Mayank Mishra
commited on
Commit
·
8f14620
1
Parent(s):
6bb0180
downcast to bf16
Browse files
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_function": "swiglu",
|
| 3 |
"add_bias": true,
|
| 4 |
"apply_residual_connection_post_layernorm": false,
|
|
@@ -20,6 +21,7 @@
|
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
"layer_norm_epsilon": 1e-05,
|
| 22 |
"model_type": "granite",
|
|
|
|
| 23 |
"n_embd": 2560,
|
| 24 |
"n_head": 32,
|
| 25 |
"n_inner": 10240,
|
|
@@ -33,7 +35,7 @@
|
|
| 33 |
"rope_theta": 10000,
|
| 34 |
"scale_attention_softmax_in_fp32": true,
|
| 35 |
"scale_attn_weights": true,
|
| 36 |
-
"torch_dtype": "
|
| 37 |
"transformers_version": "4.38.1",
|
| 38 |
"use_cache": true,
|
| 39 |
"vocab_size": 49152
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "granite-3b-code-base",
|
| 3 |
"activation_function": "swiglu",
|
| 4 |
"add_bias": true,
|
| 5 |
"apply_residual_connection_post_layernorm": false,
|
|
|
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"layer_norm_epsilon": 1e-05,
|
| 23 |
"model_type": "granite",
|
| 24 |
+
"multi_query": false,
|
| 25 |
"n_embd": 2560,
|
| 26 |
"n_head": 32,
|
| 27 |
"n_inner": 10240,
|
|
|
|
| 35 |
"rope_theta": 10000,
|
| 36 |
"scale_attention_softmax_in_fp32": true,
|
| 37 |
"scale_attn_weights": true,
|
| 38 |
+
"torch_dtype": "bfloat16",
|
| 39 |
"transformers_version": "4.38.1",
|
| 40 |
"use_cache": true,
|
| 41 |
"vocab_size": 49152
|
model-00001-of-00003.safetensors → model-00001-of-00002.safetensors
RENAMED
|
@@ -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:c68c29b3f0a88f6a60a53e2ba2f0c8c94c16f7adaf412981297bd54ed58abed4
|
| 3 |
+
size 4919566152
|
model-00002-of-00003.safetensors → model-00002-of-00002.safetensors
RENAMED
|
@@ -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 sha256:9c342afb52cc250f98581d9b2d079c273fdfdf7ab629f9c63ef11c140d6a2a9f
|
| 3 |
+
size 2045475816
|
model-00003-of-00003.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8c05dc3ccf273010235c01cadae113ec29a366a467cd78a5f2c46e713e2bedf3
|
| 3 |
-
size 4195850696
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors.index.json
CHANGED
|
@@ -1,329 +1,329 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"transformer.h.0.attn.c_attn.bias": "model-00001-of-
|
| 7 |
-
"transformer.h.0.attn.c_attn.weight": "model-00001-of-
|
| 8 |
-
"transformer.h.0.attn.c_proj.bias": "model-00001-of-
|
| 9 |
-
"transformer.h.0.attn.c_proj.weight": "model-00001-of-
|
| 10 |
-
"transformer.h.0.ln_1.weight": "model-00001-of-
|
| 11 |
-
"transformer.h.0.ln_2.weight": "model-00001-of-
|
| 12 |
-
"transformer.h.0.mlp.c_fc.bias": "model-00001-of-
|
| 13 |
-
"transformer.h.0.mlp.c_fc.weight": "model-00001-of-
|
| 14 |
-
"transformer.h.0.mlp.c_proj.bias": "model-00001-of-
|
| 15 |
-
"transformer.h.0.mlp.c_proj.weight": "model-00001-of-
|
| 16 |
-
"transformer.h.1.attn.c_attn.bias": "model-00001-of-
|
| 17 |
-
"transformer.h.1.attn.c_attn.weight": "model-00001-of-
|
| 18 |
-
"transformer.h.1.attn.c_proj.bias": "model-00001-of-
|
| 19 |
-
"transformer.h.1.attn.c_proj.weight": "model-00001-of-
|
| 20 |
-
"transformer.h.1.ln_1.weight": "model-00001-of-
|
| 21 |
-
"transformer.h.1.ln_2.weight": "model-00001-of-
|
| 22 |
-
"transformer.h.1.mlp.c_fc.bias": "model-00001-of-
|
| 23 |
-
"transformer.h.1.mlp.c_fc.weight": "model-00001-of-
|
| 24 |
-
"transformer.h.1.mlp.c_proj.bias": "model-00001-of-
|
| 25 |
-
"transformer.h.1.mlp.c_proj.weight": "model-00001-of-
|
| 26 |
-
"transformer.h.10.attn.c_attn.bias": "model-00001-of-
|
| 27 |
-
"transformer.h.10.attn.c_attn.weight": "model-00001-of-
|
| 28 |
-
"transformer.h.10.attn.c_proj.bias": "model-00001-of-
|
| 29 |
-
"transformer.h.10.attn.c_proj.weight": "model-00001-of-
|
| 30 |
-
"transformer.h.10.ln_1.weight": "model-00001-of-
|
| 31 |
-
"transformer.h.10.ln_2.weight": "model-00001-of-
|
| 32 |
-
"transformer.h.10.mlp.c_fc.bias": "model-
|
| 33 |
-
"transformer.h.10.mlp.c_fc.weight": "model-
|
| 34 |
-
"transformer.h.10.mlp.c_proj.bias": "model-
|
| 35 |
-
