fancyfeast commited on
Commit
c4a952d
1 Parent(s): 43f43ea

Upload model.safetensors.index.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +55 -55
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 16959981696
4
  },
5
  "weight_map": {
6
  "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
@@ -77,33 +77,33 @@
77
  "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
  "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
  "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
- "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
- "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
- "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
- "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
- "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
  "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
  "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
  "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
  "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
- "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
- "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
- "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
- "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
- "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
- "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
- "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
- "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
- "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
  "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
99
  "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
100
  "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
101
  "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
102
  "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
103
- "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
- "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
- "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
- "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
  "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
  "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
  "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -185,33 +185,33 @@
185
  "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
  "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
  "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
- "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
- "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
  "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
- "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
- "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
  "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
  "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
  "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
  "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
- "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
- "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
- "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
- "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
- "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
- "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
- "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
- "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
- "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
  "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
207
  "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
208
- "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
  "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
210
  "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
211
- "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
- "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
- "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
- "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
  "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
  "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
  "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -239,33 +239,33 @@
239
  "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
240
  "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
241
  "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
242
- "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
- "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
  "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
  "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
- "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
  "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
  "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
  "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
  "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
- "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
- "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
- "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
- "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
- "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
- "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
- "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
- "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
- "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
  "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
261
  "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
262
- "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
- "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
  "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
265
- "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
- "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
- "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
- "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
  "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
270
  "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
271
  "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 17859440896
4
  },
5
  "weight_map": {
6
  "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
 
77
  "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
  "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
  "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
81
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
82
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
83
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
84
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
85
  "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
  "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
  "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
  "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
90
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
91
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
92
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
93
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
94
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
95
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
96
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
97
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
98
  "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
99
  "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
100
  "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
101
  "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
102
  "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
103
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
104
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
105
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
106
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
107
  "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
  "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
  "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
 
185
  "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
  "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
  "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
189
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
190
  "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
192
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
193
  "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
  "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
  "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
  "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
198
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
199
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
200
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
201
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
202
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
203
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
204
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
205
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
206
  "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
207
  "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
208
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
209
  "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
210
  "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
211
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
212
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
213
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
214
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
215
  "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
  "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
  "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
 
239
  "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
240
  "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
241
  "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
242
+ "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
243
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
244
  "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
  "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
247
  "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
  "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
  "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
  "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
252
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
253
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
254
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
255
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
256
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
257
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
258
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
259
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
260
  "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
261
  "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
262
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
263
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
264
  "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
265
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
266
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
267
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
268
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
269
  "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
270
  "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
271
  "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",