Hugging Face's logo

lmdeploy
/
turbomind-internlm-chat-7b-w4

Model card Files
xet
Community
2
unsubscribe commited on
Commit
f912ca4
·
1 Parent(s): ec14ead

fix

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 +339 -0
  2. model_repository/postprocessing +1 -0
  3. model_repository/preprocessing +1 -0
  4. model_repository/turbomind +1 -0
  5. triton_models/interactive/1/weights +1 -0
  6. triton_models/postprocessing/1/tokenizer +1 -0
  7. triton_models/preprocessing/1/tokenizer +1 -0
  8. triton_models/weights/config.ini +3 -0
  9. triton_models/weights/layers.0.attention.w_qkv.0.bias +3 -0
  10. triton_models/weights/layers.0.attention.wo.0.bias +0 -0
  11. triton_models/weights/layers.0.attention.wo.0.scales_zeros +0 -0
  12. triton_models/weights/layers.0.attention_norm.weight +3 -0
  13. triton_models/weights/layers.0.feed_forward.w13.0.qweight +3 -0
  14. triton_models/weights/layers.0.feed_forward.w13.0.scales_zeros +3 -0
  15. triton_models/weights/layers.0.feed_forward.w2.0.qweight +3 -0
  16. triton_models/weights/layers.0.feed_forward.w2.0.scales_zeros +3 -0
  17. triton_models/weights/layers.0.ffn_norm.weight +0 -0
  18. triton_models/weights/layers.1.attention.w_qkv.0.bias +3 -0
  19. triton_models/weights/layers.1.attention.w_qkv.0.scales_zeros +3 -0
  20. triton_models/weights/layers.1.attention.wo.0.bias +3 -0
  21. triton_models/weights/layers.1.attention.wo.0.qweight +3 -0
  22. triton_models/weights/layers.1.attention.wo.0.scales_zeros +0 -0
  23. triton_models/weights/layers.1.attention_norm.weight +3 -0
  24. triton_models/weights/layers.1.feed_forward.w13.0.qweight +3 -0
  25. triton_models/weights/layers.1.feed_forward.w13.0.scales_zeros +3 -0
  26. triton_models/weights/layers.1.feed_forward.w2.0.qweight +3 -0
  27. triton_models/weights/layers.1.ffn_norm.weight +0 -0
  28. triton_models/weights/layers.10.attention.w_qkv.0.bias +3 -0
  29. triton_models/weights/layers.10.attention.w_qkv.0.qweight +3 -0
  30. triton_models/weights/layers.10.attention.wo.0.bias +3 -0
  31. triton_models/weights/layers.10.attention.wo.0.qweight +3 -0
  32. triton_models/weights/layers.10.attention.wo.0.scales_zeros +0 -0
  33. triton_models/weights/layers.10.attention_norm.weight +3 -0
  34. triton_models/weights/layers.10.feed_forward.w13.0.scales_zeros +3 -0
  35. triton_models/weights/layers.10.feed_forward.w2.0.qweight +3 -0
  36. triton_models/weights/layers.10.feed_forward.w2.0.scales_zeros +3 -0
  37. triton_models/weights/layers.10.ffn_norm.weight +3 -0
  38. triton_models/weights/layers.11.attention.w_qkv.0.bias +3 -0
  39. triton_models/weights/layers.11.attention.w_qkv.0.qweight +3 -0
  40. triton_models/weights/layers.11.attention.w_qkv.0.scales_zeros +3 -0
  41. triton_models/weights/layers.11.attention.wo.0.bias +3 -0
  42. triton_models/weights/layers.11.attention.wo.0.qweight +3 -0
  43. triton_models/weights/layers.11.attention.wo.0.scales_zeros +0 -0
  44. triton_models/weights/layers.11.attention_norm.weight +3 -0
  45. triton_models/weights/layers.11.feed_forward.w13.0.scales_zeros +3 -0
  46. triton_models/weights/layers.11.feed_forward.w2.0.qweight +3 -0
  47. triton_models/weights/layers.11.feed_forward.w2.0.scales_zeros +3 -0
  48. triton_models/weights/layers.11.ffn_norm.weight +3 -0
  49. triton_models/weights/layers.12.attention.w_qkv.0.bias +0 -0
  50. triton_models/weights/layers.12.attention.w_qkv.0.qweight +3 -0
.gitattributes CHANGED
@@ -87,3 +87,342 @@ triton_models/weights/layers.5.feed_forward.w2.0.scales_zeros filter=lfs diff=lf
87
  triton_models/weights/layers.7.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
88
  triton_models/weights/layers.8.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
89
  triton_models/weights/layers.9.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  triton_models/weights/layers.7.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
88
  triton_models/weights/layers.8.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
89
  triton_models/weights/layers.9.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
90
+ triton_models/weights filter=lfs diff=lfs merge=lfs -text
91
+ triton_models/interactive filter=lfs diff=lfs merge=lfs -text
92
+ triton_models/postprocessing filter=lfs diff=lfs merge=lfs -text
93
+ triton_models/preprocessing filter=lfs diff=lfs merge=lfs -text
94
+ triton_models/tokenizer filter=lfs diff=lfs merge=lfs -text
95
+ triton_models/weights/layers.19.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
96
+ triton_models/weights/layers.21.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
97
+ triton_models/weights/layers.24.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
98
+ triton_models/weights/layers.31.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
99
+ triton_models/weights/layers.4.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
100
+ triton_models/weights/layers.4.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
101
+ triton_models/weights/layers.6.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
102
+ triton_models/weights/layers.0.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
103
+ triton_models/weights/layers.24.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
104
+ triton_models/weights/layers.2.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
105
+ triton_models/weights/layers.3.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
106
+ triton_models/weights/layers.7.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
107
+ triton_models/weights/layers.28.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
108
+ triton_models/weights/layers.7.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
109
+ triton_models/weights/norm.weight filter=lfs diff=lfs merge=lfs -text
110
+ triton_models/weights/layers.1.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
111
+ triton_models/weights/layers.23.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
112
+ triton_models/weights/layers.9.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
113
+ triton_models/weights/config.ini filter=lfs diff=lfs merge=lfs -text
114
+ triton_models/weights/layers.11.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
115
+ triton_models/weights/layers.27.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
116
+ triton_models/weights/layers.29.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
117
+ triton_models/weights/layers.29.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
118
+ triton_models/weights/layers.23.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
119
+ triton_models/weights/layers.26.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
120
+ triton_models/weights/layers.2.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
121
+ triton_models/weights/layers.9.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
122
+ triton_models/weights/layers.0.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
123
+ triton_models/weights/layers.2.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