"transformer.h.10.mlp.c_proj.weight": "model-
|
| 36 |
-
"transformer.h.11.attn.c_attn.bias": "model-
|
| 37 |
-
"transformer.h.11.attn.c_attn.weight": "model-
|
| 38 |
-
"transformer.h.11.attn.c_proj.bias": "model-
|
| 39 |
-
"transformer.h.11.attn.c_proj.weight": "model-
|
| 40 |
-
"transformer.h.11.ln_1.weight": "model-
|
| 41 |
-
"transformer.h.11.ln_2.weight": "model-
|
| 42 |
-
"transformer.h.11.mlp.c_fc.bias": "model-
|
| 43 |
-
"transformer.h.11.mlp.c_fc.weight": "model-
|
| 44 |
-
"transformer.h.11.mlp.c_proj.bias": "model-
|
| 45 |
-
"transformer.h.11.mlp.c_proj.weight": "model-
|
| 46 |
-
"transformer.h.12.attn.c_attn.bias": "model-
|
| 47 |
-
"transformer.h.12.attn.c_attn.weight": "model-
|
| 48 |
-
"transformer.h.12.attn.c_proj.bias": "model-
|
| 49 |
-
"transformer.h.12.attn.c_proj.weight": "model-
|
| 50 |
-
"transformer.h.12.ln_1.weight": "model-
|
| 51 |
-
"transformer.h.12.ln_2.weight": "model-
|
| 52 |
-
"transformer.h.12.mlp.c_fc.bias": "model-
|
| 53 |
-
"transformer.h.12.mlp.c_fc.weight": "model-
|
| 54 |
-
"transformer.h.12.mlp.c_proj.bias": "model-
|
| 55 |
-
"transformer.h.12.mlp.c_proj.weight": "model-
|
| 56 |
-
"transformer.h.13.attn.c_attn.bias": "model-
|
| 57 |
-
"transformer.h.13.attn.c_attn.weight": "model-
|
| 58 |
-
"transformer.h.13.attn.c_proj.bias": "model-
|
| 59 |
-
"transformer.h.13.attn.c_proj.weight": "model-
|
| 60 |
-
"transformer.h.13.ln_1.weight": "model-
|
| 61 |
-
"transformer.h.13.ln_2.weight": "model-
|
| 62 |
-
"transformer.h.13.mlp.c_fc.bias": "model-
|
| 63 |
-
"transformer.h.13.mlp.c_fc.weight": "model-
|
| 64 |
-
"transformer.h.13.mlp.c_proj.bias": "model-
|
| 65 |
-
"transformer.h.13.mlp.c_proj.weight": "model-
|
| 66 |
-
"transformer.h.14.attn.c_attn.bias": "model-
|
| 67 |
-
"transformer.h.14.attn.c_attn.weight": "model-
|
| 68 |
-
"transformer.h.14.attn.c_proj.bias": "model-
|
| 69 |
-
"transformer.h.14.attn.c_proj.weight": "model-
|
| 70 |
-
"transformer.h.14.ln_1.weight": "model-
|
| 71 |
-
"transformer.h.14.ln_2.weight": "model-
|
| 72 |
-
"transformer.h.14.mlp.c_fc.bias": "model-
|
| 73 |
-
"transformer.h.14.mlp.c_fc.weight": "model-
|
| 74 |
-
"transformer.h.14.mlp.c_proj.bias": "model-
|
| 75 |
-
"transformer.h.14.mlp.c_proj.weight": "model-
|
| 76 |
-
"transformer.h.15.attn.c_attn.bias": "model-
|
| 77 |
-
"transformer.h.15.attn.c_attn.weight": "model-
|
| 78 |
-
"transformer.h.15.attn.c_proj.bias": "model-
|
| 79 |
-
"transformer.h.15.attn.c_proj.weight": "model-
|
| 80 |
-
"transformer.h.15.ln_1.weight": "model-
|
| 81 |
-
"transformer.h.15.ln_2.weight": "model-
|
| 82 |
-
"transformer.h.15.mlp.c_fc.bias": "model-
|
| 83 |
-
"transformer.h.15.mlp.c_fc.weight": "model-
|
| 84 |
-
"transformer.h.15.mlp.c_proj.bias": "model-
|
| 85 |
-
"transformer.h.15.mlp.c_proj.weight": "model-
|
| 86 |
-
"transformer.h.16.attn.c_attn.bias": "model-
|
| 87 |
-
"transformer.h.16.attn.c_attn.weight": "model-
|
| 88 |
-
"transformer.h.16.attn.c_proj.bias": "model-
|
| 89 |
-
"transformer.h.16.attn.c_proj.weight": "model-
|
| 90 |
-
"transformer.h.16.ln_1.weight": "model-
|
| 91 |
-
"transformer.h.16.ln_2.weight": "model-
|
| 92 |
-
"transformer.h.16.mlp.c_fc.bias": "model-
|
| 93 |
-
"transformer.h.16.mlp.c_fc.weight": "model-
|
| 94 |
-
"transformer.h.16.mlp.c_proj.bias": "model-
|
| 95 |
-
"transformer.h.16.mlp.c_proj.weight": "model-
|
| 96 |
-
"transformer.h.17.attn.c_attn.bias": "model-
|
| 97 |
-
"transformer.h.17.attn.c_attn.weight": "model-
|
| 98 |
-
"transformer.h.17.attn.c_proj.bias": "model-
|
| 99 |
-
"transformer.h.17.attn.c_proj.weight": "model-
|
| 100 |
-
"transformer.h.17.ln_1.weight": "model-
|
| 101 |
-
"transformer.h.17.ln_2.weight": "model-
|
| 102 |
-
"transformer.h.17.mlp.c_fc.bias": "model-
|
| 103 |
-
"transformer.h.17.mlp.c_fc.weight": "model-
|
| 104 |
-
"transformer.h.17.mlp.c_proj.bias": "model-
|
| 105 |
-
"transformer.h.17.mlp.c_proj.weight": "model-
|
| 106 |
-
"transformer.h.18.attn.c_attn.bias": "model-
|
| 107 |
-
"transformer.h.18.attn.c_attn.weight": "model-
|
| 108 |
-
"transformer.h.18.attn.c_proj.bias": "model-
