Upload folder using huggingface_hub
Browse files- config.json +1 -48
- hf_quant_config.json +1 -48
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +48 -1
config.json
CHANGED
|
@@ -115,54 +115,7 @@
|
|
| 115 |
}
|
| 116 |
},
|
| 117 |
"ignore": [
|
| 118 |
-
"lm_head"
|
| 119 |
-
"model.layers.0.mlp.gate_proj",
|
| 120 |
-
"model.layers.1.mlp.shared_experts.gate_proj",
|
| 121 |
-
"model.layers.10.mlp.shared_experts.gate_proj",
|
| 122 |
-
"model.layers.11.mlp.shared_experts.gate_proj",
|
| 123 |
-
"model.layers.12.mlp.shared_experts.gate_proj",
|
| 124 |
-
"model.layers.13.mlp.shared_experts.gate_proj",
|
| 125 |
-
"model.layers.14.mlp.shared_experts.gate_proj",
|
| 126 |
-
"model.layers.15.mlp.shared_experts.gate_proj",
|
| 127 |
-
"model.layers.16.mlp.shared_experts.gate_proj",
|
| 128 |
-
"model.layers.17.mlp.shared_experts.gate_proj",
|
| 129 |
-
"model.layers.18.mlp.shared_experts.gate_proj",
|
| 130 |
-
"model.layers.19.mlp.shared_experts.gate_proj",
|
| 131 |
-
"model.layers.2.mlp.shared_experts.gate_proj",
|
| 132 |
-
"model.layers.20.mlp.shared_experts.gate_proj",
|
| 133 |
-
"model.layers.21.mlp.shared_experts.gate_proj",
|
| 134 |
-
"model.layers.22.mlp.shared_experts.gate_proj",
|
| 135 |
-
"model.layers.23.mlp.shared_experts.gate_proj",
|
| 136 |
-
"model.layers.24.mlp.shared_experts.gate_proj",
|
| 137 |
-
"model.layers.25.mlp.shared_experts.gate_proj",
|
| 138 |
-
"model.layers.26.mlp.shared_experts.gate_proj",
|
| 139 |
-
"model.layers.27.mlp.shared_experts.gate_proj",
|
| 140 |
-
"model.layers.28.mlp.shared_experts.gate_proj",
|
| 141 |
-
"model.layers.29.mlp.shared_experts.gate_proj",
|
| 142 |
-
"model.layers.3.mlp.shared_experts.gate_proj",
|
| 143 |
-
"model.layers.30.mlp.shared_experts.gate_proj",
|
| 144 |
-
"model.layers.31.mlp.shared_experts.gate_proj",
|
| 145 |
-
"model.layers.32.mlp.shared_experts.gate_proj",
|
| 146 |
-
"model.layers.33.mlp.shared_experts.gate_proj",
|
| 147 |
-
"model.layers.34.mlp.shared_experts.gate_proj",
|
| 148 |
-
"model.layers.35.mlp.shared_experts.gate_proj",
|
| 149 |
-
"model.layers.36.mlp.shared_experts.gate_proj",
|
| 150 |
-
"model.layers.37.mlp.shared_experts.gate_proj",
|
| 151 |
-
"model.layers.38.mlp.shared_experts.gate_proj",
|
| 152 |
-
"model.layers.39.mlp.shared_experts.gate_proj",
|
| 153 |
-
"model.layers.4.mlp.shared_experts.gate_proj",
|
| 154 |
-
"model.layers.40.mlp.shared_experts.gate_proj",
|
| 155 |
-
"model.layers.41.mlp.shared_experts.gate_proj",
|
| 156 |
-
"model.layers.42.mlp.shared_experts.gate_proj",
|
| 157 |
-
"model.layers.43.mlp.shared_experts.gate_proj",
|
| 158 |
-
"model.layers.44.mlp.shared_experts.gate_proj",
|
| 159 |
-
"model.layers.45.mlp.shared_experts.gate_proj",
|
| 160 |
-
"model.layers.46.mlp.shared_experts.gate_proj",
|
| 161 |
-
"model.layers.5.mlp.shared_experts.gate_proj",
|
| 162 |
-
"model.layers.6.mlp.shared_experts.gate_proj",
|
| 163 |
-
"model.layers.7.mlp.shared_experts.gate_proj",
|
| 164 |
-
"model.layers.8.mlp.shared_experts.gate_proj",
|
| 165 |
-
"model.layers.9.mlp.shared_experts.gate_proj"
|
| 166 |
],
|
| 167 |
"quant_algo": "W8A16",
|
| 168 |
"producer": {
|
|
|
|
| 115 |
}
|
| 116 |
},
|
| 117 |
"ignore": [
|
| 118 |
+
"lm_head"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
],
|
| 120 |
"quant_algo": "W8A16",
|
| 121 |
"producer": {
|
hf_quant_config.json
CHANGED
|
@@ -7,54 +7,7 @@
|
|
| 7 |
"quant_algo": "W8A16",
|
| 8 |
"kv_cache_quant_algo": null,
|
| 9 |
"exclude_modules": [
|
| 10 |
-
"lm_head"
|
| 11 |
-
"model.layers.0.mlp.gate_proj",
|
| 12 |
-
"model.layers.1.mlp.shared_experts.gate_proj",
|
| 13 |
-
"model.layers.10.mlp.shared_experts.gate_proj",
|
| 14 |
-
"model.layers.11.mlp.shared_experts.gate_proj",
|
| 15 |
-
"model.layers.12.mlp.shared_experts.gate_proj",
|
| 16 |
-
"model.layers.13.mlp.shared_experts.gate_proj",
|
| 17 |
-
"model.layers.14.mlp.shared_experts.gate_proj",
|
| 18 |
-
"model.layers.15.mlp.shared_experts.gate_proj",
|
| 19 |
-
"model.layers.16.mlp.shared_experts.gate_proj",
|
| 20 |
-
"model.layers.17.mlp.shared_experts.gate_proj",
|
| 21 |
-
"model.layers.18.mlp.shared_experts.gate_proj",
|
| 22 |
-
"model.layers.19.mlp.shared_experts.gate_proj",
|
| 23 |
-
"model.layers.2.mlp.shared_experts.gate_proj",
|
| 24 |
-
"model.layers.20.mlp.shared_experts.gate_proj",
|
| 25 |
-
"model.layers.21.mlp.shared_experts.gate_proj",
|
| 26 |
-
"model.layers.22.mlp.shared_experts.gate_proj",
|
| 27 |
-
"model.layers.23.mlp.shared_experts.gate_proj",
|
| 28 |
-
"model.layers.24.mlp.shared_experts.gate_proj",
|
| 29 |
-
"model.layers.25.mlp.shared_experts.gate_proj",
|
| 30 |
-
"model.layers.26.mlp.shared_experts.gate_proj",
|
| 31 |
-
"model.layers.27.mlp.shared_experts.gate_proj",
|
| 32 |
-
"model.layers.28.mlp.shared_experts.gate_proj",
|
| 33 |
-
"model.layers.29.mlp.shared_experts.gate_proj",
|
| 34 |
-
"model.layers.3.mlp.shared_experts.gate_proj",
|
| 35 |
-
"model.layers.30.mlp.shared_experts.gate_proj",
|
| 36 |
-
"model.layers.31.mlp.shared_experts.gate_proj",
|
| 37 |
-
"model.layers.32.mlp.shared_experts.gate_proj",
|
| 38 |
-
"model.layers.33.mlp.shared_experts.gate_proj",
|
| 39 |
-
"model.layers.34.mlp.shared_experts.gate_proj",
|
| 40 |
-
"model.layers.35.mlp.shared_experts.gate_proj",
|
| 41 |
-
"model.layers.36.mlp.shared_experts.gate_proj",
|
| 42 |
-
"model.layers.37.mlp.shared_experts.gate_proj",
|
| 43 |
-
"model.layers.38.mlp.shared_experts.gate_proj",
|
| 44 |
-
"model.layers.39.mlp.shared_experts.gate_proj",
|
| 45 |
-
"model.layers.4.mlp.shared_experts.gate_proj",
|
| 46 |
-
"model.layers.40.mlp.shared_experts.gate_proj",
|
| 47 |
-
"model.layers.41.mlp.shared_experts.gate_proj",
|
| 48 |
-
"model.layers.42.mlp.shared_experts.gate_proj",
|
| 49 |
-
"model.layers.43.mlp.shared_experts.gate_proj",
|
| 50 |
-
"model.layers.44.mlp.shared_experts.gate_proj",
|
| 51 |
-
"model.layers.45.mlp.shared_experts.gate_proj",
|
| 52 |
-
"model.layers.46.mlp.shared_experts.gate_proj",
|
| 53 |
-
"model.layers.5.mlp.shared_experts.gate_proj",
|
| 54 |
-
"model.layers.6.mlp.shared_experts.gate_proj",
|
| 55 |
-
"model.layers.7.mlp.shared_experts.gate_proj",
|
| 56 |
-
"model.layers.8.mlp.shared_experts.gate_proj",
|
| 57 |
-
"model.layers.9.mlp.shared_experts.gate_proj"
|
| 58 |
]
|
| 59 |
}
|
| 60 |
}
|
|
|
|
| 7 |
"quant_algo": "W8A16",
|
| 8 |
"kv_cache_quant_algo": null,
|
| 9 |
"exclude_modules": [
|
| 10 |
+
"lm_head"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
]
|
| 12 |
}
|
| 13 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d16fe9402a1d9d91bd042840e31cfa7dd9f7d13e685824387c7bf1d5a2d3001b
|