124
+ triton_models/weights/layers.13.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
125
+ triton_models/weights/layers.15.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
126
+ triton_models/weights/layers.16.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
127
+ triton_models/weights/layers.22.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
128
+ triton_models/weights/layers.23.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
129
+ triton_models/weights/layers.23.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
130
+ triton_models/weights/layers.26.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
131
+ triton_models/weights/layers.12.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
132
+ triton_models/weights/layers.16.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
133
+ triton_models/weights/layers.19.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
134
+ triton_models/weights/layers.26.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
135
+ triton_models/weights/layers.26.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
136
+ triton_models/weights/layers.19.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
137
+ triton_models/weights/layers.21.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
138
+ triton_models/weights/layers.8.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
139
+ triton_models/weights/layers.15.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
140
+ triton_models/weights/layers.15.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
141
+ triton_models/weights/layers.27.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
142
+ triton_models/weights/layers.29.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
143
+ triton_models/weights/layers.2.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
144
+ triton_models/weights/layers.15.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
145
+ triton_models/weights/layers.22.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
146
+ triton_models/weights/layers.24.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
147
+ triton_models/weights/layers.25.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
148
+ triton_models/weights/layers.26.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
149
+ triton_models/weights/layers.28.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
150
+ triton_models/weights/layers.29.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
151
+ triton_models/weights/layers.2.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
152
+ triton_models/weights/layers.2.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
153
+ triton_models/weights/layers.9.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
154
+ triton_models/weights/layers.14.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
155
+ triton_models/weights/layers.24.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
156
+ triton_models/weights/layers.27.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
157
+ triton_models/weights/layers.2.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
158
+ triton_models/weights/layers.9.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
159
+ triton_models/weights/layers.10.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
160
+ triton_models/weights/layers.18.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
161
+ triton_models/weights/layers.20.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
162
+ triton_models/weights/layers.11.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
163
+ triton_models/weights/layers.5.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
164
+ triton_models/weights/layers.27.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
165
+ triton_models/weights/layers.31.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
166
+ triton_models/weights/layers.31.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
167
+ triton_models/weights/layers.5.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
168
+ triton_models/weights/layers.7.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
169
+ triton_models/weights/layers.20.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
170
+ triton_models/weights/layers.22.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
171
+ triton_models/weights/layers.25.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
172
+ triton_models/weights/layers.27.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
173
+ triton_models/weights/layers.27.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
174
+ triton_models/weights/layers.30.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
175
+ triton_models/weights/layers.9.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
176
+ triton_models/weights/layers.13.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
177
+ triton_models/weights/layers.19.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
178
+ triton_models/weights/layers.26.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
179
+ triton_models/weights/layers.7.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
180
+ triton_models/weights/layers.7.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
181
+ triton_models/weights/layers.13.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
182
+ triton_models/weights/layers.17.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
183
+ triton_models/weights/layers.22.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
184
+ triton_models/weights/layers.23.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
185
+ triton_models/weights/layers.24.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
186
+ triton_models/weights/layers.26.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
187
+ triton_models/weights/layers.11.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
188
+ triton_models/weights/layers.11.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
189
+ triton_models/weights/layers.12.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
190
+ triton_models/weights/layers.16.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
191
+ triton_models/weights/layers.17.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
192
+ triton_models/weights/layers.17.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
193
+ triton_models/weights/layers.31.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
194
+ triton_models/weights/layers.7.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
195
+ triton_models/weights/layers.9.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
196
+ triton_models/weights/layers.0.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
197
+ triton_models/weights/layers.16.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
198
+ triton_models/weights/layers.22.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
199
+ triton_models/weights/layers.25.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
200
