28/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
650
+ model/model/layers/28/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
651
+ model/model/layers/28/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
652
+ model/model/layers/28/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
653
+ model/model/layers/28/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
654
+ model/model/layers/28/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
655
+ model/model/layers/28/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
656
+ model/model/layers/28/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
657
+ model/model/layers/28/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
658
+ model/model/layers/28/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
659
+ model/model/layers/28/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
660
+ model/model/layers/29/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
661
+ model/model/layers/29/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
662
+ model/model/layers/29/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
663
+ model/model/layers/29/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
664
+ model/model/layers/29/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
665
+ model/model/layers/29/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
666
+ model/model/layers/29/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
667
+ model/model/layers/29/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
668
+ model/model/layers/29/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
669
+ model/model/layers/29/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
670
+ model/model/layers/29/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
671
+ model/model/layers/29/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
672
+ model/model/layers/29/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
673
+ model/model/layers/29/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
674
+ model/model/layers/29/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
675
+ model/model/layers/29/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
676
+ model/model/layers/29/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
677
+ model/model/layers/29/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
678
+ model/model/layers/29/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
679
+ model/model/layers/29/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
680
+ model/model/layers/29/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
681
+ model/model/layers/29/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
682
+ model/model/layers/29/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
683
+ model/model/layers/29/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
684
+ model/model/layers/29/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
685
+ model/model/layers/29/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
686
+ model/model/layers/29/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
687
+ model/model/layers/29/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
688
+ model/model/layers/3/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
689
+ model/model/layers/3/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
690
+ model/model/layers/3/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
691
+ model/model/layers/3/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
692
+ model/model/layers/3/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
693
+ model/model/layers/3/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
694
+ model/model/layers/3/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
695
+ model/model/layers/3/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
696
+ model/model/layers/3/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
697
+ model/model/layers/3/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
698
+ model/model/layers/3/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
699
+ model/model/layers/3/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
700
+ model/model/layers/3/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
701
+ model/model/layers/3/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
702
+ model/model/layers/3/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
703
+ model/model/layers/3/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
704
+ model/model/layers/3/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
705
+ model/model/layers/3/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
706
+ model/model/layers/3/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
707
+ model/model/layers/3/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
708
+ model/model/layers/3/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
709
+ model/model/layers/3/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
710
+ model/model/layers/3/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
711
+ model/model/layers/3/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
712
+ model/model/layers/3/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
713
+ model/model/layers/3/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
714
+ model/model/layers/3/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
715
+ model/model/layers/3/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
716
+ model/model/layers/30/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
717
+ model/model/layers/30/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
718
+ model/model/layers/30/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
719
+ model/model/layers/30/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
720
+ model/model/layers/30/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
721
+ model/model/layers/30/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
722
+ model/model/layers/30/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
723
+ model/model/layers/30/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
724
+ model/model/layers/30/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
725
+ model/model/layers/30/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
726
+ model/model/layers/30/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
727
+ model/model/layers/30/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
728
+ model/model/layers/30/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
729
+ model/model/layers/30/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
730
+ model/model/layers/30/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
731
+ model/model/layers/30/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
732
+ model/model/layers/30/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
733
+ model/model/layers/30/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
734
+ model/model/layers/30/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
735
+ model/model/layers/30/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
736
+ model/model/layers/30/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
737
+ model/model/layers/30/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
738
+ model/model/layers/30/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
739
+ model/model/layers/30/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
740
+ model/model/layers/30/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
741
+ model/model/layers/30/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
742
+ model/model/layers/30/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
743
+ model/model/layers/30/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
744
+ model/model/layers/31/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
745
+ model/model/layers/31/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
746
+ model/model/layers/31/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
747
+ model/model/layers/31/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
748
+ model/model/layers/31/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