|
| 109 |
-
"transformer.h.18.attn.c_proj.weight": "model-
|
| 110 |
-
"transformer.h.18.ln_1.weight": "model-
|
| 111 |
-
"transformer.h.18.ln_2.weight": "model-
|
| 112 |
-
"transformer.h.18.mlp.c_fc.bias": "model-
|
| 113 |
-
"transformer.h.18.mlp.c_fc.weight": "model-
|
| 114 |
-
"transformer.h.18.mlp.c_proj.bias": "model-
|
| 115 |
-
"transformer.h.18.mlp.c_proj.weight": "model-
|
| 116 |
-
"transformer.h.19.attn.c_attn.bias": "model-
|
| 117 |
-
"transformer.h.19.attn.c_attn.weight": "model-
|
| 118 |
-
"transformer.h.19.attn.c_proj.bias": "model-
|
| 119 |
-
"transformer.h.19.attn.c_proj.weight": "model-
|
| 120 |
-
"transformer.h.19.ln_1.weight": "model-
|
| 121 |
-
"transformer.h.19.ln_2.weight": "model-
|
| 122 |
-
"transformer.h.19.mlp.c_fc.bias": "model-
|
| 123 |
-
"transformer.h.19.mlp.c_fc.weight": "model-
|
| 124 |
-
"transformer.h.19.mlp.c_proj.bias": "model-
|
| 125 |
-
"transformer.h.19.mlp.c_proj.weight": "model-
|
| 126 |
-
"transformer.h.2.attn.c_attn.bias": "model-00001-of-
|
| 127 |
-
"transformer.h.2.attn.c_attn.weight": "model-00001-of-
|
| 128 |
-
"transformer.h.2.attn.c_proj.bias": "model-00001-of-
|
| 129 |
-
"transformer.h.2.attn.c_proj.weight": "model-00001-of-
|
| 130 |
-
"transformer.h.2.ln_1.weight": "model-00001-of-
|
| 131 |
-
"transformer.h.2.ln_2.weight": "model-00001-of-
|
| 132 |
-
"transformer.h.2.mlp.c_fc.bias": "model-00001-of-
|
| 133 |
-
"transformer.h.2.mlp.c_fc.weight": "model-00001-of-
|
| 134 |
-
"transformer.h.2.mlp.c_proj.bias": "model-00001-of-
|
| 135 |
-
"transformer.h.2.mlp.c_proj.weight": "model-00001-of-
|
| 136 |
-
"transformer.h.20.attn.c_attn.bias": "model-
|
| 137 |
-
"transformer.h.20.attn.c_attn.weight": "model-
|
| 138 |
-
"transformer.h.20.attn.c_proj.bias": "model-
|
| 139 |
-
"transformer.h.20.attn.c_proj.weight": "model-
|
| 140 |
-
"transformer.h.20.ln_1.weight": "model-
|
| 141 |
-
"transformer.h.20.ln_2.weight": "model-
|
| 142 |
-
"transformer.h.20.mlp.c_fc.bias": "model-
|
| 143 |
-
"transformer.h.20.mlp.c_fc.weight": "model-
|
| 144 |
-
"transformer.h.20.mlp.c_proj.bias": "model-
|
| 145 |
-
"transformer.h.20.mlp.c_proj.weight": "model-
|
| 146 |
-
"transformer.h.21.attn.c_attn.bias": "model-
|
| 147 |
-
"transformer.h.21.attn.c_attn.weight": "model-
|
| 148 |
-
"transformer.h.21.attn.c_proj.bias": "model-
|
| 149 |
-
"transformer.h.21.attn.c_proj.weight": "model-
|
| 150 |
-
"transformer.h.21.ln_1.weight": "model-
|
| 151 |
-
"transformer.h.21.ln_2.weight": "model-
|
| 152 |
-
"transformer.h.21.mlp.c_fc.bias": "model-
|
| 153 |
-
"transformer.h.21.mlp.c_fc.weight": "model-
|
| 154 |
-
"transformer.h.21.mlp.c_proj.bias": "model-
|
| 155 |
-
"transformer.h.21.mlp.c_proj.weight": "model-
|
| 156 |
-
"transformer.h.22.attn.c_attn.bias": "model-
|
| 157 |
-
"transformer.h.22.attn.c_attn.weight": "model-
|
| 158 |
-
"transformer.h.22.attn.c_proj.bias": "model-
|
| 159 |
-
"transformer.h.22.attn.c_proj.weight": "model-
|
| 160 |
-
"transformer.h.22.ln_1.weight": "model-
|
| 161 |
-
"transformer.h.22.ln_2.weight": "model-
|
| 162 |
-
"transformer.h.22.mlp.c_fc.bias": "model-
|
| 163 |
-
"transformer.h.22.mlp.c_fc.weight": "model-
|
| 164 |
-
"transformer.h.22.mlp.c_proj.bias": "model-
|
| 165 |
-
"transformer.h.22.mlp.c_proj.weight": "model-
|
| 166 |
-
"transformer.h.23.attn.c_attn.bias": "model-
|
| 167 |
-
"transformer.h.23.attn.c_attn.weight": "model-
|
| 168 |
-
"transformer.h.23.attn.c_proj.bias": "model-
|
| 169 |
-
"transformer.h.23.attn.c_proj.weight": "model-
|
| 170 |
-
"transformer.h.23.ln_1.weight": "model-
|
| 171 |
-
"transformer.h.23.ln_2.weight": "model-
|
| 172 |
-
"transformer.h.23.mlp.c_fc.bias": "model-
|
| 173 |
-
"transformer.h.23.mlp.c_fc.weight": "model-
|
| 174 |
-
"transformer.h.23.mlp.c_proj.bias": "model-
|
| 175 |
-
"transformer.h.23.mlp.c_proj.weight": "model-
|
| 176 |
-
"transformer.h.24.attn.c_attn.bias": "model-
|
| 177 |
-
"transformer.h.24.attn.c_attn.weight": "model-
|
| 178 |
-
"transformer.h.24.attn.c_proj.bias": "model-
|
| 179 |
-