| 3 |
+
size 49695882864
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:385786ac66776950162d4e7b1da147f06ec68dfd297c1511a65b17d5a5812d3e
|
| 3 |
+
size 8676812696
|
model.safetensors.index.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"total_parameters": 29943390976,
|
| 4 |
-
"total_size":
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"lm_head.weight": "model-00001-of-00002.safetensors",
|
|
@@ -10,6 +10,7 @@
|
|
| 10 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
"model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 12 |
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 13 |
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
"model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 15 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -223,6 +224,7 @@
|
|
| 223 |
"model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
"model.layers.1.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 225 |
"model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 226 |
"model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
"model.layers.1.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 228 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -436,6 +438,7 @@
|
|
| 436 |
"model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 437 |
"model.layers.10.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 438 |
"model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 439 |
"model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 440 |
"model.layers.10.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 441 |
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -649,6 +652,7 @@
|
|
| 649 |
"model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 650 |
"model.layers.11.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 651 |
"model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 652 |
"model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
"model.layers.11.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 654 |
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -862,6 +866,7 @@
|
|
| 862 |
"model.layers.12.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 863 |
"model.layers.12.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 864 |
"model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 865 |
"model.layers.12.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 866 |
"model.layers.12.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 867 |
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -1075,6 +1080,7 @@
|
|
| 1075 |
"model.layers.13.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1076 |
"model.layers.13.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1077 |
"model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1078 |
"model.layers.13.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1079 |
"model.layers.13.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1080 |
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -1288,6 +1294,7 @@
|
|
| 1288 |
"model.layers.14.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1289 |
"model.layers.14.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1290 |
"model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1291 |
"model.layers.14.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1292 |
"model.layers.14.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1293 |
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -1501,6 +1508,7 @@
|
|
| 1501 |
"model.layers.15.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1502 |
"model.layers.15.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1503 |
"model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1504 |
"model.layers.15.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1505 |
"model.layers.15.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1506 |
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -1714,6 +1722,7 @@
|
|
| 1714 |
"model.layers.16.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1715 |
"model.layers.16.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1716 |
"model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1717 |
"model.layers.16.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1718 |
"model.layers.16.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1719 |
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -1927,6 +1936,7 @@
|
|
| 1927 |
"model.layers.17.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1928 |
"model.layers.17.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1929 |
"model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1930 |
"model.layers.17.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1931 |
"model.layers.17.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1932 |
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -2140,6 +2150,7 @@
|
|
| 2140 |
"model.layers.18.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 2141 |
"model.layers.18.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2142 |
"model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 2143 |
"model.layers.18.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 2144 |
"model.layers.18.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2145 |
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -2353,6 +2364,7 @@
|
|
| 2353 |
"model.layers.19.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 2354 |
"model.layers.19.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2355 |
"model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 2356 |
"model.layers.19.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 2357 |
"model.layers.19.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2358 |
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -2566,6 +2578,7 @@
|
|
| 2566 |
"model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 2567 |
"model.layers.2.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2568 |
"model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 2569 |
"model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 2570 |
"model.layers.2.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2571 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -2779,6 +2792,7 @@
|
|
| 2779 |
"model.layers.20.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 2780 |
"model.layers.20.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2781 |
"model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 2782 |
"model.layers.20.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 2783 |
"model.layers.20.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2784 |