749
+ model/model/layers/31/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
750
+ model/model/layers/31/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
751
+ model/model/layers/31/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
752
+ model/model/layers/31/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
753
+ model/model/layers/31/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
754
+ model/model/layers/31/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
755
+ model/model/layers/31/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
756
+ model/model/layers/31/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
757
+ model/model/layers/31/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
758
+ model/model/layers/31/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
759
+ model/model/layers/31/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
760
+ model/model/layers/31/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
761
+ model/model/layers/31/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
762
+ model/model/layers/31/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
763
+ model/model/layers/31/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
764
+ model/model/layers/31/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
765
+ model/model/layers/31/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
766
+ model/model/layers/31/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
767
+ model/model/layers/31/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
768
+ model/model/layers/31/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
769
+ model/model/layers/31/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
770
+ model/model/layers/31/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
771
+ model/model/layers/31/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
772
+ model/model/layers/4/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
773
+ model/model/layers/4/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
774
+ model/model/layers/4/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
775
+ model/model/layers/4/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
776
+ model/model/layers/4/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
777
+ model/model/layers/4/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
778
+ model/model/layers/4/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
779
+ model/model/layers/4/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
780
+ model/model/layers/4/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
781
+ model/model/layers/4/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
782
+ model/model/layers/4/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
783
+ model/model/layers/4/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
784
+ model/model/layers/4/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
785
+ model/model/layers/4/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
786
+ model/model/layers/4/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
787
+ model/model/layers/4/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
788
+ model/model/layers/4/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
789
+ model/model/layers/4/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
790
+ model/model/layers/4/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
791
+ model/model/layers/4/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
792
+ model/model/layers/4/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
793
+ model/model/layers/4/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
794
+ model/model/layers/4/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
795
+ model/model/layers/4/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
796
+ model/model/layers/4/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
797
+ model/model/layers/4/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
798
+ model/model/layers/4/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
799
+ model/model/layers/4/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
800
+ model/model/layers/5/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
801
+ model/model/layers/5/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
802
+ model/model/layers/5/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
803
+ model/model/layers/5/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
804
+ model/model/layers/5/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
805
+ model/model/layers/5/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
806
+ model/model/layers/5/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
807
+ model/model/layers/5/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
808
+ model/model/layers/5/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
809
+ model/model/layers/5/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
810
+ model/model/layers/5/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
811
+ model/model/layers/5/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
812
+ model/model/layers/5/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
813
+ model/model/layers/5/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
814
+ model/model/layers/5/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
815
+ model/model/layers/5/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
816
+ model/model/layers/5/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
817
+ model/model/layers/5/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
818
+ model/model/layers/5/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
819
+ model/model/layers/5/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
820
+ model/model/layers/5/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
821
+ model/model/layers/5/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
822
+ model/model/layers/5/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
823
+ model/model/layers/5/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
824
+ model/model/layers/5/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
825
+ model/model/layers/5/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
826
+ model/model/layers/5/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
827
+ model/model/layers/5/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
828
+ model/model/layers/6/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
829
+ model/model/layers/6/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
830
+ model/model/layers/6/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
831
+ model/model/layers/6/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
832
+ model/model/layers/6/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
833
+ model/model/layers/6/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
834
+ model/model/layers/6/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
835
+ model/model/layers/6/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
836
+ model/model/layers/6/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
837
+ model/model/layers/6/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
838
+ model/model/layers/6/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
839
+ model/model/layers/6/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
840
+ model/model/layers/6/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
841
+ model/model/layers/6/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
842
+ model/model/layers/6/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
843
+ model/model/layers/6/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
844
+ model/model/layers/6/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
845
+ model/model/layers/6/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
846
+ model/model/layers/6/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
847
+ model/model/layers/6/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
848
+ model/model/layers/6/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
849