+ triton_models/weights/layers.25.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
201
+ triton_models/weights/layers.26.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
202
+ triton_models/weights/layers.28.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
203
+ triton_models/weights/layers.29.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
204
+ triton_models/weights/layers.5.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
205
+ triton_models/weights/layers.10.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
206
+ triton_models/weights/layers.15.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
207
+ triton_models/weights/layers.20.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
208
+ triton_models/weights/layers.25.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
209
+ triton_models/weights/layers.25.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
210
+ triton_models/weights/layers.30.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
211
+ triton_models/weights/layers.0.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
212
+ triton_models/weights/layers.13.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
213
+ triton_models/weights/layers.17.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
214
+ triton_models/weights/layers.1.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
215
+ triton_models/weights/layers.2.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
216
+ triton_models/weights/layers.30.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
217
+ triton_models/weights/layers.31.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
218
+ triton_models/weights/layers.8.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
219
+ triton_models/weights/layers.10.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
220
+ triton_models/weights/layers.10.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
221
+ triton_models/weights/layers.11.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
222
+ triton_models/weights/layers.15.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
223
+ triton_models/weights/layers.17.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
224
+ triton_models/weights/layers.20.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
225
+ triton_models/weights/layers.2.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
226
+ triton_models/weights/layers.5.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
227
+ triton_models/weights/layers.5.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
228
+ triton_models/weights/layers.13.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
229
+ triton_models/weights/layers.27.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
230
+ triton_models/weights/layers.30.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
231
+ triton_models/weights/layers.4.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
232
+ triton_models/weights/layers.4.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
233
+ triton_models/weights/layers.6.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
234
+ triton_models/weights/layers.11.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
235
+ triton_models/weights/layers.3.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
236
+ triton_models/weights/layers.6.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
237
+ triton_models/weights/layers.9.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
238
+ triton_models/weights/layers.19.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
239
+ triton_models/weights/layers.4.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
240
+ triton_models/weights/layers.23.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
241
+ triton_models/weights/layers.23.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
242
+ triton_models/weights/layers.28.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
243
+ triton_models/weights/layers.7.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
244
+ triton_models/weights/layers.8.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
245
+ triton_models/weights/layers.20.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
246
+ triton_models/weights/layers.8.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
247
+ triton_models/weights/layers.11.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
248
+ triton_models/weights/layers.18.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
249
+ triton_models/weights/layers.24.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
250
+ triton_models/weights/layers.29.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
251
+ triton_models/weights/layers.29.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
252
+ triton_models/weights/layers.3.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
253
+ triton_models/weights/tok_embeddings.weight filter=lfs diff=lfs merge=lfs -text
254
+ triton_models/weights/layers.14.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
255
+ triton_models/weights/layers.16.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
256
+ triton_models/weights/layers.24.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
257
+ triton_models/weights/layers.7.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
258
+ triton_models/weights/layers.0.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
259
+ triton_models/weights/layers.11.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
260
+ triton_models/weights/layers.17.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
261
+ triton_models/weights/layers.23.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
262
+ triton_models/weights/layers.12.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
263
+ triton_models/weights/layers.13.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
264
+ triton_models/weights/layers.19.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
265
+ triton_models/weights/layers.21.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
266
+ triton_models/weights/layers.23.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
267
+ triton_models/weights/layers.28.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
268
+ triton_models/weights/layers.4.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
269
+ triton_models/weights/layers.4.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
270
+ triton_models/weights/layers.8.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
271
+ triton_models/weights/layers.11.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
272
+ triton_models/weights/layers.19.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
273
+ triton_models/weights/layers.22.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
274
+ triton_models/weights/layers.28.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
275
+ triton_models/weights/layers.3.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
276
+ triton_models/weights/layers.4.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
277
