erfanzar commited on
Commit
ecb5df3
·
verified ·
1 Parent(s): 915ac5e

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 +453 -0
  2. README.md +159 -0
  3. chat_template.jinja +93 -0
  4. checkpoint_metadata.json +6 -0
  5. config.json +151 -0
  6. generation_config.json +13 -0
  7. model/model/embed_tokens/embedding/.zarray +1 -0
  8. model/model/embed_tokens/embedding/0.0 +3 -0
  9. model/model/embed_tokens/embedding/1.0 +3 -0
  10. model/model/embed_tokens/embedding/2.0 +3 -0
  11. model/model/embed_tokens/embedding/3.0 +3 -0
  12. model/model/layers/0/input_layernorm/kernel/.zarray +1 -0
  13. model/model/layers/0/input_layernorm/kernel/0 +0 -0
  14. model/model/layers/0/mlp/down_proj/kernel/.zarray +1 -0
  15. model/model/layers/0/mlp/down_proj/kernel/0.0 +3 -0
  16. model/model/layers/0/mlp/down_proj/kernel/0.1 +3 -0
  17. model/model/layers/0/mlp/down_proj/kernel/0.2 +3 -0
  18. model/model/layers/0/mlp/down_proj/kernel/0.3 +3 -0
  19. model/model/layers/0/mlp/gate_proj/kernel/.zarray +1 -0
  20. model/model/layers/0/mlp/gate_proj/kernel/0.0 +3 -0
  21. model/model/layers/0/mlp/gate_proj/kernel/1.0 +3 -0
  22. model/model/layers/0/mlp/gate_proj/kernel/2.0 +3 -0
  23. model/model/layers/0/mlp/gate_proj/kernel/3.0 +3 -0
  24. model/model/layers/0/mlp/up_proj/kernel/.zarray +1 -0
  25. model/model/layers/0/mlp/up_proj/kernel/0.0 +3 -0
  26. model/model/layers/0/mlp/up_proj/kernel/1.0 +3 -0
  27. model/model/layers/0/mlp/up_proj/kernel/2.0 +3 -0
  28. model/model/layers/0/mlp/up_proj/kernel/3.0 +3 -0
  29. model/model/layers/0/post_attention_layernorm/kernel/.zarray +1 -0
  30. model/model/layers/0/post_attention_layernorm/kernel/0 +0 -0
  31. model/model/layers/0/self_attn/k_proj/kernel/.zarray +1 -0
  32. model/model/layers/0/self_attn/k_proj/kernel/0.0 +3 -0
  33. model/model/layers/0/self_attn/k_proj/kernel/1.0 +3 -0
  34. model/model/layers/0/self_attn/k_proj/kernel/2.0 +3 -0
  35. model/model/layers/0/self_attn/k_proj/kernel/3.0 +3 -0
  36. model/model/layers/0/self_attn/o_proj/kernel/.zarray +1 -0
  37. model/model/layers/0/self_attn/o_proj/kernel/0.0 +3 -0
  38. model/model/layers/0/self_attn/o_proj/kernel/0.1 +3 -0
  39. model/model/layers/0/self_attn/o_proj/kernel/0.2 +3 -0
  40. model/model/layers/0/self_attn/o_proj/kernel/0.3 +3 -0
  41. model/model/layers/0/self_attn/q_proj/kernel/.zarray +1 -0
  42. model/model/layers/0/self_attn/q_proj/kernel/0.0 +3 -0
  43. model/model/layers/0/self_attn/q_proj/kernel/1.0 +3 -0
  44. model/model/layers/0/self_attn/q_proj/kernel/2.0 +3 -0
  45. model/model/layers/0/self_attn/q_proj/kernel/3.0 +3 -0
  46. model/model/layers/0/self_attn/v_proj/kernel/.zarray +1 -0
  47. model/model/layers/0/self_attn/v_proj/kernel/0.0 +3 -0
  48. model/model/layers/0/self_attn/v_proj/kernel/1.0 +3 -0
  49. model/model/layers/0/self_attn/v_proj/kernel/2.0 +3 -0
  50. model/model/layers/0/self_attn/v_proj/kernel/3.0 +3 -0
.gitattributes CHANGED
@@ -33,3 +33,456 @@ 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/model/embed_tokens/embedding/0.0 filter=lfs diff=lfs merge=lfs -text
37
+ model/model/embed_tokens/embedding/1.0 filter=lfs diff=lfs merge=lfs -text
38
+ model/model/embed_tokens/embedding/2.0 filter=lfs diff=lfs merge=lfs -text
39
+ model/model/embed_tokens/embedding/3.0 filter=lfs diff=lfs merge=lfs -text
40
+ model/model/layers/0/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
41
+ model/model/layers/0/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
42
+ model/model/layers/0/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
43
+ model/model/layers/0/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
44
+ model/model/layers/0/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
45
+ model/model/layers/0/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
46
+ model/model/layers/0/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
47
+ model/model/layers/0/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
48
+ model/model/layers/0/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
49
+ model/model/layers/0/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
50
+ model/model/layers/0/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
51
+ model/model/layers/0/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
52
+ model/model/layers/0/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
53
+ model/model/layers/0/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
54
+ model/model/layers/0/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
55
+ model/model/layers/0/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
56
+ model/model/layers/0/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
57
+ model/model/layers/0/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
58
+ model/model/layers/0/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
59
+ model/model/layers/0/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
60
+ model/model/layers/0/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
61
+ model/model/layers/0/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
62
+ model/model/layers/0/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
63
+ model/model/layers/0/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
64
+ model/model/layers/0/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
65
+ model/model/layers/0/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
66
+ model/model/layers/0/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
67
+ model/model/layers/0/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
68
+ model/model/layers/1/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
69
+ model/model/layers/1/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
70
+ model/model/layers/1/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
71
+ model/model/layers/1/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
72
+ model/model/layers/1/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
73
+ model/model/layers/1/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
74
+ model/model/layers/1/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
75
+ model/model/layers/1/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
76
+ model/model/layers/1/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
77
+ model/model/layers/1/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
78
+ model/model/layers/1/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
79
+ model/model/layers/1/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
80