+ model/model/layers/6/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
850
+ model/model/layers/6/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
851
+ model/model/layers/6/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
852
+ model/model/layers/6/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
853
+ model/model/layers/6/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
854
+ model/model/layers/6/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
855
+ model/model/layers/6/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
856
+ model/model/layers/7/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
857
+ model/model/layers/7/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
858
+ model/model/layers/7/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
859
+ model/model/layers/7/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
860
+ model/model/layers/7/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
861
+ model/model/layers/7/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
862
+ model/model/layers/7/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
863
+ model/model/layers/7/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
864
+ model/model/layers/7/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
865
+ model/model/layers/7/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
866
+ model/model/layers/7/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
867
+ model/model/layers/7/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
868
+ model/model/layers/7/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
869
+ model/model/layers/7/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
870
+ model/model/layers/7/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
871
+ model/model/layers/7/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
872
+ model/model/layers/7/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
873
+ model/model/layers/7/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
874
+ model/model/layers/7/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
875
+ model/model/layers/7/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
876
+ model/model/layers/7/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
877
+ model/model/layers/7/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
878
+ model/model/layers/7/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
879
+ model/model/layers/7/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
880
+ model/model/layers/7/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
881
+ model/model/layers/7/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
882
+ model/model/layers/7/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
883
+ model/model/layers/7/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
884
+ model/model/layers/8/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
885
+ model/model/layers/8/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
886
+ model/model/layers/8/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
887
+ model/model/layers/8/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
888
+ model/model/layers/8/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
889
+ model/model/layers/8/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
890
+ model/model/layers/8/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
891
+ model/model/layers/8/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
892
+ model/model/layers/8/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
893
+ model/model/layers/8/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
894
+ model/model/layers/8/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
895
+ model/model/layers/8/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
896
+ model/model/layers/8/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
897
+ model/model/layers/8/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
898
+ model/model/layers/8/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
899
+ model/model/layers/8/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
900
+ model/model/layers/8/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
901
+ model/model/layers/8/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
902
+ model/model/layers/8/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
903
+ model/model/layers/8/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
904
+ model/model/layers/8/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
905
+ model/model/layers/8/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
906
+ model/model/layers/8/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
907
+ model/model/layers/8/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
908
+ model/model/layers/8/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
909
+ model/model/layers/8/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
910
+ model/model/layers/8/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
911
+ model/model/layers/8/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
912
+ model/model/layers/9/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
913
+ model/model/layers/9/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
914
+ model/model/layers/9/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
915
+ model/model/layers/9/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
916
+ model/model/layers/9/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
917
+ model/model/layers/9/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
918
+ model/model/layers/9/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
919
+ model/model/layers/9/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
920
+ model/model/layers/9/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
921
+ model/model/layers/9/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
922
+ model/model/layers/9/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
923
+ model/model/layers/9/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
924
+ model/model/layers/9/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
925
+ model/model/layers/9/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
926
+ model/model/layers/9/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
927
+ model/model/layers/9/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
928
+ model/model/layers/9/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
929
+ model/model/layers/9/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
930
+ model/model/layers/9/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
931
+ model/model/layers/9/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
932
+ model/model/layers/9/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
933
+ model/model/layers/9/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
934
+ model/model/layers/9/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
935
+ model/model/layers/9/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
936
+ model/model/layers/9/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
937
+ model/model/layers/9/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
938
+ model/model/layers/9/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
939
+ model/model/layers/9/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
940
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: easydel
3
+ pipeline_tag: text-generation
4
+ tags:
5
+ - easydel
6
+ - jax
7
+ - "llama"
8
+ - "CausalLM"
9
+ - "vanilla"
10
+ ---
11
+
12
+ <p align="center">
13
+ <img alt="easydel" src="https://raw.githubusercontent.com/erfanzar/easydel/main/images/easydel-logo-with-text.png">
14
+ </p>
15
+
16
+ <h1 align="center">meta-llama/Llama-3.1-8B-Instruct</h1>
17
+
18
+ <div align="center">
19
+ EasyDeL checkpoint converted from meta-llama/Llama-3.1-8B-Instruct.
20
+ </div>
21
+
22
+ ## Overview
23
+
24
+ This checkpoint is intended to be loaded with EasyDeL on JAX (CPU/GPU/TPU). It supports sharded loading with `auto_shard_model=True` and configurable precision via `dtype`, `param_dtype`, and `precision`.