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -2992,6 +3006,7 @@
|
|
| 2992 |
"model.layers.21.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 2993 |
"model.layers.21.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2994 |
"model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 2995 |
"model.layers.21.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 2996 |
"model.layers.21.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2997 |
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -3205,6 +3220,7 @@
|
|
| 3205 |
"model.layers.22.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 3206 |
"model.layers.22.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3207 |
"model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 3208 |
"model.layers.22.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 3209 |
"model.layers.22.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3210 |
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -3418,6 +3434,7 @@
|
|
| 3418 |
"model.layers.23.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 3419 |
"model.layers.23.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3420 |
"model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 3421 |
"model.layers.23.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 3422 |
"model.layers.23.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3423 |
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -3631,6 +3648,7 @@
|
|
| 3631 |
"model.layers.24.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 3632 |
"model.layers.24.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3633 |
"model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 3634 |
"model.layers.24.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 3635 |
"model.layers.24.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3636 |
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -3844,6 +3862,7 @@
|
|
| 3844 |
"model.layers.25.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 3845 |
"model.layers.25.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3846 |
"model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 3847 |
"model.layers.25.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 3848 |
"model.layers.25.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3849 |
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -4057,6 +4076,7 @@
|
|
| 4057 |
"model.layers.26.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4058 |
"model.layers.26.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4059 |
"model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4060 |
"model.layers.26.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4061 |
"model.layers.26.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4062 |
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -4270,6 +4290,7 @@
|
|
| 4270 |
"model.layers.27.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4271 |
"model.layers.27.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4272 |
"model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4273 |
"model.layers.27.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4274 |
"model.layers.27.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4275 |
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -4483,6 +4504,7 @@
|
|
| 4483 |
"model.layers.28.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4484 |
"model.layers.28.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4485 |
"model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4486 |
"model.layers.28.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4487 |
"model.layers.28.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4488 |
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -4696,6 +4718,7 @@
|
|
| 4696 |
"model.layers.29.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4697 |
"model.layers.29.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4698 |
"model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4699 |
"model.layers.29.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4700 |
"model.layers.29.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4701 |
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -4909,6 +4932,7 @@
|
|
| 4909 |
"model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4910 |
"model.layers.3.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4911 |
"model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4912 |
"model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4913 |
"model.layers.3.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4914 |
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -5122,6 +5146,7 @@
|
|
| 5122 |
"model.layers.30.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 5123 |
"model.layers.30.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5124 |
"model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 5125 |
"model.layers.30.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 5126 |
"model.layers.30.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5127 |
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -5335,6 +5360,7 @@
|
|
| 5335 |
"model.layers.31.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 5336 |
"model.layers.31.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5337 |
"model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 5338 |
"model.layers.31.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 5339 |
"model.layers.31.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5340 |
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -5548,6 +5574,7 @@
|
|
| 5548 |
"model.layers.32.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 5549 |
"model.layers.32.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5550 |
"model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 5551 |
"model.layers.32.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 5552 |
"model.layers.32.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5553 |
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -5761,6 +5788,7 @@
|
|
| 5761 |
"model.layers.33.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 5762 |
"model.layers.33.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5763 |
"model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 5764 |
"model.layers.33.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 5765 |
"model.layers.33.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5766 |
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -5974,6 +6002,7 @@
|
|
| 5974 |
"model.layers.34.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 5975 |