+ model/model/layers/1/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
81
+ model/model/layers/1/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
82
+ model/model/layers/1/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
83
+ model/model/layers/1/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
84
+ model/model/layers/1/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
85
+ model/model/layers/1/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
86
+ model/model/layers/1/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
87
+ model/model/layers/1/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
88
+ model/model/layers/1/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
89
+ model/model/layers/1/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
90
+ model/model/layers/1/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
91
+ model/model/layers/1/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
92
+ model/model/layers/1/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
93
+ model/model/layers/1/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
94
+ model/model/layers/1/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
95
+ model/model/layers/1/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
96
+ model/model/layers/10/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
97
+ model/model/layers/10/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
98
+ model/model/layers/10/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
99
+ model/model/layers/10/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
100
+ model/model/layers/10/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
101
+ model/model/layers/10/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
102
+ model/model/layers/10/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
103
+ model/model/layers/10/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
104
+ model/model/layers/10/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
105
+ model/model/layers/10/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
106
+ model/model/layers/10/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
107
+ model/model/layers/10/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
108
+ model/model/layers/10/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
109
+ model/model/layers/10/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
110
+ model/model/layers/10/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
111
+ model/model/layers/10/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
112
+ model/model/layers/10/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
113
+ model/model/layers/10/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
114
+ model/model/layers/10/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
115
+ model/model/layers/10/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
116
+ model/model/layers/10/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
117
+ model/model/layers/10/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
118
+ model/model/layers/10/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
119
+ model/model/layers/10/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
120
+ model/model/layers/10/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
121
+ model/model/layers/10/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
122
+ model/model/layers/10/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
123
+ model/model/layers/10/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
124
+ model/model/layers/11/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
125
+ model/model/layers/11/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
126
+ model/model/layers/11/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
127
+ model/model/layers/11/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
128
+ model/model/layers/11/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
129
+ model/model/layers/11/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
130
+ model/model/layers/11/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
131
+ model/model/layers/11/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
132
+ model/model/layers/11/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
133
+ model/model/layers/11/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
134
+ model/model/layers/11/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
135
+ model/model/layers/11/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
136
+ model/model/layers/11/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
137
+ model/model/layers/11/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
138
+ model/model/layers/11/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
139
+ model/model/layers/11/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
140
+ model/model/layers/11/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
141
+ model/model/layers/11/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
142
+ model/model/layers/11/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
143
+ model/model/layers/11/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
144
+ model/model/layers/11/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
145
+ model/model/layers/11/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
146
+ model/model/layers/11/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
147
+ model/model/layers/11/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
148
+ model/model/layers/11/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
149
+ model/model/layers/11/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
150
+ model/model/layers/11/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
151
+ model/model/layers/11/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
152
+ model/model/layers/12/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
153
+ model/model/layers/12/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
154
+ model/model/layers/12/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
155
+ model/model/layers/12/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
156
+ model/model/layers/12/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
157
+ model/model/layers/12/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
158
+ model/model/layers/12/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
159
+ model/model/layers/12/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
160
+ model/model/layers/12/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