25
+
26
+ ## Quickstart
27
+
28
+ ```python
29
+ import easydel as ed
30
+ from jax import numpy as jnp, lax
31
+
32
+ repo_id = "EasyDeL/Llama-3.1-8B-Instruct"
33
+
34
+ dtype = jnp.bfloat16 # try jnp.float16 on many GPUs
35
+
36
+ model = ed.AutoEasyDeLModelForCausalLM.from_pretrained(
37
+ repo_id,
38
+ dtype=dtype,
39
+ param_dtype=dtype,
40
+ precision=lax.Precision("fastest"),
41
+ sharding_axis_names=("dp", "fsdp", "ep", "tp", "sp"),
42
+ sharding_axis_dims=(1, -1, 1, 1, 1),
43
+ config_kwargs=ed.EasyDeLBaseConfigDict(
44
+ attn_dtype=dtype,
45
+ attn_mechanism=ed.AttentionMechanisms.VANILLA,
46
+ fsdp_is_ep_bound=True,
47
+ sp_is_ep_bound=True,
48
+ moe_method=ed.MoEMethods.FUSED_MOE,
49
+ ),
50
+ auto_shard_model=True,
51
+ partition_axis=ed.PartitionAxis(),
52
+ )
53
+ ```
54
+
55
+ If the repository only provides PyTorch weights, pass `from_torch=True` to `from_pretrained(...)`.
56
+
57
+ ## Sharding & Parallelism (Multi-Device)
58
+
59
+ EasyDeL can scale to multiple devices by creating a logical device mesh. Most EasyDeL loaders use a 5D mesh:
60
+
61
+ - `dp`: data parallel (replicated parameters, different batch shards)
62
+ - `fsdp`: parameter sharding (memory saver; often the biggest axis)
63
+ - `ep`: expert parallel (MoE; keep `1` for non-MoE models)
64
+ - `tp`: tensor parallel (splits large matmuls)
65
+ - `sp`: sequence parallel (splits sequence dimension)
66
+
67
+ Use `sharding_axis_names=("dp","fsdp","ep","tp","sp")` and choose `sharding_axis_dims` so that their product equals your device count.
68
+ You can use `-1` in `sharding_axis_dims` to let EasyDeL infer the remaining dimension.
69
+
70
+ <details>
71
+ <summary>Example sharding configs</summary>
72
+
73
+ ```python
74
+ # 8 devices, pure FSDP
75
+ sharding_axis_dims = (1, 8, 1, 1, 1)
76
+
77
+ # 8 devices, 2-way DP x 4-way FSDP
78
+ sharding_axis_dims = (2, 4, 1, 1, 1)
79
+
80
+ # 8 devices, 4-way FSDP x 2-way TP
81
+ sharding_axis_dims = (1, 4, 1, 2, 1)
82
+ ```
83
+ </details>
84
+
85
+ ## Using via `eLargeModel` (ELM)
86
+
87
+ `eLargeModel` is a higher-level interface that wires together loading, sharding, training, and eSurge inference from a single config.
88
+
89
+ ```python
90
+ from easydel import eLargeModel
91
+
92
+ repo_id = "EasyDeL/Llama-3.1-8B-Instruct"
93
+
94
+ elm = eLargeModel.from_pretrained(repo_id) # task is auto-detected
95
+ elm.set_dtype("bf16")
96
+ elm.set_sharding(axis_names=("dp", "fsdp", "ep", "tp", "sp"), axis_dims=(1, -1, 1, 1, 1))
97
+
98
+ model = elm.build_model()
99
+ # Optional: build an inference engine
100
+ # engine = elm.build_esurge()
101
+ ```
102
+
103
+ <details>
104
+ <summary>ELM YAML config example</summary>
105
+
106
+ ```yaml
107
+ model:
108
+ name_or_path: "EasyDeL/Llama-3.1-8B-Instruct"
109
+
110
+ loader:
111
+ dtype: bf16
112
+ param_dtype: bf16
113
+
114
+ sharding:
115
+ axis_dims: [1, -1, 1, 1, 1]
116
+ auto_shard_model: true
117
+ ```
118
+ </details>
119
+
120
+ ## Features
121
+
122
+ **EasyDeL:**
123
+ - JAX native implementation and sharded execution
124
+ - Configurable attention backends via `AttentionMechanisms.*`
125
+ - Precision control via `dtype`, `param_dtype`, and `precision`
126
+
127
+ ## Installation
128
+
129
+ ```bash
130
+ pip install easydel
131
+ ```
132
+
133
+ ## Links
134
+
135
+ - EasyDeL GitHub: https://github.com/erfanzar/EasyDeL
136
+ - Docs: https://easydel.readthedocs.io/en/latest/
137
+
138
+ ## Supported Tasks
139
+
140
+ - CausalLM
141
+
142
+ ## Limitations
143
+
144
+ - Refer to the original model card for training data, evaluation, and intended use.
