Upload GSAForCausalLM
Browse files- README.md +4 -4
- config.json +1 -2
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +32 -0
README.md
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
-
|
| 4 |
tags:
|
| 5 |
-
|
| 6 |
-
|
| 7 |
license: mit
|
| 8 |
datasets:
|
| 9 |
-
|
| 10 |
library_name: fla
|
| 11 |
---
|
| 12 |
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
+
- en
|
| 4 |
tags:
|
| 5 |
+
- text-generation
|
| 6 |
+
- gsa
|
| 7 |
license: mit
|
| 8 |
datasets:
|
| 9 |
+
- cerebras/SlimPajama-627B
|
| 10 |
library_name: fla
|
| 11 |
---
|
| 12 |
|
config.json
CHANGED
|
@@ -25,7 +25,6 @@
|
|
| 25 |
"max_position_embeddings": 2048,
|
| 26 |
"model_type": "gsa",
|
| 27 |
"norm_eps": 1e-06,
|
| 28 |
-
"norm_first": true,
|
| 29 |
"num_heads": 5,
|
| 30 |
"num_hidden_layers": 32,
|
| 31 |
"num_kv_heads": null,
|
|
@@ -41,4 +40,4 @@
|
|
| 41 |
"use_rope": false,
|
| 42 |
"use_short_conv": false,
|
| 43 |
"vocab_size": 32000
|
| 44 |
-
}
|
|
|
|
| 25 |
"max_position_embeddings": 2048,
|
| 26 |
"model_type": "gsa",
|
| 27 |
"norm_eps": 1e-06,
|
|
|
|
| 28 |
"num_heads": 5,
|
| 29 |
"num_hidden_layers": 32,
|
| 30 |
"num_kv_heads": null,
|
|
|
|
| 40 |
"use_rope": false,
|
| 41 |
"use_short_conv": false,
|
| 42 |
"vocab_size": 32000
|
| 43 |
+
}
|
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 sha256:61bf7abe9029bac6c2107a585d2fb86a406ef10b6c9c00388bdbedef20faad5a
|
| 3 |
+
size 4997466120
|
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:ad92f32fdda1162edeb0d1478c67fc779c66c85013e8cf82a0ae5f9bc9079bc1
|
| 3 |
+
size 458119208
|
model.safetensors.index.json
CHANGED
|
@@ -13,6 +13,7 @@
|
|
| 13 |
"model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 16 |
"model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
"model.layers.1.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
"model.layers.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -22,6 +23,7 @@
|
|
| 22 |
"model.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 25 |
"model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
"model.layers.10.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
"model.layers.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -31,6 +33,7 @@
|
|
| 31 |
"model.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 34 |
"model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
"model.layers.11.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
"model.layers.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -40,6 +43,7 @@
|
|
| 40 |
"model.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 43 |
"model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
"model.layers.12.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
"model.layers.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -49,6 +53,7 @@
|
|
| 49 |
"model.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 52 |
"model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
"model.layers.13.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
"model.layers.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -58,6 +63,7 @@
|
|
| 58 |
"model.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 61 |
"model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
"model.layers.14.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
"model.layers.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -67,6 +73,7 @@
|
|
| 67 |
"model.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 70 |
"model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
"model.layers.15.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
"model.layers.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -76,6 +83,7 @@
|
|
| 76 |
"model.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 77 |
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 79 |
"model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
"model.layers.16.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
"model.layers.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -85,6 +93,7 @@
|
|
| 85 |
"model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 88 |
"model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
"model.layers.17.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
"model.layers.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -94,6 +103,7 @@
|
|
| 94 |
"model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 97 |
"model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
"model.layers.18.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
"model.layers.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -103,6 +113,7 @@
|
|
| 103 |
"model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 106 |
"model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
"model.layers.19.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
"model.layers.19.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -112,6 +123,7 @@
|
|
| 112 |
"model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 115 |
"model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
"model.layers.2.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
"model.layers.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -121,6 +133,7 @@
|
|
| 121 |
"model.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 124 |
"model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
"model.layers.20.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
"model.layers.20.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -130,6 +143,7 @@
|
|
| 130 |
"model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 131 |
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 133 |
"model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
"model.layers.21.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
"model.layers.21.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -139,6 +153,7 @@
|
|
| 139 |
"model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 142 |
"model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 143 |
"model.layers.22.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
"model.layers.22.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -148,6 +163,7 @@
|
|
| 148 |
"model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 151 |
"model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 152 |
"model.layers.23.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
"model.layers.23.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -157,6 +173,7 @@
|
|
| 157 |
"model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 160 |
"model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 161 |
"model.layers.24.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
"model.layers.24.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -166,6 +183,7 @@
|
|
| 166 |
"model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 169 |
"model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 170 |
"model.layers.25.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
"model.layers.25.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -175,6 +193,7 @@
|
|
| 175 |
"model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 176 |
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 178 |
"model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 179 |
"model.layers.26.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
"model.layers.26.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -184,6 +203,7 @@
|
|
| 184 |
"model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 185 |
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 187 |
"model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 188 |
"model.layers.27.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
"model.layers.27.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -193,6 +213,7 @@
|
|
| 193 |
"model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 196 |
"model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 197 |
"model.layers.28.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
"model.layers.28.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -202,6 +223,7 @@
|
|
| 202 |
"model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 203 |
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 205 |
"model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 206 |
"model.layers.29.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
"model.layers.29.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -211,6 +233,7 @@
|
|
| 211 |
"model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 212 |
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 214 |
"model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 215 |
"model.layers.3.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
"model.layers.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -220,6 +243,7 @@
|
|
| 220 |
"model.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 221 |
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 223 |
"model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 224 |
"model.layers.30.attn.f_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
"model.layers.30.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -229,6 +253,7 @@
|
|
| 229 |
"model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 230 |
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 232 |
"model.layers.30.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
"model.layers.31.attn.f_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
"model.layers.31.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -238,6 +263,7 @@
|
|
| 238 |
"model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 239 |
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 241 |
"model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
| 242 |
"model.layers.4.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
"model.layers.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -247,6 +273,7 @@
|
|
| 247 |
"model.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 248 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 250 |
"model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 251 |
"model.layers.5.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
"model.layers.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -256,6 +283,7 @@
|
|
| 256 |
"model.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 259 |
"model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 260 |
"model.layers.6.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 261 |
"model.layers.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -265,6 +293,7 @@
|
|
| 265 |
"model.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 268 |