161
+ model/model/layers/12/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
162
+ model/model/layers/12/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
163
+ model/model/layers/12/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
164
+ model/model/layers/12/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
165
+ model/model/layers/12/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
166
+ model/model/layers/12/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
167
+ model/model/layers/12/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
168
+ model/model/layers/12/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
169
+ model/model/layers/12/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
170
+ model/model/layers/12/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
171
+ model/model/layers/12/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
172
+ model/model/layers/12/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
173
+ model/model/layers/12/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
174
+ model/model/layers/12/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
175
+ model/model/layers/12/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
176
+ model/model/layers/12/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
177
+ model/model/layers/12/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
178
+ model/model/layers/12/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
179
+ model/model/layers/12/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
180
+ model/model/layers/13/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
181
+ model/model/layers/13/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
182
+ model/model/layers/13/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
183
+ model/model/layers/13/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
184
+ model/model/layers/13/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
185
+ model/model/layers/13/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
186
+ model/model/layers/13/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
187
+ model/model/layers/13/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
188
+ model/model/layers/13/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
189
+ model/model/layers/13/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
190
+ model/model/layers/13/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
191
+ model/model/layers/13/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
192
+ model/model/layers/13/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
193
+ model/model/layers/13/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
194
+ model/model/layers/13/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
195
+ model/model/layers/13/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
196
+ model/model/layers/13/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
197
+ model/model/layers/13/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
198
+ model/model/layers/13/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
199
+ model/model/layers/13/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
200
+ model/model/layers/13/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
201
+ model/model/layers/13/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
202
+ model/model/layers/13/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
203
+ model/model/layers/13/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
204
+ model/model/layers/13/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
205
+ model/model/layers/13/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
206
+ model/model/layers/13/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
207
+ model/model/layers/13/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
208
+ model/model/layers/14/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
209
+ model/model/layers/14/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
210
+ model/model/layers/14/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
211
+ model/model/layers/14/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
212
+ model/model/layers/14/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
213
+ model/model/layers/14/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
214
+ model/model/layers/14/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
215
+ model/model/layers/14/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
216
+ model/model/layers/14/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
217
+ model/model/layers/14/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
218
+ model/model/layers/14/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
219
+ model/model/layers/14/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
220
+ model/model/layers/14/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
221
+ model/model/layers/14/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
222
+ model/model/layers/14/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
223
+ model/model/layers/14/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
224
+ model/model/layers/14/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
225
+ model/model/layers/14/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
226
+ model/model/layers/14/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
227
+ model/model/layers/14/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
228
+ model/model/layers/14/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
229
+ model/model/layers/14/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
230
+ model/model/layers/14/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
231
+ model/model/layers/14/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
232
+ model/model/layers/14/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
233
+ model/model/layers/14/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
234
+ model/model/layers/14/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
235
+ model/model/layers/14/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
236
+ model/model/layers/15/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
237
+ model/model/layers/15/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
238
+ model/model/layers/15/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
239
+ model/model/layers/15/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
240