145
+
146
+ ## License
147
+
148
+ EasyDeL is released under the Apache-2.0 license. The license for this model's weights may differ; please consult the original repository.
149
+
150
+ ## Citation
151
+
152
+ ```bibtex
153
+ @misc{Zare Chavoshi_2023,
154
+ title={EasyDeL: An open-source library for enhancing and streamlining the training process of machine learning models},
155
+ url={https://github.com/erfanzar/EasyDeL},
156
+ author={Zare Chavoshi, Erfan},
157
+ year={2023}
158
+ }
159
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
checkpoint_metadata.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "timestamp": "2025-12-28T15:52:01.245819",
3
+ "custom_metadata": {
4
+ "step": 0
5
+ }
6
+ }
config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_external_rope_config_kwargs": {},
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_mechanism": "vanilla",
9
+ "backend": null,
10
+ "bits": null,
11
+ "blocksize_b": 1,
12
+ "blocksize_k": 128,
13
+ "blocksize_q": 128,
14
+ "bos_token_id": 128000,
15
+ "decode_attn_mechanism": null,
16
+ "dtype": "bfloat16",
17
+ "easy_method": "train",
18
+ "embd_pdrop": 0.0,
19
+ "eos_token_id": [
20
+ 128001,
21
+ 128008,
22
+ 128009
23
+ ],
24
+ "fcm_max_ratio": -1,
25
+ "fcm_min_ratio": -1,
26
+ "flash_attention_backward_pass_impl": "triton",
27
+ "fsdp_is_ep_bound": true,
28
+ "gradient_checkpointing": "",
29
+ "gradient_checkpointing_targets": null,
30
+ "hardware_abstraction": false,
31
+ "head_dim": 128,
32
+ "hidden_act": "silu",
33
+ "hidden_size": 4096,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 14336,
36
+ "kv_cache_quantization_config": null,
37
+ "kv_cache_sharding_sequence_axis_name": "sp",
38
+ "layer_types": [
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention"
71
+ ],
72
+ "max_position_embeddings": 131072,
73
+ "mlp_bias": false,
74
+ "model_type": "llama",
75
+ "moe_force_xla_gmm": false,
76
+ "moe_method": "fused_moe",
77
+ "moe_tiling_size_batch": 4,
78
+ "moe_tiling_size_dim": 128,
79
+ "moe_tiling_size_seqlen": 128,
80
+ "num_attention_heads": 32,
81
+ "num_hidden_layers": 32,
82
+ "num_key_value_heads": 8,
83
+ "number_rep_kv": 1,
84
+ "operation_configs": null,
85
+ "pallas_k_block_size": 128,
86
+ "pallas_m_block_size": 128,
87
+ "pallas_n_block_size": 128,
88
+ "partition_axis": {
89
+ "attention_dim_axis": null,
90
+ "attention_kv_dim_axis": null,
91
+ "batch_axis": [
92
+ "fsdp",
93
+ "dp"
94
+ ],
95
+ "bias_head_sequence_axis": null,
96
+ "bias_key_sequence_axis": null,
97
+ "data_parallel_axis": "dp",
98
+ "decode_attention_dim_axis": null,
99
+ "decode_attention_kv_dim_axis": null,
100
+ "decode_batch_axis": [
101
+ "fsdp",
102
+ "dp"
103
+ ],
104
+ "decode_head_axis": "tp",
105
+ "decode_key_sequence_axis": "sp",
106
+ "decode_kv_head_axis": "tp",
107
+ "decode_query_sequence_axis": null,
108
+ "expert_axis": "ep",
109
+ "expert_gate_axis": null,
110
+ "expert_parallel_axis": "ep",
111
+ "fully_sharded_data_parallel_axis": "fsdp",
112
+ "head_axis": "tp",
113
+ "hidden_state_axis": "tp",
114
+ "key_sequence_axis": "sp",
115
+ "kv_head_axis": "tp",
116
+ "mlp_intermediate_axis": "tp",
117
+ "query_sequence_axis": "sp",
118
+ "sequence_axis": "sp",
119
+ "sequence_parallel_axis": "sp",
120
+ "tensor_parallel_axis": "tp",
121
+ "vocab_axis": "tp"
122
+ },
123
+ "platform": null,
124
+ "precompute_masks": true,
125
+ "pretraining_tp": 1,
126
+ "quantization_config": null,
127
+ "resid_pdrop": 0.0,
128
+ "rms_norm_eps": 1e-05,
129
+ "rope_scaling": {
130
+ "factor": 8.0,
131
+ "high_freq_factor": 4.0,
132
+ "low_freq_factor": 1.0,
133
+ "original_max_position_embeddings": 8192,
134
+ "rope_type": "llama3"
135
+ },
136
+ "rope_theta": 500000.0,
137
+ "scan_attention_layers": false,
138
+ "scan_layers": false,
139
+ "scan_mlp_chunk_size": 1024,
140
+ "scan_ring_attention": true,
141
+ "sequence_axis_name": "sp",
