Hugging Face's logo

cstr
/
zerank-1-small-ONNX

Text Ranking
ONNX
English
fastembed
qwen3
reranking
quantized
custom_code
Model card Files
xet
 Community
cstr commited on
Commit
af72d8f
·
verified ·
1 Parent(s): ba9c38b

Export zerank-1-small v2: dynamic batch + correct chat template

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 +197 -0
  2. base.model.embed_tokens.weight +3 -0
  3. base.model.layers.0.input_layernorm.weight +0 -0
  4. base.model.layers.0.mlp.down_proj.weight +3 -0
  5. base.model.layers.0.mlp.gate_proj.weight +3 -0
  6. base.model.layers.0.mlp.up_proj.weight +3 -0
  7. base.model.layers.0.post_attention_layernorm.weight +0 -0
  8. base.model.layers.0.self_attn.k_proj.weight +3 -0
  9. base.model.layers.0.self_attn.o_proj.weight +3 -0
  10. base.model.layers.0.self_attn.q_proj.weight +3 -0
  11. base.model.layers.0.self_attn.v_proj.weight +3 -0
  12. base.model.layers.1.input_layernorm.weight +0 -0
  13. base.model.layers.1.mlp.down_proj.weight +3 -0
  14. base.model.layers.1.mlp.gate_proj.weight +3 -0
  15. base.model.layers.1.mlp.up_proj.weight +3 -0
  16. base.model.layers.1.post_attention_layernorm.weight +0 -0
  17. base.model.layers.1.self_attn.k_proj.weight +3 -0
  18. base.model.layers.1.self_attn.o_proj.weight +3 -0
  19. base.model.layers.1.self_attn.q_proj.weight +3 -0
  20. base.model.layers.1.self_attn.v_proj.weight +3 -0
  21. base.model.layers.10.input_layernorm.weight +0 -0
  22. base.model.layers.10.mlp.down_proj.weight +3 -0
  23. base.model.layers.10.mlp.gate_proj.weight +3 -0
  24. base.model.layers.10.mlp.up_proj.weight +3 -0
  25. base.model.layers.10.post_attention_layernorm.weight +0 -0
  26. base.model.layers.10.self_attn.k_proj.weight +3 -0
  27. base.model.layers.10.self_attn.o_proj.weight +3 -0
  28. base.model.layers.10.self_attn.q_proj.weight +3 -0
  29. base.model.layers.10.self_attn.v_proj.weight +3 -0
  30. base.model.layers.11.input_layernorm.weight +0 -0
  31. base.model.layers.11.mlp.down_proj.weight +3 -0
  32. base.model.layers.11.mlp.gate_proj.weight +3 -0
  33. base.model.layers.11.mlp.up_proj.weight +3 -0
  34. base.model.layers.11.post_attention_layernorm.weight +0 -0
  35. base.model.layers.11.self_attn.k_proj.weight +3 -0
  36. base.model.layers.11.self_attn.o_proj.weight +3 -0
  37. base.model.layers.11.self_attn.q_proj.weight +3 -0
  38. base.model.layers.11.self_attn.v_proj.weight +3 -0
  39. base.model.layers.12.input_layernorm.weight +0 -0
  40. base.model.layers.12.mlp.down_proj.weight +3 -0
  41. base.model.layers.12.mlp.gate_proj.weight +3 -0
  42. base.model.layers.12.mlp.up_proj.weight +3 -0
  43. base.model.layers.12.post_attention_layernorm.weight +0 -0
  44. base.model.layers.12.self_attn.k_proj.weight +3 -0
  45. base.model.layers.12.self_attn.o_proj.weight +3 -0
  46. base.model.layers.12.self_attn.q_proj.weight +3 -0
  47. base.model.layers.12.self_attn.v_proj.weight +3 -0
  48. base.model.layers.13.input_layernorm.weight +0 -0
  49. base.model.layers.13.mlp.down_proj.weight +3 -0
  50. base.model.layers.13.mlp.gate_proj.weight +3 -0
.gitattributes CHANGED
@@ -36,3 +36,200 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  model_int8.onnx_data filter=lfs diff=lfs merge=lfs -text
37
  model.onnx_data filter=lfs diff=lfs merge=lfs -text
38
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  model_int8.onnx_data filter=lfs diff=lfs merge=lfs -text
37
  model.onnx_data filter=lfs diff=lfs merge=lfs -text
38
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ base.model.embed_tokens.weight filter=lfs diff=lfs merge=lfs -text
40
+ base.model.layers.0.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
41
+ base.model.layers.0.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
42
+ base.model.layers.0.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
43
+ base.model.layers.0.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
44
+ base.model.layers.0.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
45
+ base.model.layers.0.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
46
+ base.model.layers.0.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
47
+ base.model.layers.1.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
48
+ base.model.layers.1.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
49
+ base.model.layers.1.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
50
+ base.model.layers.1.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
51
+ base.model.layers.1.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
52
+ base.model.layers.1.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
53
+ base.model.layers.1.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
54
+ base.model.layers.10.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
55
+ base.model.layers.10.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
56
+ base.model.layers.10.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
57
+ base.model.layers.10.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
58
+ base.model.layers.10.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
59
+ base.model.layers.10.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
60
+ base.model.layers.10.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
61
+ base.model.layers.11.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
62
+ base.model.layers.11.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
63
+ base.model.layers.11.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
64
+ base.model.layers.11.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
65
+ base.model.layers.11.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
66
+ base.model.layers.11.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
67
+ base.model.layers.11.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
68
+ base.model.layers.12.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
69
+ base.model.layers.12.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
70
+ base.model.layers.12.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
71
+ base.model.layers.12.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
72
+ base.model.layers.12.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
73
+ base.model.layers.12.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
74
+ base.model.layers.12.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
75
+ base.model.layers.13.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
76
+ base.model.layers.13.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