+ model/model/layers/15/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
241
+ model/model/layers/15/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
242
+ model/model/layers/15/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
243
+ model/model/layers/15/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
244
+ model/model/layers/15/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
245
+ model/model/layers/15/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
246
+ model/model/layers/15/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
247
+ model/model/layers/15/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
248
+ model/model/layers/15/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
249
+ model/model/layers/15/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
250
+ model/model/layers/15/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
251
+ model/model/layers/15/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
252
+ model/model/layers/15/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
253
+ model/model/layers/15/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
254
+ model/model/layers/15/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
255
+ model/model/layers/15/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
256
+ model/model/layers/15/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
257
+ model/model/layers/15/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
258
+ model/model/layers/15/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
259
+ model/model/layers/15/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
260
+ model/model/layers/15/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
261
+ model/model/layers/15/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
262
+ model/model/layers/15/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
263
+ model/model/layers/15/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
264
+ model/model/layers/2/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
265
+ model/model/layers/2/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
266
+ model/model/layers/2/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
267
+ model/model/layers/2/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
268
+ model/model/layers/2/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
269
+ model/model/layers/2/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
270
+ model/model/layers/2/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
271
+ model/model/layers/2/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
272
+ model/model/layers/2/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
273
+ model/model/layers/2/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
274
+ model/model/layers/2/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
275
+ model/model/layers/2/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
276
+ model/model/layers/2/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
277
+ model/model/layers/2/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
278
+ model/model/layers/2/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
279
+ model/model/layers/2/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
280
+ model/model/layers/2/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
281
+ model/model/layers/2/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
282
+ model/model/layers/2/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
283
+ model/model/layers/2/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
284
+ model/model/layers/2/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
285
+ model/model/layers/2/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
286
+ model/model/layers/2/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
287
+ model/model/layers/2/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
288
+ model/model/layers/2/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
289
+ model/model/layers/2/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
290
+ model/model/layers/2/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
291
+ model/model/layers/2/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
292
+ model/model/layers/3/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
293
+ model/model/layers/3/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
294
+ model/model/layers/3/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
295
+ model/model/layers/3/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
296
+ model/model/layers/3/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
297
+ model/model/layers/3/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
298
+ model/model/layers/3/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
299
+ model/model/layers/3/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
300
+ model/model/layers/3/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
301
+ model/model/layers/3/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
302
+ model/model/layers/3/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
303
+ model/model/layers/3/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
304
+ model/model/layers/3/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
305
+ model/model/layers/3/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
306
+ model/model/layers/3/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
307
+ model/model/layers/3/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
308
+ model/model/layers/3/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
309
+ model/model/layers/3/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
310
+ model/model/layers/3/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
311
+ model/model/layers/3/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
312
+ model/model/layers/3/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
313
+ model/model/layers/3/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
314
+ model/model/layers/3/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
315
+ model/model/layers/3/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
316
+ model/model/layers/3/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
317
+ model/model/layers/3/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
318
+ model/model/layers/3/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
319
+ model/model/layers/3/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
320
+ model/model/layers/4/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