"transformer.h.24.attn.c_proj.weight": "model-
|
| 180 |
-
"transformer.h.24.ln_1.weight": "model-
|
| 181 |
-
"transformer.h.24.ln_2.weight": "model-
|
| 182 |
-
"transformer.h.24.mlp.c_fc.bias": "model-
|
| 183 |
-
"transformer.h.24.mlp.c_fc.weight": "model-
|
| 184 |
-
"transformer.h.24.mlp.c_proj.bias": "model-
|
| 185 |
-
"transformer.h.24.mlp.c_proj.weight": "model-
|
| 186 |
-
"transformer.h.25.attn.c_attn.bias": "model-
|
| 187 |
-
"transformer.h.25.attn.c_attn.weight": "model-
|
| 188 |
-
"transformer.h.25.attn.c_proj.bias": "model-
|
| 189 |
-
"transformer.h.25.attn.c_proj.weight": "model-
|
| 190 |
-
"transformer.h.25.ln_1.weight": "model-
|
| 191 |
-
"transformer.h.25.ln_2.weight": "model-
|
| 192 |
-
"transformer.h.25.mlp.c_fc.bias": "model-
|
| 193 |
-
"transformer.h.25.mlp.c_fc.weight": "model-
|
| 194 |
-
"transformer.h.25.mlp.c_proj.bias": "model-
|
| 195 |
-
"transformer.h.25.mlp.c_proj.weight": "model-
|
| 196 |
-
"transformer.h.26.attn.c_attn.bias": "model-
|
| 197 |
-
"transformer.h.26.attn.c_attn.weight": "model-
|
| 198 |
-
"transformer.h.26.attn.c_proj.bias": "model-
|
| 199 |
-
"transformer.h.26.attn.c_proj.weight": "model-
|
| 200 |
-
"transformer.h.26.ln_1.weight": "model-
|
| 201 |
-
"transformer.h.26.ln_2.weight": "model-
|
| 202 |
-
"transformer.h.26.mlp.c_fc.bias": "model-
|
| 203 |
-
"transformer.h.26.mlp.c_fc.weight": "model-
|
| 204 |
-
"transformer.h.26.mlp.c_proj.bias": "model-
|
| 205 |
-
"transformer.h.26.mlp.c_proj.weight": "model-
|
| 206 |
-
"transformer.h.27.attn.c_attn.bias": "model-
|
| 207 |
-
"transformer.h.27.attn.c_attn.weight": "model-
|
| 208 |
-
"transformer.h.27.attn.c_proj.bias": "model-
|
| 209 |
-
"transformer.h.27.attn.c_proj.weight": "model-
|
| 210 |
-
"transformer.h.27.ln_1.weight": "model-
|
| 211 |
-
"transformer.h.27.ln_2.weight": "model-
|
| 212 |
-
"transformer.h.27.mlp.c_fc.bias": "model-
|
| 213 |
-
"transformer.h.27.mlp.c_fc.weight": "model-
|
| 214 |
-
"transformer.h.27.mlp.c_proj.bias": "model-
|
| 215 |
-
"transformer.h.27.mlp.c_proj.weight": "model-
|
| 216 |
-
"transformer.h.28.attn.c_attn.bias": "model-
|
| 217 |
-
"transformer.h.28.attn.c_attn.weight": "model-
|
| 218 |
-
"transformer.h.28.attn.c_proj.bias": "model-
|
| 219 |
-
"transformer.h.28.attn.c_proj.weight": "model-
|
| 220 |
-
"transformer.h.28.ln_1.weight": "model-
|
| 221 |
-
"transformer.h.28.ln_2.weight": "model-
|
| 222 |
-
"transformer.h.28.mlp.c_fc.bias": "model-
|
| 223 |
-
"transformer.h.28.mlp.c_fc.weight": "model-
|
| 224 |
-
"transformer.h.28.mlp.c_proj.bias": "model-
|
| 225 |
-
"transformer.h.28.mlp.c_proj.weight": "model-
|
| 226 |
-
"transformer.h.29.attn.c_attn.bias": "model-
|
| 227 |
-
"transformer.h.29.attn.c_attn.weight": "model-
|
| 228 |
-
"transformer.h.29.attn.c_proj.bias": "model-
|
| 229 |
-
"transformer.h.29.attn.c_proj.weight": "model-
|
| 230 |
-
"transformer.h.29.ln_1.weight": "model-
|
| 231 |
-
"transformer.h.29.ln_2.weight": "model-
|
| 232 |
-
"transformer.h.29.mlp.c_fc.bias": "model-
|
| 233 |
-
"transformer.h.29.mlp.c_fc.weight": "model-
|
| 234 |
-
"transformer.h.29.mlp.c_proj.bias": "model-
|
| 235 |
-
"transformer.h.29.mlp.c_proj.weight": "model-
|
| 236 |
-
"transformer.h.3.attn.c_attn.bias": "model-00001-of-
|
| 237 |
-
"transformer.h.3.attn.c_attn.weight": "model-00001-of-
|
| 238 |
-
"transformer.h.3.attn.c_proj.bias": "model-00001-of-
|
| 239 |
-
"transformer.h.3.attn.c_proj.weight": "model-00001-of-
|
| 240 |
-
"transformer.h.3.ln_1.weight": "model-00001-of-
|
| 241 |
-
"transformer.h.3.ln_2.weight": "model-00001-of-
|
| 242 |
-
"transformer.h.3.mlp.c_fc.bias": "model-00001-of-
|
| 243 |
-
"transformer.h.3.mlp.c_fc.weight": "model-00001-of-
|
| 244 |
-
"transformer.h.3.mlp.c_proj.bias": "model-00001-of-
|
| 245 |
-
"transformer.h.3.mlp.c_proj.weight": "model-00001-of-
|
| 246 |
-
"transformer.h.30.attn.c_attn.bias": "model-
|
| 247 |
-
"transformer.h.30.attn.c_attn.weight": "model-
|
| 248 |
-
"transformer.h.30.attn.c_proj.bias": "model-
|
| 249 |
-
"transformer.h.30.attn.c_proj.weight": "model-