77
+ base.model.layers.13.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
78
+ base.model.layers.13.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
79
+ base.model.layers.13.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
80
+ base.model.layers.13.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
81
+ base.model.layers.13.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
82
+ base.model.layers.14.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
83
+ base.model.layers.14.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
84
+ base.model.layers.14.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
85
+ base.model.layers.14.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
86
+ base.model.layers.14.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
87
+ base.model.layers.14.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
88
+ base.model.layers.14.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
89
+ base.model.layers.15.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
90
+ base.model.layers.15.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
91
+ base.model.layers.15.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
92
+ base.model.layers.15.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
93
+ base.model.layers.15.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
94
+ base.model.layers.15.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
95
+ base.model.layers.15.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
96
+ base.model.layers.16.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
97
+ base.model.layers.16.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
98
+ base.model.layers.16.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
99
+ base.model.layers.16.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
100
+ base.model.layers.16.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
101
+ base.model.layers.16.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
102
+ base.model.layers.16.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
103
+ base.model.layers.17.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
104
+ base.model.layers.17.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
105
+ base.model.layers.17.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
106
+ base.model.layers.17.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
107
+ base.model.layers.17.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
108
+ base.model.layers.17.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
109
+ base.model.layers.17.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
110
+ base.model.layers.18.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
111
+ base.model.layers.18.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
112
+ base.model.layers.18.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
113
+ base.model.layers.18.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
114
+ base.model.layers.18.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
115
+ base.model.layers.18.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
116
+ base.model.layers.18.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
117
+ base.model.layers.19.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
118
+ base.model.layers.19.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
119
+ base.model.layers.19.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
120
+ base.model.layers.19.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
121
+ base.model.layers.19.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
122
+ base.model.layers.19.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
123
+ base.model.layers.19.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
124
+ base.model.layers.2.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
125
+ base.model.layers.2.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
126
+ base.model.layers.2.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
127
+ base.model.layers.2.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
128
+ base.model.layers.2.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
129
+ base.model.layers.2.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
130
+ base.model.layers.2.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
131
+ base.model.layers.20.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
132
+ base.model.layers.20.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
133
+ base.model.layers.20.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
134
+ base.model.layers.20.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
135
+ base.model.layers.20.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
136
+ base.model.layers.20.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
137
+ base.model.layers.20.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
138
+ base.model.layers.21.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
139
+ base.model.layers.21.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
140
+ base.model.layers.21.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
141
+ base.model.layers.21.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
142
+ base.model.layers.21.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
143
+ base.model.layers.21.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
144
+ base.model.layers.21.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
145
+ base.model.layers.22.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
146
+ base.model.layers.22.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
147
+ base.model.layers.22.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
148
+ base.model.layers.22.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
149
+ base.model.layers.22.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
150
+ base.model.layers.22.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
151
+ base.model.layers.22.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
152
+ base.model.layers.23.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
153
+ base.model.layers.23.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
154
+ base.model.layers.23.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
155
+ base.model.layers.23.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
156
+ base.model.layers.23.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
157
