jondurbin commited on
Commit
e6b91f9
1 Parent(s): 254460a

Upload pytorch_model.bin.index.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. pytorch_model.bin.index.json +49 -1
pytorch_model.bin.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 67487940608
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "pytorch_model-00007-of-00007.bin",
@@ -13,6 +13,7 @@
13
  "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
14
  "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
15
  "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
 
16
  "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
17
  "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
18
  "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
@@ -22,6 +23,7 @@
22
  "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
23
  "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
24
  "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
 
25
  "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
26
  "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
27
  "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -31,6 +33,7 @@
31
  "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
32
  "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
33
  "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
 
34
  "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
35
  "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
36
  "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -40,6 +43,7 @@
40
  "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
41
  "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
42
  "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
 
43
  "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
44
  "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
45
  "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -49,6 +53,7 @@
49
  "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
50
  "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
51
  "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
 
52
  "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
53
  "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
54
  "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -58,6 +63,7 @@
58
  "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
59
  "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
60
  "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
 
61
  "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
62
  "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
63
  "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -67,6 +73,7 @@
67
  "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
68
  "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
69
  "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
 
70
  "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
71
  "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
72
  "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -76,6 +83,7 @@
76
  "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
77
  "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
78
  "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
 
79
  "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
80
  "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
81
  "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -85,6 +93,7 @@
85
  "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
86
  "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
87
  "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
 
88
  "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
89
  "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
90
  "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -94,6 +103,7 @@
94
  "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
95
  "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
96
  "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
 
97
  "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
98
  "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
99
  "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -103,6 +113,7 @@
103
  "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
104
  "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
105
  "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
 
106
  "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
107
  "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
108
  "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
@@ -112,6 +123,7 @@
112
  "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
113
  "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
114
  "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
 
115
  "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
116
  "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
117
  "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
@@ -121,6 +133,7 @@
121
  "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
122
  "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
123
  "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
 
124
  "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
125
  "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
126
  "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -130,6 +143,7 @@
130
  "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
131
  "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
132
  "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
 
133
  "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
134
  "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
135
  "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -139,6 +153,7 @@
139
  "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
140
  "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
141
  "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
 
142
  "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
143
  "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
144
  "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -148,6 +163,7 @@
148
  "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
149
  "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
150
  "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
 
151
  "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
152
  "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
153
  "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -157,6 +173,7 @@
157
  "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
158
  "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
159
  "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
 
160
  "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
161
  "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
162
  "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -166,6 +183,7 @@
166
  "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
167
  "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
168
  "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
 
169
  "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
170
  "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
171
  "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -175,6 +193,7 @@
175
  "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
176
  "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
177
  "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
 
178
  "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
179
  "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
180
  "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
@@ -184,6 +203,7 @@
184
  "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
185
  "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
186
  "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
 
187
  "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
188
  "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
189
  "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -193,6 +213,7 @@
193
  "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
194
  "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
195
  "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
 
196
  "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
197
  "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
198
  "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -202,6 +223,7 @@
202
  "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
203
  "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
204
  "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
 
205
  "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
206
  "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
207
  "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -211,6 +233,7 @@
211
  "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
212
  "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
213
  "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
 
214
  "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
215
  "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
216
  "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
@@ -220,6 +243,7 @@
220
  "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
221
  "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
222
  "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
 
223
  "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
224
  "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
225
  "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -229,6 +253,7 @@
229
  "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
230
  "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
231
  "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
 
232
  "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
233
  "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
234
  "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -238,6 +263,7 @@
238
  "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
239
  "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
240
  "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
 
241
  "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
242
  "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
243
  "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -247,6 +273,7 @@
247
  "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
248
  "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
249
  "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
 
250
  "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
251
  "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
252
  "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
@@ -256,6 +283,7 @@
256
  "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
257
  "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
258
  "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
 
259
  "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
260
  "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
261
  "model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -265,6 +293,7 @@
265
  "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
266
  "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
267
  "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
 
268
  "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
269
  "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
270
  "model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -274,6 +303,7 @@
274
  "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
275
  "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
276
  "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
 
277
  "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
278
  "model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
279
  "model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -283,6 +313,7 @@
283
  "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
284
  "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
285
  "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
 
286
  "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
287
  "model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
288
  "model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -292,6 +323,7 @@
292
  "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
293
  "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
294
  "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
 
295
  "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
296
  "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
297
  "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -301,6 +333,7 @@
301
  "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
302
  "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
303
  "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
 
304
  "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
305
  "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
306
  "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -310,6 +343,7 @@
310
  "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
311
  "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
312
  "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
 
313
  "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
314
  "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
315
  "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
@@ -319,6 +353,7 @@
319
  "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
320
  "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
321
  "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
 
322
  "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
323
  "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
324
  "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
@@ -328,6 +363,7 @@
328
  "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
329
  "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
330
  "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
 
331
  "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
332
  "model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
333
  "model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -337,6 +373,7 @@
337
  "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
338
  "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
339
  "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
 
340
  "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
341
  "model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
342
  "model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -346,6 +383,7 @@
346
  "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
347
  "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
348
  "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
 
349
  "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
350
  "model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
351
  "model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -355,6 +393,7 @@
355
  "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
356
  "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
357
  "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
 
358
  "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
359
  "model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
360
  "model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -364,6 +403,7 @@
364
  "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
365
  "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
366
  "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
 
367
  "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
368
  "model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
369
  "model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -373,6 +413,7 @@
373
  "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
374
  "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
375
  "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
 
376
  "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
377
  "model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
378
  "model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -382,6 +423,7 @@
382
  "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
383
  "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
384
  "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
 
385
  "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
386
  "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
387
  "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
@@ -391,6 +433,7 @@
391
  "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
392
  "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
393
  "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
 