+ triton_models/weights/layers.4.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
278
+ triton_models/weights/layers.8.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
279
+ triton_models/weights/layers.8.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
280
+ triton_models/weights/layers.14.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
281
+ triton_models/weights/layers.23.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
282
+ triton_models/weights/layers.25.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
283
+ triton_models/weights/layers.6.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
284
+ triton_models/weights/layers.9.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
285
+ triton_models/weights/layers.0.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
286
+ triton_models/weights/layers.18.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
287
+ triton_models/weights/layers.19.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
288
+ triton_models/weights/layers.20.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
289
+ triton_models/weights/layers.21.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
290
+ triton_models/weights/layers.28.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
291
+ triton_models/weights/layers.31.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
292
+ triton_models/weights/layers.8.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
293
+ triton_models/weights/layers.9.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
294
+ triton_models/weights/layers.10.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
295
+ triton_models/weights/layers.18.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
296
+ triton_models/weights/layers.18.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
297
+ triton_models/weights/layers.1.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
298
+ triton_models/weights/layers.21.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
299
+ triton_models/weights/layers.21.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
300
+ triton_models/weights/layers.2.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
301
+ triton_models/weights/layers.31.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
302
+ triton_models/weights/layers.6.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
303
+ triton_models/weights/layers.12.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
304
+ triton_models/weights/layers.20.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
305
+ triton_models/weights/layers.28.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
306
+ triton_models/weights/layers.29.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
307
+ triton_models/weights/layers.13.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
308
+ triton_models/weights/layers.14.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
309
+ triton_models/weights/layers.1.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
310
+ triton_models/weights/layers.24.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
311
+ triton_models/weights/layers.28.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
312
+ triton_models/weights/layers.13.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
313
+ triton_models/weights/layers.3.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
314
+ triton_models/weights/layers.0.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
315
+ triton_models/weights/layers.10.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
316
+ triton_models/weights/layers.15.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
317
+ triton_models/weights/layers.18.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
318
+ triton_models/weights/layers.23.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
319
+ triton_models/weights/layers.28.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
320
+ triton_models/weights/layers.5.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
321
+ triton_models/weights/layers.12.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
322
+ triton_models/weights/layers.12.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
323
+ triton_models/weights/layers.17.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
324
+ triton_models/weights/layers.19.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
325
+ triton_models/weights/layers.20.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
326
+ triton_models/weights/layers.29.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
327
+ triton_models/weights/layers.3.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
328
+ triton_models/weights/layers.8.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
329
+ triton_models/weights/layers.0.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
330
+ triton_models/weights/layers.10.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
331
+ triton_models/weights/layers.18.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
332
+ triton_models/weights/layers.1.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
333
+ triton_models/weights/layers.16.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
334
+ triton_models/weights/layers.28.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
335
+ triton_models/weights/layers.3.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
336
+ triton_models/weights/layers.12.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
337
+ triton_models/weights/layers.14.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
338
+ triton_models/weights/layers.30.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
339
+ triton_models/weights/layers.30.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
340
+ triton_models/weights/layers.31.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
341
+ triton_models/weights/layers.1.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
342
+ triton_models/weights/layers.3.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
343
+ triton_models/weights/layers.4.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
344
+ triton_models/weights/layers.9.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
345
+ triton_models/weights/layers.22.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
346
+ triton_models/weights/layers.25.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
347
+ triton_models/weights/layers.9.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
348
+ triton_models/weights/layers.16.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
349
+ triton_models/weights/layers.21.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
350
+ triton_models/weights/layers.25.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
351
+ triton_models/weights/layers.12.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
352
+ triton_models/weights/layers.12.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
353
+ triton_models/weights/layers.17.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