321
+ model/model/layers/4/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
322
+ model/model/layers/4/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
323
+ model/model/layers/4/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
324
+ model/model/layers/4/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
325
+ model/model/layers/4/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
326
+ model/model/layers/4/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
327
+ model/model/layers/4/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
328
+ model/model/layers/4/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
329
+ model/model/layers/4/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
330
+ model/model/layers/4/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
331
+ model/model/layers/4/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
332
+ model/model/layers/4/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
333
+ model/model/layers/4/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
334
+ model/model/layers/4/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
335
+ model/model/layers/4/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
336
+ model/model/layers/4/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
337
+ model/model/layers/4/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
338
+ model/model/layers/4/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
339
+ model/model/layers/4/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
340
+ model/model/layers/4/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
341
+ model/model/layers/4/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
342
+ model/model/layers/4/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
343
+ model/model/layers/4/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
344
+ model/model/layers/4/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
345
+ model/model/layers/4/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
346
+ model/model/layers/4/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
347
+ model/model/layers/4/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
348
+ model/model/layers/5/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
349
+ model/model/layers/5/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
350
+ model/model/layers/5/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
351
+ model/model/layers/5/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
352
+ model/model/layers/5/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
353
+ model/model/layers/5/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
354
+ model/model/layers/5/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
355
+ model/model/layers/5/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
356
+ model/model/layers/5/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
357
+ model/model/layers/5/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
358
+ model/model/layers/5/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
359
+ model/model/layers/5/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
360
+ model/model/layers/5/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
361
+ model/model/layers/5/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
362
+ model/model/layers/5/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
363
+ model/model/layers/5/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
364
+ model/model/layers/5/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
365
+ model/model/layers/5/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
366
+ model/model/layers/5/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
367
+ model/model/layers/5/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
368
+ model/model/layers/5/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
369
+ model/model/layers/5/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
370
+ model/model/layers/5/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
371
+ model/model/layers/5/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
372
+ model/model/layers/5/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
373
+ model/model/layers/5/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
374
+ model/model/layers/5/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
375
+ model/model/layers/5/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
376
+ model/model/layers/6/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
377
+ model/model/layers/6/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
378
+ model/model/layers/6/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
379
+ model/model/layers/6/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
380
+ model/model/layers/6/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
381
+ model/model/layers/6/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
382
+ model/model/layers/6/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
383
+ model/model/layers/6/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
384
+ model/model/layers/6/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
385
+ model/model/layers/6/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
386
+ model/model/layers/6/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
387
+ model/model/layers/6/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
388
+ model/model/layers/6/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
389
+ model/model/layers/6/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
390
+ model/model/layers/6/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
391
+ model/model/layers/6/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
392
+ model/model/layers/6/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
393
+ model/model/layers/6/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
394
+ model/model/layers/6/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
395
+ model/model/layers/6/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
396
+ model/model/layers/6/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
397
+ model/model/layers/6/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
398
+ model/model/layers/6/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
399
+ model/model/layers/6/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
400
+ model/model/layers/6/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
401
+ model/model/layers/6/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