142
+ "sharding_axis_dims": [
143
+ 1,
144
+ -1,
145
+ 1,
146
+ 1,
147
+ 1
148
+ ],
149
+ "sharding_axis_names": [
150
+ "dp",
151
+ "fsdp",
152
+ "ep",
153
+ "tp",
154
+ "sp"
155
+ ],
156
+ "sharding_dcn_axis_dims": null,
157
+ "sp_is_ep_bound": true,
158
+ "tie_word_embeddings": false,
159
+ "transformers_version": "4.57.3",
160
+ "use_cache": true,
161
+ "use_expert_tensor_mode": false,
162
+ "use_ring_of_experts": false,
163
+ "use_scan_mlp": false,
164
+ "use_sharded_kv_caching": false,
165
+ "use_sharding_constraint": false,
166
+ "vocab_size": 128256
167
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.57.3",
12
+ "trust_remote_code": false
13
+ }
model/lm_head/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1024,128256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,128256],"zarr_format":2}
model/lm_head/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff526baf11850cf595c631b99fd8a31180ec54288c1fb7438f2755fda739222e
3
+ size 202298140
model/lm_head/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98bd980b7cde00dc6d09bf64bf6da481624ad9d4e5176bf79cf27e2f73fe9fea
3
+ size 202287233
model/lm_head/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec3f1811db4ba9be2bb2bd8a89179596fceb0d65b590935048eff8fa079a3bc
3
+ size 202332628
model/lm_head/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d94e762aa58f616a3cab02bbf3cf6baa5ba9aebd6272925e34720db52f5ef9
3
+ size 202245405
model/model/embed_tokens/embedding/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[32064,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[128256,4096],"zarr_format":2}
model/model/embed_tokens/embedding/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e4d3731d108c6e7ec59162aa31a1e08e5d0beca4cbbc08c2de302760993312
3
+ size 203771352
model/model/embed_tokens/embedding/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f20bc86bc6e168d46126e3ea44bd23a01e18bc2ba832901a5e2b39c32332cf1
3
+ size 203200906
model/model/embed_tokens/embedding/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a132eeec176eb2937291c4dd6ce9dbe468eda3e7a8a142198e0a9888a0505285
3
+ size 203119838
model/model/embed_tokens/embedding/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb98143be2f821539ae442e2450bd7797aae4d86b7e7103bc669a95a1c760c85
3
+ size 203146569
model/model/layers/0/input_layernorm/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}
model/model/layers/0/input_layernorm/kernel/0 ADDED
Binary file (6.6 kB). View file
 
model/model/layers/0/mlp/down_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[14336,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[14336,4096],"zarr_format":2}
model/model/layers/0/mlp/down_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34a8178afc0ff52206aedf8728531af9932f547cc3bdc14fa3277bf63f55bbc
3
+ size 22767224
model/model/layers/0/mlp/down_proj/kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0fd1f6d6ddca4368bf043b7b7415ced5297c5c83338ba74856ce6c18a62d3ea
3
+ size 22765988
model/model/layers/0/mlp/down_proj/kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031e663c4009a81e33be3f432a057ca5cf0979c8de2f2578b8aa1abe31890d07
3
+ size 22765326
model/model/layers/0/mlp/down_proj/kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55140d450edc670be1b1ffcf167041b77e8f0d3c7af483f7620da9be0d7b44bd
3
+ size 22768556
model/model/layers/0/mlp/gate_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1024,14336],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,14336],"zarr_format":2}
model/model/layers/0/mlp/gate_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2476d55c94a91142c49c7500b69c90a0d71159fed3772f55904baec88f74716
3
+ size 22754790
model/model/layers/0/mlp/gate_proj/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0414858e729b552dd8ff1b2500b397ae499ed4ccbfd20d8fba6db7279bc6f1
3
+ size 22752200