+ base.model.layers.23.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
158
+ base.model.layers.23.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
159
+ base.model.layers.24.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
160
+ base.model.layers.24.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
161
+ base.model.layers.24.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
162
+ base.model.layers.24.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
163
+ base.model.layers.24.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
164
+ base.model.layers.24.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
165
+ base.model.layers.24.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
166
+ base.model.layers.25.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
167
+ base.model.layers.25.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
168
+ base.model.layers.25.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
169
+ base.model.layers.25.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
170
+ base.model.layers.25.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
171
+ base.model.layers.25.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
172
+ base.model.layers.25.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
173
+ base.model.layers.26.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
174
+ base.model.layers.26.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
175
+ base.model.layers.26.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
176
+ base.model.layers.26.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
177
+ base.model.layers.26.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
178
+ base.model.layers.26.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
179
+ base.model.layers.26.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
180
+ base.model.layers.27.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
181
+ base.model.layers.27.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
182
+ base.model.layers.27.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
183
+ base.model.layers.27.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
184
+ base.model.layers.27.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
185
+ base.model.layers.27.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
186
+ base.model.layers.27.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
187
+ base.model.layers.3.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
188
+ base.model.layers.3.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
189
+ base.model.layers.3.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
190
+ base.model.layers.3.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
191
+ base.model.layers.3.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
192
+ base.model.layers.3.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
193
+ base.model.layers.3.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
194
+ base.model.layers.4.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
195
+ base.model.layers.4.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
196
+ base.model.layers.4.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
197
+ base.model.layers.4.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
198
+ base.model.layers.4.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
199
+ base.model.layers.4.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
200
+ base.model.layers.4.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
201
+ base.model.layers.5.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
202
+ base.model.layers.5.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
203
+ base.model.layers.5.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
204
+ base.model.layers.5.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
205
+ base.model.layers.5.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
206
+ base.model.layers.5.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
207
+ base.model.layers.5.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
208
+ base.model.layers.6.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
209
+ base.model.layers.6.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
210
+ base.model.layers.6.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
211
+ base.model.layers.6.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
212
+ base.model.layers.6.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
213
+ base.model.layers.6.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
214
+ base.model.layers.6.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
215
+ base.model.layers.7.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
216
+ base.model.layers.7.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
217
+ base.model.layers.7.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
218
+ base.model.layers.7.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
219
+ base.model.layers.7.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
220
+ base.model.layers.7.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
221
+ base.model.layers.7.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
222
+ base.model.layers.8.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
223
+ base.model.layers.8.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
224
+ base.model.layers.8.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
225
+ base.model.layers.8.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
226
+ base.model.layers.8.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
227
+ base.model.layers.8.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
228
+ base.model.layers.8.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
229
+ base.model.layers.9.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
230
+ base.model.layers.9.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
231
+ base.model.layers.9.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
232
+ base.model.layers.9.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
233
+ base.model.layers.9.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
234
+ base.model.layers.9.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
235
+ base.model.layers.9.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
base.model.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bccd2bc5ec321a16d2c273d27634c9fe272fa5814fecc1fa48790fe7793edead
3
+ size 622329856