"model.layers.34.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5976 |
"model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 5977 |
"model.layers.34.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 5978 |
"model.layers.34.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5979 |
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -6187,6 +6216,7 @@
|
|
| 6187 |
"model.layers.35.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 6188 |
"model.layers.35.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6189 |
"model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 6190 |
"model.layers.35.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 6191 |
"model.layers.35.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6192 |
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -6400,6 +6430,7 @@
|
|
| 6400 |
"model.layers.36.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 6401 |
"model.layers.36.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6402 |
"model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 6403 |
"model.layers.36.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 6404 |
"model.layers.36.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6405 |
"model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -6613,6 +6644,7 @@
|
|
| 6613 |
"model.layers.37.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 6614 |
"model.layers.37.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6615 |
"model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 6616 |
"model.layers.37.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 6617 |
"model.layers.37.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6618 |
"model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -6826,6 +6858,7 @@
|
|
| 6826 |
"model.layers.38.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 6827 |
"model.layers.38.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6828 |
"model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 6829 |
"model.layers.38.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 6830 |
"model.layers.38.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6831 |
"model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -7039,6 +7072,7 @@
|
|
| 7039 |
"model.layers.39.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 7040 |
"model.layers.39.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7041 |
"model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 7042 |
"model.layers.39.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 7043 |
"model.layers.39.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7044 |
"model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -7252,6 +7286,7 @@
|
|
| 7252 |
"model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 7253 |
"model.layers.4.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7254 |
"model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 7255 |
"model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 7256 |
"model.layers.4.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7257 |
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -7465,6 +7500,7 @@
|
|
| 7465 |
"model.layers.40.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 7466 |
"model.layers.40.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7467 |
"model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 7468 |
"model.layers.40.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 7469 |
"model.layers.40.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7470 |
"model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
@@ -7678,6 +7714,7 @@
|
|
| 7678 |
"model.layers.41.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 7679 |
"model.layers.41.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7680 |
"model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 7681 |
"model.layers.41.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 7682 |
"model.layers.41.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7683 |
"model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
@@ -7891,6 +7928,7 @@
|
|
| 7891 |
"model.layers.42.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 7892 |
"model.layers.42.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7893 |
"model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 7894 |
"model.layers.42.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 7895 |
"model.layers.42.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7896 |
"model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
@@ -8104,6 +8142,7 @@
|
|
| 8104 |
"model.layers.43.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 8105 |
"model.layers.43.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8106 |
"model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 8107 |
"model.layers.43.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 8108 |
"model.layers.43.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8109 |
"model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
@@ -8317,6 +8356,7 @@
|
|
| 8317 |
"model.layers.44.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 8318 |
"model.layers.44.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8319 |
"model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 8320 |
"model.layers.44.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 8321 |
"model.layers.44.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8322 |
"model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
@@ -8530,6 +8570,7 @@
|
|
| 8530 |
"model.layers.45.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 8531 |
"model.layers.45.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8532 |
"model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 8533 |
"model.layers.45.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 8534 |
"model.layers.45.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8535 |
"model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
@@ -8743,6 +8784,7 @@
|
|
| 8743 |
"model.layers.46.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 8744 |
"model.layers.46.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8745 |
"model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 8746 |
"model.layers.46.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 8747 |
"model.layers.46.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8748 |
"model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
@@ -8956,6 +8998,7 @@
|
|
| 8956 |
"model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 8957 |
"model.layers.5.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 8958 |