354
+ triton_models/weights/layers.1.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
355
+ triton_models/weights/layers.30.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
356
+ triton_models/weights/layers.5.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
357
+ triton_models/weights/layers.6.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
358
+ triton_models/weights/layers.21.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
359
+ triton_models/weights/layers.30.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
360
+ triton_models/weights/layers.31.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
361
+ triton_models/weights/layers.3.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
362
+ triton_models/weights/layers.18.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
363
+ triton_models/weights/layers.26.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
364
+ triton_models/weights/layers.27.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
365
+ triton_models/weights/layers.11.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
366
+ triton_models/weights/layers.15.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
367
+ triton_models/weights/layers.22.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
368
+ triton_models/weights/layers.27.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
369
+ triton_models/weights/layers.6.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
370
+ triton_models/weights/layers.6.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
371
+ triton_models/weights/layers.8.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
372
+ triton_models/weights/layers.17.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
373
+ triton_models/weights/layers.22.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
374
+ triton_models/weights/layers.27.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
375
+ triton_models/weights/layers.29.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
376
+ triton_models/weights/layers.30.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
377
+ triton_models/weights/layers.10.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
378
+ triton_models/weights/layers.12.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
379
+ triton_models/weights/layers.17.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
380
+ triton_models/weights/layers.8.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
381
+ triton_models/weights/layers.22.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
382
+ triton_models/weights/layers.24.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
383
+ triton_models/weights/layers.30.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
384
+ triton_models/weights/layers.14.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
385
+ triton_models/weights/layers.19.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
386
+ triton_models/weights/layers.20.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
387
+ triton_models/weights/layers.25.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
388
+ triton_models/weights/layers.31.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
389
+ triton_models/weights/layers.5.feed_forward.w13.0.qweight filter=lfs diff=lfs merge=lfs -text
390
+ triton_models/weights/output.weight filter=lfs diff=lfs merge=lfs -text
391
+ triton_models/weights/layers.1.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
392
+ triton_models/weights/layers.3.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
393
+ triton_models/weights/layers.4.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
394
+ triton_models/weights/layers.10.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
395
+ triton_models/weights/layers.1.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
396
+ triton_models/weights/layers.30.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
397
+ triton_models/weights/layers.7.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
398
+ triton_models/weights/layers.14.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
399
+ triton_models/weights/layers.14.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
400
+ triton_models/weights/layers.15.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
401
+ triton_models/weights/layers.25.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
402
+ triton_models/weights/layers.27.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
403
+ triton_models/weights/layers.12.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
404
+ triton_models/weights/layers.13.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
405
+ triton_models/weights/layers.17.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
406
+ triton_models/weights/layers.1.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
407
+ triton_models/weights/layers.3.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
408
+ triton_models/weights/layers.7.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
409
+ triton_models/weights/layers.10.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
410
+ triton_models/weights/layers.24.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
411
+ triton_models/weights/layers.0.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
412
+ triton_models/weights/layers.16.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
413
+ triton_models/weights/layers.5.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
414
+ triton_models/weights/layers.6.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
415
+ triton_models/weights/layers.6.feed_forward.w2.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
416
+ triton_models/weights/layers.6.ffn_norm.weight filter=lfs diff=lfs merge=lfs -text
417
+ triton_models/weights/layers.7.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
418
+ triton_models/weights/layers.14.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
419
+ triton_models/weights/layers.20.attention.wo.0.bias filter=lfs diff=lfs merge=lfs -text
420
+ triton_models/weights/layers.6.attention.w_qkv.0.qweight filter=lfs diff=lfs merge=lfs -text
421
+ triton_models/weights/layers.11.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
422
+ triton_models/weights/layers.17.attention_norm.weight filter=lfs diff=lfs merge=lfs -text
423
+ triton_models/weights/layers.18.feed_forward.w2.0.qweight filter=lfs diff=lfs merge=lfs -text
424
+ triton_models/weights/layers.20.attention.w_qkv.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
425
+ triton_models/weights/layers.21.attention.wo.0.qweight filter=lfs diff=lfs merge=lfs -text
426
+ triton_models/weights/layers.22.attention.wo.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
427
+ triton_models/weights/layers.26.attention.w_qkv.0.bias filter=lfs diff=lfs merge=lfs -text
428
+ triton_models/weights/layers.5.feed_forward.w13.0.scales_zeros filter=lfs diff=lfs merge=lfs -text
model_repository/postprocessing ADDED
@@ -0,0 +1 @@
 