|
| 250 |
-
"transformer.h.30.ln_1.weight": "model-
|
| 251 |
-
"transformer.h.30.ln_2.weight": "model-
|
| 252 |
-
"transformer.h.30.mlp.c_fc.bias": "model-
|
| 253 |
-
"transformer.h.30.mlp.c_fc.weight": "model-
|
| 254 |
-
"transformer.h.30.mlp.c_proj.bias": "model-
|
| 255 |
-
"transformer.h.30.mlp.c_proj.weight": "model-
|
| 256 |
-
"transformer.h.31.attn.c_attn.bias": "model-
|
| 257 |
-
"transformer.h.31.attn.c_attn.weight": "model-
|
| 258 |
-
"transformer.h.31.attn.c_proj.bias": "model-
|
| 259 |
-
"transformer.h.31.attn.c_proj.weight": "model-
|
| 260 |
-
"transformer.h.31.ln_1.weight": "model-
|
| 261 |
-
"transformer.h.31.ln_2.weight": "model-
|
| 262 |
-
"transformer.h.31.mlp.c_fc.bias": "model-
|
| 263 |
-
"transformer.h.31.mlp.c_fc.weight": "model-
|
| 264 |
-
"transformer.h.31.mlp.c_proj.bias": "model-
|
| 265 |
-
"transformer.h.31.mlp.c_proj.weight": "model-
|
| 266 |
-
"transformer.h.4.attn.c_attn.bias": "model-00001-of-
|
| 267 |
-
"transformer.h.4.attn.c_attn.weight": "model-00001-of-
|
| 268 |
-
"transformer.h.4.attn.c_proj.bias": "model-00001-of-
|
| 269 |
-
"transformer.h.4.attn.c_proj.weight": "model-00001-of-
|
| 270 |
-
"transformer.h.4.ln_1.weight": "model-00001-of-
|
| 271 |
-
"transformer.h.4.ln_2.weight": "model-00001-of-
|
| 272 |
-
"transformer.h.4.mlp.c_fc.bias": "model-00001-of-
|
| 273 |
-
"transformer.h.4.mlp.c_fc.weight": "model-00001-of-
|
| 274 |
-
"transformer.h.4.mlp.c_proj.bias": "model-00001-of-
|
| 275 |
-
"transformer.h.4.mlp.c_proj.weight": "model-00001-of-
|
| 276 |
-
"transformer.h.5.attn.c_attn.bias": "model-00001-of-
|
| 277 |
-
"transformer.h.5.attn.c_attn.weight": "model-00001-of-
|
| 278 |
-
"transformer.h.5.attn.c_proj.bias": "model-00001-of-
|
| 279 |
-
"transformer.h.5.attn.c_proj.weight": "model-00001-of-
|
| 280 |
-
"transformer.h.5.ln_1.weight": "model-00001-of-
|
| 281 |
-
"transformer.h.5.ln_2.weight": "model-00001-of-
|
| 282 |
-
"transformer.h.5.mlp.c_fc.bias": "model-00001-of-
|
| 283 |
-
"transformer.h.5.mlp.c_fc.weight": "model-00001-of-
|
| 284 |
-
"transformer.h.5.mlp.c_proj.bias": "model-00001-of-
|
| 285 |
-
"transformer.h.5.mlp.c_proj.weight": "model-00001-of-
|
| 286 |
-
"transformer.h.6.attn.c_attn.bias": "model-00001-of-
|
| 287 |
-
"transformer.h.6.attn.c_attn.weight": "model-00001-of-
|
| 288 |
-
"transformer.h.6.attn.c_proj.bias": "model-00001-of-
|
| 289 |
-
"transformer.h.6.attn.c_proj.weight": "model-00001-of-
|
| 290 |
-
"transformer.h.6.ln_1.weight": "model-00001-of-
|
| 291 |
-
"transformer.h.6.ln_2.weight": "model-00001-of-
|
| 292 |
-
"transformer.h.6.mlp.c_fc.bias": "model-00001-of-
|
| 293 |
-
"transformer.h.6.mlp.c_fc.weight": "model-00001-of-
|
| 294 |
-
"transformer.h.6.mlp.c_proj.bias": "model-00001-of-
|
| 295 |
-
"transformer.h.6.mlp.c_proj.weight": "model-00001-of-
|
| 296 |
-
"transformer.h.7.attn.c_attn.bias": "model-00001-of-
|
| 297 |
-
"transformer.h.7.attn.c_attn.weight": "model-00001-of-
|
| 298 |
-
"transformer.h.7.attn.c_proj.bias": "model-00001-of-
|
| 299 |
-
"transformer.h.7.attn.c_proj.weight": "model-00001-of-
|
| 300 |
-
"transformer.h.7.ln_1.weight": "model-00001-of-
|
| 301 |
-
"transformer.h.7.ln_2.weight": "model-00001-of-
|
| 302 |
-
"transformer.h.7.mlp.c_fc.bias": "model-00001-of-
|
| 303 |
-
"transformer.h.7.mlp.c_fc.weight": "model-00001-of-
|
| 304 |
-
"transformer.h.7.mlp.c_proj.bias": "model-00001-of-
|
| 305 |
-
"transformer.h.7.mlp.c_proj.weight": "model-00001-of-
|
| 306 |
-
"transformer.h.8.attn.c_attn.bias": "model-00001-of-
|
| 307 |
-
"transformer.h.8.attn.c_attn.weight": "model-00001-of-
|
| 308 |
-
"transformer.h.8.attn.c_proj.bias": "model-00001-of-
|
| 309 |
-
"transformer.h.8.attn.c_proj.weight": "model-00001-of-
|
| 310 |
-
"transformer.h.8.ln_1.weight": "model-00001-of-
|
| 311 |
-
"transformer.h.8.ln_2.weight": "model-00001-of-
|
| 312 |
-
"transformer.h.8.mlp.c_fc.bias": "model-00001-of-
|
| 313 |
-
"transformer.h.8.mlp.c_fc.weight": "model-00001-of-
|
| 314 |
-
"transformer.h.8.mlp.c_proj.bias": "model-00001-of-
|
| 315 |
-