402
+ model/model/layers/6/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
403
+ model/model/layers/6/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
404
+ model/model/layers/7/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
405
+ model/model/layers/7/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
406
+ model/model/layers/7/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
407
+ model/model/layers/7/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
408
+ model/model/layers/7/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
409
+ model/model/layers/7/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
410
+ model/model/layers/7/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
411
+ model/model/layers/7/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
412
+ model/model/layers/7/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
413
+ model/model/layers/7/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
414
+ model/model/layers/7/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
415
+ model/model/layers/7/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
416
+ model/model/layers/7/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
417
+ model/model/layers/7/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
418
+ model/model/layers/7/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
419
+ model/model/layers/7/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
420
+ model/model/layers/7/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
421
+ model/model/layers/7/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
422
+ model/model/layers/7/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
423
+ model/model/layers/7/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
424
+ model/model/layers/7/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
425
+ model/model/layers/7/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
426
+ model/model/layers/7/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
427
+ model/model/layers/7/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
428
+ model/model/layers/7/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
429
+ model/model/layers/7/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
430
+ model/model/layers/7/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
431
+ model/model/layers/7/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
432
+ model/model/layers/8/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
433
+ model/model/layers/8/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
434
+ model/model/layers/8/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
435
+ model/model/layers/8/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
436
+ model/model/layers/8/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
437
+ model/model/layers/8/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
438
+ model/model/layers/8/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
439
+ model/model/layers/8/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
440
+ model/model/layers/8/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
441
+ model/model/layers/8/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
442
+ model/model/layers/8/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
443
+ model/model/layers/8/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
444
+ model/model/layers/8/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
445
+ model/model/layers/8/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
446
+ model/model/layers/8/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
447
+ model/model/layers/8/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
448
+ model/model/layers/8/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
449
+ model/model/layers/8/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
450
+ model/model/layers/8/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
451
+ model/model/layers/8/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
452
+ model/model/layers/8/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
453
+ model/model/layers/8/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
454
+ model/model/layers/8/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
455
+ model/model/layers/8/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
456
+ model/model/layers/8/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
457
+ model/model/layers/8/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
458
+ model/model/layers/8/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
459
+ model/model/layers/8/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
460
+ model/model/layers/9/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
461
+ model/model/layers/9/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
462
+ model/model/layers/9/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
463
+ model/model/layers/9/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
464
+ model/model/layers/9/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
465
+ model/model/layers/9/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
466
+ model/model/layers/9/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
467
+ model/model/layers/9/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
468
+ model/model/layers/9/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
469
+ model/model/layers/9/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
470
+ model/model/layers/9/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
471
+ model/model/layers/9/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
472
+ model/model/layers/9/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
473
+ model/model/layers/9/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
474
+ model/model/layers/9/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
475
+ model/model/layers/9/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
476
+ model/model/layers/9/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
477
+ model/model/layers/9/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
478
+ model/model/layers/9/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
479
+ model/model/layers/9/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
480
+ model/model/layers/9/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
481
+ model/model/layers/9/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
482
+ model/model/layers/9/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