"model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 8959 |
"model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 8960 |
"model.layers.5.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 8961 |
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -9169,6 +9212,7 @@
|
|
| 9169 |
"model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9170 |
"model.layers.6.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9171 |
"model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 9172 |
"model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 9173 |
"model.layers.6.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9174 |
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -9382,6 +9426,7 @@
|
|
| 9382 |
"model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9383 |
"model.layers.7.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9384 |
"model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 9385 |
"model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 9386 |
"model.layers.7.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9387 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -9595,6 +9640,7 @@
|
|
| 9595 |
"model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9596 |
"model.layers.8.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9597 |
"model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 9598 |
"model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 9599 |
"model.layers.8.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9600 |
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
@@ -9808,6 +9854,7 @@
|
|
| 9808 |
"model.layers.9.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9809 |
"model.layers.9.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9810 |
"model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 9811 |
"model.layers.9.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 9812 |
"model.layers.9.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9813 |
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"total_parameters": 29943390976,
|
| 4 |
+
"total_size": 58371456000
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"lm_head.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 10 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
"model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 12 |
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 14 |
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
"model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 16 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 224 |
"model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
"model.layers.1.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 226 |
"model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.1.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 228 |
"model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
"model.layers.1.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 230 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 438 |
"model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
"model.layers.10.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 440 |
"model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.layers.10.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 442 |
"model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 443 |
"model.layers.10.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 444 |
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 652 |
"model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
"model.layers.11.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 654 |
"model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.layers.11.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 656 |
"model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 657 |
"model.layers.11.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 658 |
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 866 |
"model.layers.12.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 867 |
"model.layers.12.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 868 |
"model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 869 |
+
"model.layers.12.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 870 |
"model.layers.12.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 871 |
"model.layers.12.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 872 |
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1080 |
"model.layers.13.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1081 |
"model.layers.13.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1082 |
"model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 1083 |
+
"model.layers.13.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1084 |
"model.layers.13.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1085 |
"model.layers.13.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1086 |
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1294 |
"model.layers.14.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1295 |
"model.layers.14.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1296 |
"model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 1297 |
+
"model.layers.14.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1298 |
"model.layers.14.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1299 |
"model.layers.14.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1300 |
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1508 |
"model.layers.15.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1509 |
"model.layers.15.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1510 |
"model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 1511 |
+
"model.layers.15.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1512 |
"model.layers.15.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1513 |
"model.layers.15.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1514 |
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1722 |
"model.layers.16.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1723 |
"model.layers.16.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1724 |
"model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 1725 |
+
"model.layers.16.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1726 |
"model.layers.16.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1727 |
"model.layers.16.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1728 |
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1936 |
"model.layers.17.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 1937 |