"model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 269 |
"model.layers.7.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
"model.layers.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -274,6 +303,7 @@
|
|
| 274 |
"model.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 275 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 277 |
"model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
"model.layers.8.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
"model.layers.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -283,6 +313,7 @@
|
|
| 283 |
"model.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 284 |
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 286 |
"model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 287 |
"model.layers.9.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
"model.layers.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -292,6 +323,7 @@
|
|
| 292 |
"model.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 295 |
"model.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 296 |
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 297 |
}
|
|
|
|
| 13 |
"model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
"model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
"model.layers.1.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
"model.layers.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 23 |
"model.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
"model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
"model.layers.10.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
"model.layers.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 33 |
"model.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
"model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
"model.layers.11.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
"model.layers.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 43 |
"model.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
"model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
"model.layers.12.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
"model.layers.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 53 |
"model.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
"model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
"model.layers.13.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
"model.layers.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 63 |
"model.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
"model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
"model.layers.14.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
"model.layers.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 73 |
"model.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
"model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 78 |
"model.layers.15.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
"model.layers.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 83 |
"model.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
"model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 88 |
"model.layers.16.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
"model.layers.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 93 |
"model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
"model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
"model.layers.17.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
"model.layers.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 103 |
"model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
"model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
"model.layers.18.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
"model.layers.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 113 |
"model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
"model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
"model.layers.19.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
"model.layers.19.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 123 |
"model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
"model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
"model.layers.2.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
"model.layers.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 133 |
"model.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
"model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 138 |
"model.layers.20.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
"model.layers.20.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 143 |
"model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 144 |
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
"model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
"model.layers.21.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
"model.layers.21.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 153 |
"model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
"model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
"model.layers.22.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
"model.layers.22.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 163 |
"model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 164 |
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
"model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
"model.layers.23.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
"model.layers.23.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 173 |
"model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 174 |
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
"model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
"model.layers.24.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
"model.layers.24.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 183 |
"model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 184 |
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
"model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 188 |
"model.layers.25.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
"model.layers.25.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 193 |
"model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
"model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 198 |
"model.layers.26.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
"model.layers.26.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 203 |
"model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 204 |
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
"model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 208 |
"model.layers.27.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
"model.layers.27.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 213 |
"model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
"model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 218 |
"model.layers.28.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
"model.layers.28.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 223 |
"model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 224 |
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
"model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 228 |
"model.layers.29.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
"model.layers.29.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 233 |
"model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
"model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 238 |
"model.layers.3.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
"model.layers.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 243 |
"model.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 244 |
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
"model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 248 |
"model.layers.30.attn.f_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
"model.layers.30.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 253 |
"model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 254 |
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
"model.layers.30.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
| 258 |
"model.layers.31.attn.f_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
"model.layers.31.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 263 |
"model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 264 |
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 265 |
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 267 |
"model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
| 268 |
"model.layers.4.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
"model.layers.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 273 |
"model.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 274 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
"model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
"model.layers.5.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
"model.layers.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 283 |
"model.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 284 |
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
"model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
"model.layers.6.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
"model.layers.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 293 |
"model.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 294 |
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 297 |
"model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 298 |
"model.layers.7.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
"model.layers.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 303 |
"model.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 304 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
"model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 308 |
"model.layers.8.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
"model.layers.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 313 |
"model.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 314 |
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
"model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 318 |
"model.layers.9.attn.f_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
"model.layers.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 323 |
"model.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
"model.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 328 |
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 329 |
}
|