483
+ model/model/layers/9/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
484
+ model/model/layers/9/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
485
+ model/model/layers/9/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
486
+ model/model/layers/9/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
487
+ model/model/layers/9/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
488
+ 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-3.2-1B-Instruct</h1>
17
+
18
+ <div align="center">
19
+ EasyDeL checkpoint converted from meta-llama/Llama-3.2-1B-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-3.2-1B-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-3.2-1B-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-3.2-1B-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 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
29
+ {%- if tools is not none %}
30
+ {{- "Environment: ipython\n" }}
31
+ {%- endif %}
32
+ {{- "Cutting Knowledge Date: December 2023\n" }}
33
+ {{- "Today Date: " + date_string + "\n\n" }}
34
+ {%- if tools is not none and not tools_in_user_message %}
35
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
36
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
37
+ {{- "Do not use variables.\n\n" }}
38
+ {%- for t in tools %}
39
+ {{- t | tojson(indent=4) }}
40
+ {{- "\n\n" }}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {{- system_message }}
44
+ {{- "<|eot_id|>" }}
45
+
46
+ {#- Custom tools are passed in a user message with some extra guidance #}
47
+ {%- if tools_in_user_message and not tools is none %}
48
+ {#- Extract the first user message so we can plug it in here #}
49
+ {%- if messages | length != 0 %}
50
+ {%- set first_user_message = messages[0]['content']|trim %}
51
+ {%- set messages = messages[1:] %}
52
+ {%- else %}
53
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
54
+ {%- endif %}
55
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
56
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
57
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
58
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
59
+ {{- "Do not use variables.\n\n" }}
60
+ {%- for t in tools %}
61
+ {{- t | tojson(indent=4) }}
62
+ {{- "\n\n" }}
63
+ {%- endfor %}
64
+ {{- first_user_message + "<|eot_id|>"}}
65
+ {%- endif %}
66
+
67
+ {%- for message in messages %}
68
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
69
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
70
+ {%- elif 'tool_calls' in message %}
71
+ {%- if not message.tool_calls|length == 1 %}
72
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
73
+ {%- endif %}
74
+ {%- set tool_call = message.tool_calls[0].function %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- '{"name": "' + tool_call.name + '", ' }}
77
+ {{- '"parameters": ' }}
78
+ {{- tool_call.arguments | tojson }}
79
+ {{- "}" }}
80
+ {{- "<|eot_id|>" }}
81
+ {%- elif message.role == "tool" or message.role == "ipython" %}
82
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
83
+ {%- if message.content is mapping or message.content is iterable %}
84
+ {{- message.content | tojson }}
85
+ {%- else %}
86
+ {{- message.content }}
87
+ {%- endif %}
88
+ {{- "<|eot_id|>" }}
89
+ {%- endif %}
90
+ {%- endfor %}
91
+ {%- if add_generation_prompt %}
92
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
93
+ {%- endif %}
checkpoint_metadata.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "timestamp": "2025-12-28T22:19:36.412661",
3
+ "custom_metadata": {
4
+ "step": 0
5
+ }
6
+ }
config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 64,
32
+ "hidden_act": "silu",
33
+ "hidden_size": 2048,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 8192,
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
+ ],
56
+ "max_position_embeddings": 131072,
57
+ "mlp_bias": false,
58
+ "model_type": "llama",
59
+ "moe_force_xla_gmm": false,
60
+ "moe_method": "fused_moe",
61
+ "moe_tiling_size_batch": 4,
62
+ "moe_tiling_size_dim": 128,
63
+ "moe_tiling_size_seqlen": 128,
64
+ "num_attention_heads": 32,
65
+ "num_hidden_layers": 16,
66
+ "num_key_value_heads": 8,
67
+ "number_rep_kv": 1,
68
+ "operation_configs": null,
69
+ "pallas_k_block_size": 128,
70
+ "pallas_m_block_size": 128,
71
+ "pallas_n_block_size": 128,
72
+ "partition_axis": {
73
+ "attention_dim_axis": null,
74
+ "attention_kv_dim_axis": null,
75
+ "batch_axis": [
76
+ "fsdp",
77
+ "dp"
78
+ ],
79
+ "bias_head_sequence_axis": null,
80
+ "bias_key_sequence_axis": null,
81
+ "data_parallel_axis": "dp",
82
+ "decode_attention_dim_axis": null,
83
+ "decode_attention_kv_dim_axis": null,
84
+ "decode_batch_axis": [
85
+ "fsdp",
86
+ "dp"
87
+ ],
88
+ "decode_head_axis": "tp",
89
+ "decode_key_sequence_axis": "sp",
90
+ "decode_kv_head_axis": "tp",
91
+ "decode_query_sequence_axis": null,
92
+ "expert_axis": "ep",
93
+ "expert_gate_axis": null,
94
+ "expert_parallel_axis": "ep",
95
+ "fully_sharded_data_parallel_axis": "fsdp",
96
+ "head_axis": "tp",
97
+ "hidden_state_axis": "tp",
98
+ "key_sequence_axis": "sp",
99
+ "kv_head_axis": "tp",
100
+ "mlp_intermediate_axis": "tp",
101
+ "query_sequence_axis": "sp",
102
+ "sequence_axis": "sp",
103
+ "sequence_parallel_axis": "sp",
104
+ "tensor_parallel_axis": "tp",
105
+ "vocab_axis": "tp"
106
+ },
107
+ "platform": null,
108
+ "precompute_masks": true,
109
+ "pretraining_tp": 1,
110
+ "quantization_config": null,
111
+ "resid_pdrop": 0.0,
112
+ "rms_norm_eps": 1e-05,
113
+ "rope_scaling": {
114
+ "factor": 32.0,
115
+ "high_freq_factor": 4.0,
116
+ "low_freq_factor": 1.0,
117
+ "original_max_position_embeddings": 8192,
118
+ "rope_type": "llama3"
119
+ },
120
+ "rope_theta": 500000.0,
121
+ "scan_attention_layers": false,
122
+ "scan_layers": false,
123
+ "scan_mlp_chunk_size": 1024,
124
+ "scan_ring_attention": true,
125
+ "sequence_axis_name": "sp",
126
+ "sharding_axis_dims": [
127
+ 1,
128
+ -1,
129
+ 1,
130
+ 1,
131
+ 1
132
+ ],
133
+ "sharding_axis_names": [
134
+ "dp",
135
+ "fsdp",
136
+ "ep",
137
+ "tp",
138
+ "sp"
139
+ ],
140
+ "sharding_dcn_axis_dims": null,
141
+ "sp_is_ep_bound": true,
142
+ "tie_word_embeddings": true,
143
+ "transformers_version": "4.57.3",
144
+ "use_cache": true,
145
+ "use_expert_tensor_mode": false,
146
+ "use_ring_of_experts": false,
147
+ "use_scan_mlp": false,
148
+ "use_sharded_kv_caching": false,
149
+ "use_sharding_constraint": false,
150
+ "vocab_size": 128256
151
+ }