 
1
+ ../triton_models/postprocessing
model_repository/preprocessing ADDED
@@ -0,0 +1 @@
 
 
1
+ ../triton_models/preprocessing
model_repository/turbomind ADDED
@@ -0,0 +1 @@
 
 
1
+ ../triton_models/interactive
triton_models/interactive/1/weights ADDED
@@ -0,0 +1 @@
 
 
1
+ ../../weights
triton_models/postprocessing/1/tokenizer ADDED
@@ -0,0 +1 @@
 
 
1
+ ../../tokenizer
triton_models/preprocessing/1/tokenizer ADDED
@@ -0,0 +1 @@
 
 
1
+ ../../tokenizer
triton_models/weights/config.ini ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a850b8d6fbd6a6570d75ce8a82cf6e65bbae893da34a81130d09e9f3780c795
3
+ size 533
triton_models/weights/layers.0.attention.w_qkv.0.bias ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547f5579d9e162c0a7c9742da756e2ef2454693120286d6e657e89cf06c5cd64
3
+ size 24576
triton_models/weights/layers.0.attention.wo.0.bias CHANGED
Binary files a/triton_models/weights/layers.0.attention.wo.0.bias and b/triton_models/weights/layers.0.attention.wo.0.bias differ
 
triton_models/weights/layers.0.attention.wo.0.scales_zeros CHANGED
Binary files a/triton_models/weights/layers.0.attention.wo.0.scales_zeros and b/triton_models/weights/layers.0.attention.wo.0.scales_zeros differ
 