"transformer.h.8.mlp.c_proj.weight": "model-00001-of-
|
| 316 |
-
"transformer.h.9.attn.c_attn.bias": "model-00001-of-
|
| 317 |
-
"transformer.h.9.attn.c_attn.weight": "model-00001-of-
|
| 318 |
-
"transformer.h.9.attn.c_proj.bias": "model-00001-of-
|
| 319 |
-
"transformer.h.9.attn.c_proj.weight": "model-00001-of-
|
| 320 |
-
"transformer.h.9.ln_1.weight": "model-00001-of-
|
| 321 |
-
"transformer.h.9.ln_2.weight": "model-00001-of-
|
| 322 |
-
"transformer.h.9.mlp.c_fc.bias": "model-00001-of-
|
| 323 |
-
"transformer.h.9.mlp.c_fc.weight": "model-00001-of-
|
| 324 |
-
"transformer.h.9.mlp.c_proj.bias": "model-00001-of-
|
| 325 |
-
"transformer.h.9.mlp.c_proj.weight": "model-00001-of-
|
| 326 |
-
"transformer.ln_f.weight": "model-
|
| 327 |
-
"transformer.wte.weight": "model-00001-of-
|
| 328 |
}
|
| 329 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 6965007360
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 7 |
+
"transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 9 |
+
"transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 15 |
+
"transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 23 |
+
"transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 25 |
+
"transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 27 |
+
"transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 33 |
+
"transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 35 |
+
"transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 37 |
+
"transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 39 |
+
"transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 45 |
+
"transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 47 |
+
"transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 49 |
+
"transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 57 |
+
"transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 59 |
+
"transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 63 |
+
"transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 69 |
+
"transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 73 |
+
"transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 75 |
+
"transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 83 |
+
"transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 85 |
+
"transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 87 |
+
"transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 93 |
+
"transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 95 |
+
"transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 97 |
+
"transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 99 |
+
"transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 105 |
+
"transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 107 |
+
"transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"transformer.h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 109 |
+
"transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 117 |
+
"transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"transformer.h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 119 |
+
"transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 123 |
+
"transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 129 |
+
"transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 133 |
+
"transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 135 |
+
"transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"transformer.h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 143 |
+
"transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 145 |
+
"transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"transformer.h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 147 |
+
"transformer.h.21.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"transformer.h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"transformer.h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 153 |
+
"transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 155 |
+
"transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"transformer.h.22.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 157 |
+
"transformer.h.22.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"transformer.h.22.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 159 |
+
"transformer.h.22.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"transformer.h.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 163 |
+
"transformer.h.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 165 |
+
"transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"transformer.h.23.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 167 |
+
"transformer.h.23.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"transformer.h.23.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"transformer.h.23.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 173 |
+
"transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"transformer.h.24.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 177 |
+
"transformer.h.24.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"transformer.h.24.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 179 |
+
"transformer.h.24.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"transformer.h.24.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"transformer.h.24.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"transformer.h.24.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 183 |
+
"transformer.h.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"transformer.h.24.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"transformer.h.24.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"transformer.h.25.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"transformer.h.25.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"transformer.h.25.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 189 |
+
"transformer.h.25.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"transformer.h.25.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"transformer.h.25.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"transformer.h.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"transformer.h.25.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"transformer.h.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 195 |
+
"transformer.h.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"transformer.h.26.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"transformer.h.26.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"transformer.h.26.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"transformer.h.26.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"transformer.h.26.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"transformer.h.26.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"transformer.h.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 203 |
+
"transformer.h.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"transformer.h.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"transformer.h.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"transformer.h.27.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 207 |
+
"transformer.h.27.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"transformer.h.27.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"transformer.h.27.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"transformer.h.27.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"transformer.h.27.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"transformer.h.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"transformer.h.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"transformer.h.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 215 |
+
"transformer.h.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"transformer.h.28.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"transformer.h.28.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"transformer.h.28.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 219 |
+