"model.layers.17.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1938 |
"model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 1939 |
+
"model.layers.17.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1940 |
"model.layers.17.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1941 |
"model.layers.17.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 1942 |
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 2150 |
"model.layers.18.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 2151 |
"model.layers.18.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2152 |
"model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 2153 |
+
"model.layers.18.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2154 |
"model.layers.18.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 2155 |
"model.layers.18.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2156 |
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 2364 |
"model.layers.19.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 2365 |
"model.layers.19.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2366 |
"model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 2367 |
+
"model.layers.19.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2368 |
"model.layers.19.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 2369 |
"model.layers.19.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2370 |
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 2578 |
"model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 2579 |
"model.layers.2.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2580 |
"model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 2581 |
+
"model.layers.2.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2582 |
"model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 2583 |
"model.layers.2.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2584 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 2792 |
"model.layers.20.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 2793 |
"model.layers.20.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2794 |
"model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 2795 |
+
"model.layers.20.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2796 |
"model.layers.20.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 2797 |
"model.layers.20.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 2798 |
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 3006 |
"model.layers.21.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 3007 |
"model.layers.21.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3008 |
"model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 3009 |
+
"model.layers.21.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3010 |
"model.layers.21.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 3011 |
"model.layers.21.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3012 |
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 3220 |
"model.layers.22.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 3221 |
"model.layers.22.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3222 |
"model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 3223 |
+
"model.layers.22.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3224 |
"model.layers.22.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 3225 |
"model.layers.22.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3226 |
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 3434 |
"model.layers.23.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 3435 |
"model.layers.23.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3436 |
"model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 3437 |
+
"model.layers.23.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3438 |
"model.layers.23.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 3439 |
"model.layers.23.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3440 |
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 3648 |
"model.layers.24.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 3649 |
"model.layers.24.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3650 |
"model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 3651 |
+
"model.layers.24.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3652 |
"model.layers.24.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 3653 |
"model.layers.24.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3654 |
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 3862 |
"model.layers.25.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 3863 |
"model.layers.25.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3864 |
"model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 3865 |
+
"model.layers.25.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3866 |
"model.layers.25.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 3867 |
"model.layers.25.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 3868 |
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4076 |
"model.layers.26.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4077 |
"model.layers.26.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4078 |
"model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 4079 |
+
"model.layers.26.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4080 |
"model.layers.26.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4081 |
"model.layers.26.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4082 |
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4290 |
"model.layers.27.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4291 |
"model.layers.27.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4292 |
"model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 4293 |
+
"model.layers.27.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4294 |
"model.layers.27.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4295 |
"model.layers.27.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4296 |
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4504 |
"model.layers.28.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4505 |
"model.layers.28.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4506 |
"model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 4507 |
+
"model.layers.28.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4508 |
"model.layers.28.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4509 |
"model.layers.28.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4510 |