triton_models/weights/layers.0.attention_norm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5309c2a959a53b21c4b1f49f7c93daaf374b77f1c5c9f5fee8d12fa0c8707ac9
3
+ size 8192
triton_models/weights/layers.0.feed_forward.w13.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b45a7275d2fc9fdf7dd6b09efefcb80c0e3417b090f26917e437c7204ffd56bc
3
+ size 45088768
triton_models/weights/layers.0.feed_forward.w13.0.scales_zeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a5106824b6b0e662e92adaf846c7dd591dd4b443a41aea4724fe3b88105b22
3
+ size 2818048
triton_models/weights/layers.0.feed_forward.w2.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cbe17de514f024a9df3492fd7c8fcb2b1d51ca8a7f7159cd28b6379f534e3d1
3
+ size 22544384
triton_models/weights/layers.0.feed_forward.w2.0.scales_zeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85694cde4fcec6a6b33f6bb79a24861e537a179aa856ed0476c23e96c18d03f1
3
+ size 1409024
triton_models/weights/layers.0.ffn_norm.weight CHANGED
Binary files a/triton_models/weights/layers.0.ffn_norm.weight and b/triton_models/weights/layers.0.ffn_norm.weight differ
 
triton_models/weights/layers.1.attention.w_qkv.0.bias ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ca7a2b80c55e425dc25f70953457f2ac86045dbd5bd2c7d7c8b66a62b29100
3
+ size 24576
triton_models/weights/layers.1.attention.w_qkv.0.scales_zeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3c2e6037ed2c12636f4c43908aba1530f2be6223d507a4ffb9fe14b9bccb85
3
+ size 1572864
triton_models/weights/layers.1.attention.wo.0.bias ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c5e5d6dfbab21b80c849355f4570c97d003294213160102ad061015d2e8023
3
+ size 8192
triton_models/weights/layers.1.attention.wo.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999c68581392eda48ec0959d6f136ac0ede1415b8fb2d8543d2e43da6b9b5e8f
3
+ size 8388608
triton_models/weights/layers.1.attention.wo.0.scales_zeros CHANGED
Binary files a/triton_models/weights/layers.1.attention.wo.0.scales_zeros and b/triton_models/weights/layers.1.attention.wo.0.scales_zeros differ
 
triton_models/weights/layers.1.attention_norm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5429be888a4676503ca59739f1a0518d7e9f605c79b350a184e5fdd3ff97319
3
+ size 8192
triton_models/weights/layers.1.feed_forward.w13.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c65b9b6d3afaac783d6f2a7c20e75f416de95517d6fc5561671ee754dcc96633
3
+ size 45088768
triton_models/weights/layers.1.feed_forward.w13.0.scales_zeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc2e80dbc3bb15e9ac88267ca6ab236b7f111fdcadf5a1c7d80792578189fc69
3
+ size 2818048
triton_models/weights/layers.1.feed_forward.w2.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d7423a4cf64808fee78746af69549b334bd3744e7470f78688ce6e782823d26
3
+ size 22544384
triton_models/weights/layers.1.ffn_norm.weight CHANGED
Binary files a/triton_models/weights/layers.1.ffn_norm.weight and b/triton_models/weights/layers.1.ffn_norm.weight differ
 
triton_models/weights/layers.10.attention.w_qkv.0.bias ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdaacb6661143bcdad683d50cdecaefb70adac9e9f1bfe8cf4399e9394a563ef
3
+ size 24576
triton_models/weights/layers.10.attention.w_qkv.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5bcc888716d911ace609374ffbd45e700a29a6e219a29293ece57168bc3d7c1
3
+ size 25165824
triton_models/weights/layers.10.attention.wo.0.bias ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427302a6d0a0bcb68cb169c9985ea305b6234e54685e238d56b096155dfa2f23
3
+ size 8192
triton_models/weights/layers.10.attention.wo.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f47191f7bfd3444dd48fa791438f0ee97cc633ec63d60705101e9a58f0fde01
3
+ size 8388608
triton_models/weights/layers.10.attention.wo.0.scales_zeros CHANGED
Binary files a/triton_models/weights/layers.10.attention.wo.0.scales_zeros and b/triton_models/weights/layers.10.attention.wo.0.scales_zeros differ
 