"transformer.h.28.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"transformer.h.28.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"transformer.h.28.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"transformer.h.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"transformer.h.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"transformer.h.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 225 |
+
"transformer.h.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"transformer.h.29.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 227 |
+
"transformer.h.29.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"transformer.h.29.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"transformer.h.29.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"transformer.h.29.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"transformer.h.29.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"transformer.h.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"transformer.h.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"transformer.h.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"transformer.h.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 237 |
+
"transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 239 |
+
"transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 243 |
+
"transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 245 |
+
"transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"transformer.h.30.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"transformer.h.30.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"transformer.h.30.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 249 |
+
"transformer.h.30.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"transformer.h.30.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"transformer.h.30.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"transformer.h.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 253 |
+
"transformer.h.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"transformer.h.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 255 |
+
"transformer.h.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"transformer.h.31.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"transformer.h.31.attn.c_attn.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"transformer.h.31.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"transformer.h.31.attn.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"transformer.h.31.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"transformer.h.31.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"transformer.h.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 263 |
+
"transformer.h.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"transformer.h.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 265 |
+
"transformer.h.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 267 |
+
"transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 273 |
+
"transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 275 |
+
"transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 277 |
+
"transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 279 |
+
"transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 285 |
+
"transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 287 |
+
"transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 289 |
+
"transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 297 |
+
"transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 299 |
+
"transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 309 |
+
"transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 313 |
+
"transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 315 |
+
"transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 323 |
+
"transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 325 |
+
"transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"transformer.ln_f.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"transformer.wte.weight": "model-00001-of-00002.safetensors"
|
| 328 |
}
|
| 329 |
}
|