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/model/embed_tokens/embedding/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[32064,2048],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[128256,2048],"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 sha256:4ea837b38624449d8ab8c668e77176d00703925f32bb438ce913e2222694b7d0
3
+ size 102492789
model/model/embed_tokens/embedding/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea7ed6da80a63a248ac2481e2b82b88d0a145a41c7fabc254677ca24b09c679
3
+ size 102484784
model/model/embed_tokens/embedding/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbca9f6c5e667388a9e6445b417032c35898a688bcf2ca123a65a21c171bae55
3
+ size 102479657
model/model/embed_tokens/embedding/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a691d334486c9613e348a52dd956ed7ef644ecbe32c09c6305f4f5df54889c6
3
+ size 101688512
model/model/layers/0/input_layernorm/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[2048],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048],"zarr_format":2}
model/model/layers/0/input_layernorm/kernel/0 ADDED
Binary file (2.84 kB). View file
 
model/model/layers/0/mlp/down_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[8192,512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[8192,2048],"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 sha256:9d6a786d98070521e730d218d02ab9a510e3f32bb3800014e7b480f1a9bff656
3
+ size 6527475
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 sha256:7af4228604a0048ccad8da87f67951727acc054aa6e8f8973c5dd77c7b46bde0
3
+ size 6528474
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 sha256:154596ecb52b421450500626ef1bdc563dcf1420a98a62e0267d08006d365f61
3
+ size 6526280
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 sha256:0e033eed0a285e527d0aaaac87f285714c37269f3ab4615b490b0cfd81902bc0
3
+ size 6527877
model/model/layers/0/mlp/gate_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[512,8192],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048,8192],"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 sha256:21b405be1611368b2f7f889e59b732ff785be445e4c9ccead5f9057cfe3a19c9
3
+ size 6538934
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 sha256:3ac49d8d1c7bb012db9efd933884fc43c6ed80d378e65e51e120f209f17faaf8
3
+ size 6536157
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 sha256:8cdcabf5db44daca65844a808368306eaec12f04b0813c02d5aa482895c8783b
3
+ size 6539230
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 sha256:78b0e654c953a1252780595e72015df465beb137bb455470d62600879b701ab2
3
+ size 6539301
model/model/layers/0/mlp/up_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[512,8192],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048,8192],"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 sha256:02bef30fbbae495ea9023edcf1e664187fd7ed8f082897bb07a8a976f8279f90
3
+ size 6529491
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 sha256:3df9f3b7ac315d43b19fa301151aea24f39be17b127e1d42605778bbe4b9c782
3
+ size 6526459
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:fe13b34c095a68ed3ca264d915a038cb004703cf9ed41c1dba49430c97665334
3
+ size 6528775
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:affeca4f12b92a702938164e824368427b2b75fb1aea3e132858ef9d047ebd33
3
+ size 6530095
model/model/layers/0/post_attention_layernorm/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[2048],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048],"zarr_format":2}
model/model/layers/0/post_attention_layernorm/kernel/0 ADDED
Binary file (1.99 kB). View file
 
model/model/layers/0/self_attn/k_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[512,512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048,512],"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 sha256:87e1dc807c3d4bc782822200a7f86cc621324d2d7a21d2db2f1f6e9ee55da179
3
+ size 414402
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:c1e33ea14570cb6a35fa6005b9209dddf060c08d043e3ef61222a8ead6ecbde7
3
+ size 414730
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 sha256:1210968776a4ac9f29c715939344d6fdd1bc2203412a24211bacf1c8e9cf55b6
3
+ size 415025
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 sha256:4e24f82d8850f260b0774b46407cf9dab147a6c8771016426baad44caf67482b
3
+ size 414790
model/model/layers/0/self_attn/o_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[2048,512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048,2048],"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 sha256:0597eb782a53d6aa632d27f0516292551b505910d46137a9c43fe347f3318ceb
3
+ size 1640502
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 sha256:55c4e61602a7f16064a205ae526a7f71fc4beae692db92a009593c41bc79b2e0
3
+ size 1639848
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 sha256:23f5810937dcc2a929f3a01ea51010dc40fa264d3e01f378f1c8a9d7eb61b852
3
+ size 1640166
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:c92f1849f8664e3030868f71bd315e66ad3539b0e9c0ce673d4ec2fbd81d1e7a
3
+ size 1640754
model/model/layers/0/self_attn/q_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[512,2048],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048,2048],"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 sha256:46ab7d3932f1aa9567c15aec0eb8ac8d6e7dc646a6a1ff24617eefdbd23ce5f8
3
+ size 1657678
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 sha256:62aa6fadaf4a3d404d814e283e42ee3c32dd3084a0180f9664bedea574b06f57
3
+ size 1659813
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 sha256:04b4696d98a01c707cafe7aec0652331b9e5ebd4299afcde9d68d0e432deff61
3
+ size 1660245
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 sha256:58757a51a3cd976f00417957d1f0820225c56d57235d9d0b16c69d8091340b2a
3
+ size 1658737
model/model/layers/0/self_attn/v_proj/kernel/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[512,512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048,512],"zarr_format":2}
model/model/layers/0/self_attn/v_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0b896e9cda0219ec8e0eda3bea0ec559f601eb43f69de45fd136ccd7b5edc7
3
+ size 414432
model/model/layers/0/self_attn/v_proj/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f93ad4937ab7a65785916562c133808c80436feff8fcb1241f687b0adc01b740
3
+ size 414974
model/model/layers/0/self_attn/v_proj/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d6a45031b3b43db3d940b1bbcc37cfffde8b2078db5031be6676ee832abe11
3
+ size 414881
model/model/layers/0/self_attn/v_proj/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d5d34a6a13b2e719073ecafa48558f8572aeb832d6c9cb6559358f5ffa549a
3
+ size 414444