triton_models/weights/layers.10.attention_norm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf5190cc4f0c1af1d01e83af56f0555c80ac9a60ac3ddbe3eb05540f75f23e7
3
+ size 8192
triton_models/weights/layers.10.feed_forward.w13.0.scales_zeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce2c913d673934f53e3a679636dac6f8579c5d98fc019eecabb2baa62bf57dfd
3
+ size 2818048
triton_models/weights/layers.10.feed_forward.w2.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ea488def05cc9c1bb2e6d1e882e8a0b373d2ad4a90ed6744b7361111bf8b66
3
+ size 22544384
triton_models/weights/layers.10.feed_forward.w2.0.scales_zeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216d21ebef71b462b2dcba01cd89ec65648d5307593e2b82d41c73b9f54f8960
3
+ size 1409024
triton_models/weights/layers.10.ffn_norm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d053c03d94746626943d65f8fdb6ba2d885134fcbd8f0e5e268be86fce4c8c
3
+ size 8192
triton_models/weights/layers.11.attention.w_qkv.0.bias ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6709641a530a8d6e3d5cc9e343ce22d5e48def0e27805554a737541cde37d003
3
+ size 24576
triton_models/weights/layers.11.attention.w_qkv.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5ba9c7c53edb796072a976adfdea59567d46b93e2bdd4eaf5f3b3cf8368b85
3
+ size 25165824
triton_models/weights/layers.11.attention.w_qkv.0.scales_zeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e784f9aff0ccf9a71ce884238b2097762f5ca3dcc807a2ff837f9057d0c5ab73
3
+ size 1572864
triton_models/weights/layers.11.attention.wo.0.bias ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516d43217f987517209e6c4cd70dcdce2a09dabf56005907f85fffc20e65fa21
3
+ size 8192
triton_models/weights/layers.11.attention.wo.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a1eafd71714a79f1775bdfa628d67a3bfa7b4cc3759349a4054cb11d728c8b
3
+ size 8388608
triton_models/weights/layers.11.attention.wo.0.scales_zeros CHANGED
Binary files a/triton_models/weights/layers.11.attention.wo.0.scales_zeros and b/triton_models/weights/layers.11.attention.wo.0.scales_zeros differ
 
triton_models/weights/layers.11.attention_norm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1383107953f2159d0f09c7e3fce1410330dea9995886ae3c1cec7f3443aeb0
3
+ size 8192
triton_models/weights/layers.11.feed_forward.w13.0.scales_zeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622bb760551cc76bb1a34e291a757149176b4b20fb399c2b26f841dfa834cc5c
3
+ size 2818048
triton_models/weights/layers.11.feed_forward.w2.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a2ef761ce21d7468b4b8941250a6390bb1aec98fa54b12ddf4dc398bcfb07d
3
+ size 22544384
triton_models/weights/layers.11.feed_forward.w2.0.scales_zeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a093e42e7bb1c4c80b54577d22a8428a79274ccd62667a9e2bbcbfe28630fa
3
+ size 1409024
triton_models/weights/layers.11.ffn_norm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f2e4a928640f3697388fad13ba06d344dc549c0d660cec49b68a1b2748ead6
3
+ size 8192
triton_models/weights/layers.12.attention.w_qkv.0.bias CHANGED
Binary files a/triton_models/weights/layers.12.attention.w_qkv.0.bias and b/triton_models/weights/layers.12.attention.w_qkv.0.bias differ
 
triton_models/weights/layers.12.attention.w_qkv.0.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e8f1f2b311380de70db967a7b4abb576df1ed31c36d40f69f4e6216fdc3965
3
+ size 25165824