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4718 |
"model.layers.29.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4719 |
"model.layers.29.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4720 |
"model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 4721 |
+
"model.layers.29.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4722 |
"model.layers.29.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4723 |
"model.layers.29.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4724 |
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 4932 |
"model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 4933 |
"model.layers.3.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4934 |
"model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 4935 |
+
"model.layers.3.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4936 |
"model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 4937 |
"model.layers.3.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 4938 |
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 5146 |
"model.layers.30.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 5147 |
"model.layers.30.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5148 |
"model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 5149 |
+
"model.layers.30.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5150 |
"model.layers.30.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 5151 |
"model.layers.30.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5152 |
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 5360 |
"model.layers.31.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 5361 |
"model.layers.31.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5362 |
"model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 5363 |
+
"model.layers.31.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5364 |
"model.layers.31.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 5365 |
"model.layers.31.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5366 |
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 5574 |
"model.layers.32.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 5575 |
"model.layers.32.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5576 |
"model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 5577 |
+
"model.layers.32.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5578 |
"model.layers.32.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 5579 |
"model.layers.32.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5580 |
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 5788 |
"model.layers.33.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 5789 |
"model.layers.33.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5790 |
"model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 5791 |
+
"model.layers.33.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5792 |
"model.layers.33.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 5793 |
"model.layers.33.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 5794 |
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 6002 |
"model.layers.34.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 6003 |
"model.layers.34.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6004 |
"model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 6005 |
+
"model.layers.34.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6006 |
"model.layers.34.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 6007 |
"model.layers.34.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6008 |
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 6216 |
"model.layers.35.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 6217 |
"model.layers.35.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6218 |
"model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 6219 |
+
"model.layers.35.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6220 |
"model.layers.35.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 6221 |
"model.layers.35.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6222 |
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 6430 |
"model.layers.36.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 6431 |
"model.layers.36.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6432 |
"model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 6433 |
+
"model.layers.36.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6434 |
"model.layers.36.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 6435 |
"model.layers.36.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6436 |
"model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 6644 |
"model.layers.37.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 6645 |
"model.layers.37.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6646 |
"model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 6647 |
+
"model.layers.37.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6648 |
"model.layers.37.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 6649 |
"model.layers.37.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6650 |
"model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 6858 |
"model.layers.38.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 6859 |
"model.layers.38.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6860 |
"model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 6861 |
+
"model.layers.38.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6862 |
"model.layers.38.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 6863 |
"model.layers.38.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 6864 |
"model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 7072 |
"model.layers.39.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 7073 |
"model.layers.39.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7074 |
"model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 7075 |
+
"model.layers.39.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7076 |
"model.layers.39.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 7077 |
"model.layers.39.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7078 |
"model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 7286 |
"model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 7287 |
"model.layers.4.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7288 |
"model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 7289 |
+
"model.layers.4.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7290 |
"model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 7291 |