model/model/layers/0/mlp/gate_proj/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b25e6fc7f4d5643a608e0b3d8434ef49c2949991c6179afaf0fefa617b1bf18
3
+ size 22751594
model/model/layers/0/mlp/gate_proj/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1406e9dffe05c7c657e1424eb6f697b93898fcfa5e645890e0f2b82e80f1b5
3
+ size 22747920
model/model/layers/0/mlp/up_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1024,14336],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,14336],"zarr_format":2}
model/model/layers/0/mlp/up_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:697dcddd580ebd2770467cf9ad3f6d2e15ce1ac91aa6cb813f02ec2ecf319e15
3
+ size 22770807
model/model/layers/0/mlp/up_proj/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca372df4611861ead3d13590ee4fb876c038f4d711fd1dcd141b18e9a326942
3
+ size 22768893
model/model/layers/0/mlp/up_proj/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8838efbd4f90cd8094a2f22b80cb12a2524e82554977e931d699c35cc045d7e0
3
+ size 22768999
model/model/layers/0/mlp/up_proj/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037685c9191502fe85b4742d973477aa57e9110c077a0a3cbae0f0fffd03dbc1
3
+ size 22768005
model/model/layers/0/post_attention_layernorm/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}
model/model/layers/0/post_attention_layernorm/kernel/0 ADDED
Binary file (3.28 kB). View file
 
model/model/layers/0/self_attn/k_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1024,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,1024],"zarr_format":2}
model/model/layers/0/self_attn/k_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5293e3dd1b7bbe3b50adce07e213e077af7c16eb70d80595b61d1c0b4c9b59be
3
+ size 1716588
model/model/layers/0/self_attn/k_proj/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:838c710e4c6cb1c1f52d359d1c3569df3679ed1094e5a2ed6b3bfdb2707355e8
3
+ size 1717484
model/model/layers/0/self_attn/k_proj/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d06eae5386e95b789952ed60c6671921988ceffa57ab195f2b22bf0b095cf7d
3
+ size 1717297
model/model/layers/0/self_attn/k_proj/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52089f971e56531234a5ed2b3e1314bb04c16c088e129f6382b831ca0fe36690
3
+ size 1715686
model/model/layers/0/self_attn/o_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[4096,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
model/model/layers/0/self_attn/o_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22307eebfaa1037eee9e28d15803c9f3da8d9d7a560abe592c90794b004e10c0
3
+ size 6552752
model/model/layers/0/self_attn/o_proj/kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d044796bf11e7c923a22d07556a4fcd603587153626c4b8605b20ecaade533e2
3
+ size 6552313
model/model/layers/0/self_attn/o_proj/kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb05c9ca6c4a3748c26bc96948eea493a30b48a9166975200813a5b12c644a3
3
+ size 6551390
model/model/layers/0/self_attn/o_proj/kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac206f11c57c67f31180310a96d5aa1482dc1a3988c24fa5b46227a5b086208c
3
+ size 6553091
model/model/layers/0/self_attn/q_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[1024,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}
model/model/layers/0/self_attn/q_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f82d5a294ffb39c19bedb4a8593d6d370cdd8100521ed7e62fd7c1748ae09ba
3
+ size 6896131
model/model/layers/0/self_attn/q_proj/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9074c0e24f8468732290184e12ff5e494a6e3081d9f481621c2696ca0fb0ef8
3
+ size 6899117
model/model/layers/0/self_attn/q_proj/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0053a27b2be8907b3f49457977f7043cfee271b37f82a9e0310e10038aa6d2e2
3
+ size 6895292
model/model/layers/0/self_attn/q_proj/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0dcc6218c8b5ea403dd21be06a09afc5467f516cfa05e93bbb87634c7d16cf6
3
+ size 6887653