394
  "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
395
  "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
396
  "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
@@ -400,6 +443,7 @@
400
  "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
401
  "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
402
  "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
 
403
  "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
404
  "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
405
  "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -409,6 +453,7 @@
409
  "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
410
  "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
411
  "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
 
412
  "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
413
  "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
414
  "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -418,6 +463,7 @@
418
  "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
419
  "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
420
  "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
 
421
  "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
422
  "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
423
  "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -427,6 +473,7 @@
427
  "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
428
  "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
429
  "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
 
430
  "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
431
  "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
432
  "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
@@ -436,6 +483,7 @@
436
  "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
437
  "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
438
  "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
 
439
  "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
440
  "model.norm.weight": "pytorch_model-00007-of-00007.bin"
441
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 67487952896
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "pytorch_model-00007-of-00007.bin",
 
13
  "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
14
  "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
15
  "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
17
  "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
18
  "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
19
  "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
 
23
  "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
24
  "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
25
  "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
27
  "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
28
  "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
29
  "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
 
33
  "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
34
  "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
35
  "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
37
  "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
38
  "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
39
  "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
 
43
  "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
44
  "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
45
  "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
47
  "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
48
  "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
49
  "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
 
53
  "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
54
  "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
55
  "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
57
  "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
58
  "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
59
  "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
 
63
  "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
64
  "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
65
  "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
67
  "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
68
  "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
69
  "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
 
73
  "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
74
  "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
75
  "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
77
  "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
78
  "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
79
  "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
 
83
  "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
84
  "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
85
  "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
87
  "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
88
  "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
89
  "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
 
93
  "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
94
  "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
95
  "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
97
  "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
98
  "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
99
  "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
 
103
  "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
104
  "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
105
  "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
107
  "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
108
  "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
109
  "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
 
113
  "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
114
  "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
115
  "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
117
  "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
118
  "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
119
  "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
 
123
  "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
124
  "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
125
  "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
127
  "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
128
  "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
129
  "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
 
133
  "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
134
  "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
135
  "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
137
  "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
138
  "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
139
  "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
 
143
  "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
144
  "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
145
  "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
147
  "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
148
  "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
149
  "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
 
153
  "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
154
  "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
155
  "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
157
  "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
158
  "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
159
  "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
 
163
  "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
164
  "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
165
  "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
167
  "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
168
  "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
169
  "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
 
173
  "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
174
  "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
175
  "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
177
  "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
178
  "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
179
  "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
 
183
  "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
184
  "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
185
  "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
187
  "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
188
  "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
189
  "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
 
193
  "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
194
  "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
195
  "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
197
  "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
198
  "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
199
  "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
 
203
  "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
204
  "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
205
  "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
207
  "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
208
  "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
209
  "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
 
213
  "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
214
  "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
215
  "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
217
  "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
218
  "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
219
  "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
 
223
  "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
224
  "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
225
  "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
227
  "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
228
  "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
229
  "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
 
233
  "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
234
  "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
235
  "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
237
  "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
238
  "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
239
  "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
 
243
  "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
244
  "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
245
  "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
247
  "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
248
  "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
249
  "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
 
253
  "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
254
  "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
255
  "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
257
  "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
258
  "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
259
  "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
 
263
  "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
264
  "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
265
  "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
267
  "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
268
  "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
269
  "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
 
273
  "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
274
  "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
275
  "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
277
  "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
278
  "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
279
  "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
 
283
  "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
284
  "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
285
  "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
287
  "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
288
  "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
289
  "model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
 
293
  "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
294
  "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
295
  "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
297
  "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
298
  "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
299
  "model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
 
303
  "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
304
  "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
305
  "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
307
  "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
308
  "model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
309
  "model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
 
313
  "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
314
  "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
315
  "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
317
  "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
318
  "model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
319
  "model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
 
323
  "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
324
  "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
325
  "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
327
  "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
328
  "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
329
  "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
 
333
  "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
334
  "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
335
  "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
337
  "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
338
  "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
339
  "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
 
343
  "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
344
  "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
345
  "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
347
  "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
348
  "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
349
  "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
 
353
  "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
354
  "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
355
  "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
357
  "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
358
  "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
359
  "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
 
363
  "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
364
  "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
365
  "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
366
+ "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
367
  "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
368
  "model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
369
  "model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
 
373
  "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
374
  "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
375
  "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
376
+ "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
377
  "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
378
  "model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
379
  "model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
 
383
  "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
384
  "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
385
  "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
386
+ "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
387
  "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
388
  "model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
389
  "model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
 
393
  "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
394
  "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
395
  "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
396
+ "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
397
  "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
398
  "model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
399
  "model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
 
403
  "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
404
  "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
405
  "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
406
+ "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
407
  "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
408
  "model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
409
  "model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
 
413
  "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
414
  "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
415
  "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
416
+ "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
417
  "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
418
  "model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
419
  "model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
 
423
  "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
424
  "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
425
  "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
426
+ "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
427
  "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
428
  "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
429
  "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
 
433
  "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
434
  "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
435
  "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
436
+ "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
437
  "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
438
  "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
439
  "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
 
443
  "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
444
  "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
445
  "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
446
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
447
  "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
448
  "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
449
  "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
 
453
  "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
454
  "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
455
  "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
456
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
457
  "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
458
  "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
459
  "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
 
463
  "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
464
  "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
465
  "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
466
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
467
  "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
468
  "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
469
  "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
 
473
  "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
474
  "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
475
  "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
476
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
477
  "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
478
  "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
479
  "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
 
483
  "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
484
  "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
485
  "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
486
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
487
  "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
488
  "model.norm.weight": "pytorch_model-00007-of-00007.bin"
489
  }