"model.layers.4.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 7292 |
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 7500 |
"model.layers.40.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 7501 |
"model.layers.40.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7502 |
"model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 7503 |
+
"model.layers.40.mlp.shared_experts.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7504 |
"model.layers.40.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 7505 |
"model.layers.40.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7506 |
"model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 7714 |
"model.layers.41.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 7715 |
"model.layers.41.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7716 |
"model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 7717 |
+
"model.layers.41.mlp.shared_experts.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7718 |
"model.layers.41.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 7719 |
"model.layers.41.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7720 |
"model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 7928 |
"model.layers.42.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 7929 |
"model.layers.42.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7930 |
"model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 7931 |
+
"model.layers.42.mlp.shared_experts.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7932 |
"model.layers.42.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 7933 |
"model.layers.42.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 7934 |
"model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 8142 |
"model.layers.43.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 8143 |
"model.layers.43.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8144 |
"model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 8145 |
+
"model.layers.43.mlp.shared_experts.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8146 |
"model.layers.43.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 8147 |
"model.layers.43.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8148 |
"model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 8356 |
"model.layers.44.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 8357 |
"model.layers.44.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8358 |
"model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 8359 |
+
"model.layers.44.mlp.shared_experts.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8360 |
"model.layers.44.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 8361 |
"model.layers.44.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8362 |
"model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 8570 |
"model.layers.45.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 8571 |
"model.layers.45.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8572 |
"model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 8573 |
+
"model.layers.45.mlp.shared_experts.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8574 |
"model.layers.45.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 8575 |
"model.layers.45.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8576 |
"model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 8784 |
"model.layers.46.mlp.shared_experts.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 8785 |
"model.layers.46.mlp.shared_experts.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8786 |
"model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 8787 |
+
"model.layers.46.mlp.shared_experts.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8788 |
"model.layers.46.mlp.shared_experts.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 8789 |
"model.layers.46.mlp.shared_experts.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
| 8790 |
"model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 8998 |
"model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 8999 |
"model.layers.5.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9000 |
"model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 9001 |
+
"model.layers.5.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9002 |
"model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 9003 |
"model.layers.5.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9004 |
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 9212 |
"model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9213 |
"model.layers.6.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9214 |
"model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 9215 |
+
"model.layers.6.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9216 |
"model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 9217 |
"model.layers.6.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9218 |
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 9426 |
"model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9427 |
"model.layers.7.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9428 |
"model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 9429 |
+
"model.layers.7.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9430 |
"model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 9431 |
"model.layers.7.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9432 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 9640 |
"model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9641 |
"model.layers.8.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9642 |
"model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 9643 |
+
"model.layers.8.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9644 |
"model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 9645 |
"model.layers.8.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9646 |
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 9854 |
"model.layers.9.mlp.shared_experts.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9855 |
"model.layers.9.mlp.shared_experts.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9856 |
"model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 9857 |
+
"model.layers.9.mlp.shared_experts.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9858 |
"model.layers.9.mlp.shared_experts.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 9859 |
"model.layers.9.mlp.shared_experts.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
| 9860 |
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|