base.model.layers.0.input_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.0.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70cdf4e6b448eb93e8c09676e991a535a329509f29db854149527e102d1b17a
3
+ size 25165824
base.model.layers.0.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2e2f7c3759533b1c93d6000695cd1afdf6d887ec86a92708a565f55c26bfe78
3
+ size 25165824
base.model.layers.0.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4212cf7a10adb352e6d699731942a164b917e302279c9fb9aa69be5008403f61
3
+ size 25165824
base.model.layers.0.post_attention_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.0.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0cb6630f23d6e417c8a44c2c90f4e2cf2fc48936979138f2c9096ceb6825d8f
3
+ size 4194304
base.model.layers.0.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cbbc4a8bcb24c1557897e599671ee2e81c3853d3b9bd6d7652694d5225ebdbe
3
+ size 8388608
base.model.layers.0.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66a1c09cf6fa8f8b41c97a525b25ce50cb19447f962b6a4362f11915dc829a1
3
+ size 8388608
base.model.layers.0.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c13b8bac9f14f8bb78f2d5fef0329ee73c3d25993417b810fcd4d59b8bf1e8e
3
+ size 4194304
base.model.layers.1.input_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.1.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1145fde26898babda456b0a1875b0eba4848a4d42219699ac5e1d3e6f156857
3
+ size 25165824
base.model.layers.1.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cabfa69754bb71ce58c4f0501e0eeda0db4a38dce24d5ca1730d41eff76de05
3
+ size 25165824
base.model.layers.1.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffff8c09bfa15febfa4e078177165afdab9b8c128a0c718ec7b821a2a0f983e6
3
+ size 25165824
base.model.layers.1.post_attention_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.1.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3124cd4ebc90744a0dc930c9e271016590ca0a37def9ed8a6207c5cc1c510136
3
+ size 4194304
base.model.layers.1.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef991cc1f6fa39ead098244cf4c8c9938e57cb59abdbd952faf3d994a3ea2bd9
3
+ size 8388608
base.model.layers.1.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43e5890c9bd566785514234f5cf407b059330239d303b4080c0f3f3b2c84825
3
+ size 8388608
base.model.layers.1.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e8a76f5c12315b16488ca42d37a0cc66c18f2849fb0d17c90052615e6c10279
3
+ size 4194304
base.model.layers.10.input_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.10.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e2a3bc1ac76a5982ece487f919877970eecc14db9f10aefb326b07007cc9a3
3
+ size 25165824
base.model.layers.10.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5bff4d1e1587753431cd6ef64442824598764656d2cdd8c8eaee9c4f86cdf1
3
+ size 25165824
base.model.layers.10.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42240622a217f92fab7fc35427e1530f2302eb93f1554be83e0028a63481201
3
+ size 25165824
base.model.layers.10.post_attention_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.10.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb6ebcaee3685c1f5e6d3d9c744e9d245dac28beebfaec6bb8d1657b7cad1c0
3
+ size 4194304
base.model.layers.10.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ae6fef6f43244e04be863afd5b60c2c7f36ac4c6c829b46be6a2193d939e50
3
+ size 8388608
base.model.layers.10.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e41a37d283a38b3b4071c0bfdb14670badd83c4b625e1f9017ff3012a6244f
3
+ size 8388608
base.model.layers.10.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608ff2053d77b3b506db4c84655ae5114a19088aa3322515ad7ed795fb62517d
3
+ size 4194304
base.model.layers.11.input_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.11.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:680383ded670b1afcf37813a260661206267b7f5dfcc60a1a60c61a2136990f5
3
+ size 25165824
base.model.layers.11.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a8da64d52995f9e35e615d5e6c606a4027a9054891e0d084ad7ffb3e30029e
3
+ size 25165824
base.model.layers.11.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d87ad92a529f2392b2c3814c57b14d4d0e7b0a98ef2730aa2e303a375a19c0
3
+ size 25165824
base.model.layers.11.post_attention_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.11.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b083d76ac7d42f0f94b61d8ddbc0ff87e2b1eff0d65e41c4c0e16350d78873
3
+ size 4194304
base.model.layers.11.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55d4438adc80dd29118058c6b0952342479cccdff85449d0557eeb4cd1627f09
3
+ size 8388608
base.model.layers.11.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde0440d8536ffecf7aa1fa225b8209954743e8c9703166b7cc331c75c48125a
3
+ size 8388608
base.model.layers.11.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b9f4f85caf4f567c55d801c718c3d0feb28df288b7b61d35e77c9655d324c4
3
+ size 4194304
base.model.layers.12.input_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.12.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5113c378c146354e2fc8fec6f4f52386e651ca76b17f3e25833a72b8204dca5b
3
+ size 25165824
base.model.layers.12.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500521d50e93d22727c1c65b73d4e42d92966b590f5ce8bf93cc6768addc9937
3
+ size 25165824
base.model.layers.12.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d25bc35c69f8aa5c9384f0cd4542b6997151da706ea67ed266b0e025a285d4c
3
+ size 25165824
base.model.layers.12.post_attention_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.12.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3fc468410ffb5bec7bf6ba15786a3fcda93353b0d139e99fd4facd259622a4
3
+ size 4194304
base.model.layers.12.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2269bec1734fb414f693a2fe334182653dd6d7effb51efdc702e149d447ba17a
3
+ size 8388608
base.model.layers.12.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1224b2faeba4cf44088d46d41f77c7532029887b249497c5e3c09b9e28ade866
3
+ size 8388608
base.model.layers.12.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81c747cbfaaa8d96ec4a3d425587fb9a7ae2d209ca3ea1b99c8387ce495aaca
3
+ size 4194304
base.model.layers.13.input_layernorm.weight ADDED
Binary file (4.1 kB). View file
 
base.model.layers.13.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d2a453e05b261315b0e189bf7cd51db133fcaed33efdc791447b6a9bf0adb1
3
+ size 25165824
base.model.layers.13.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55aeb6a4130a063afe98faa91a76b40f775a3a570bf1ad07621e62b014ce3244
3
+ size 25165824