Upload RetNetForCausalLM
Browse files- README.md +1 -1
- config.json +9 -1
- generation_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
|
@@ -8,4 +8,4 @@ license: mit
|
|
| 8 |
datasets:
|
| 9 |
- cerebras/SlimPajama-627B
|
| 10 |
library_name: fla
|
| 11 |
-
---
|
|
|
|
| 8 |
datasets:
|
| 9 |
- cerebras/SlimPajama-627B
|
| 10 |
library_name: fla
|
| 11 |
+
---
|
config.json
CHANGED
|
@@ -3,11 +3,15 @@
|
|
| 3 |
"architectures": [
|
| 4 |
"RetNetForCausalLM"
|
| 5 |
],
|
|
|
|
| 6 |
"attn_mode": "chunk",
|
| 7 |
"bos_token_id": 1,
|
|
|
|
|
|
|
| 8 |
"eos_token_id": 2,
|
| 9 |
"expand_k": 1,
|
| 10 |
"expand_v": 2,
|
|
|
|
| 11 |
"fuse_cross_entropy": true,
|
| 12 |
"fuse_norm": true,
|
| 13 |
"hidden_act": "swish",
|
|
@@ -17,12 +21,16 @@
|
|
| 17 |
"intermediate_size": null,
|
| 18 |
"max_position_embeddings": 2048,
|
| 19 |
"model_type": "retnet",
|
|
|
|
| 20 |
"num_heads": 10,
|
| 21 |
"num_hidden_layers": 32,
|
|
|
|
| 22 |
"rms_norm_eps": 1e-06,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
-
"transformers_version": "4.
|
| 26 |
"use_cache": true,
|
|
|
|
|
|
|
| 27 |
"vocab_size": 32000
|
| 28 |
}
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
"RetNetForCausalLM"
|
| 5 |
],
|
| 6 |
+
"attn": null,
|
| 7 |
"attn_mode": "chunk",
|
| 8 |
"bos_token_id": 1,
|
| 9 |
+
"conv_size": 4,
|
| 10 |
+
"elementwise_affine": true,
|
| 11 |
"eos_token_id": 2,
|
| 12 |
"expand_k": 1,
|
| 13 |
"expand_v": 2,
|
| 14 |
+
"feature_map": null,
|
| 15 |
"fuse_cross_entropy": true,
|
| 16 |
"fuse_norm": true,
|
| 17 |
"hidden_act": "swish",
|
|
|
|
| 21 |
"intermediate_size": null,
|
| 22 |
"max_position_embeddings": 2048,
|
| 23 |
"model_type": "retnet",
|
| 24 |
+
"norm_eps": 1e-06,
|
| 25 |
"num_heads": 10,
|
| 26 |
"num_hidden_layers": 32,
|
| 27 |
+
"num_kv_heads": null,
|
| 28 |
"rms_norm_eps": 1e-06,
|
| 29 |
"tie_word_embeddings": false,
|
| 30 |
"torch_dtype": "bfloat16",
|
| 31 |
+
"transformers_version": "4.48.2",
|
| 32 |
"use_cache": true,
|
| 33 |
+
"use_output_gate": true,
|
| 34 |
+
"use_short_conv": false,
|
| 35 |
"vocab_size": 32000
|
| 36 |
}
|
generation_config.json
CHANGED
|
@@ -2,6 +2,5 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
-
"transformers_version": "4.
|
| 6 |
-
"use_cache": false
|
| 7 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.48.2"
|
|
|
|
| 6 |
}
|
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 sha256:853459d8b6843b6618db908d2756f1bb2e622b8e039916a84fb890422505d111
|
| 3 |
+
size 4987669992
|
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:d3526856f41bda10650e99253396ed97aadc557b1f4d4fb9eef6eeef710ac941
|
| 3 |
+
size 457466128
|
model.safetensors.index.json
CHANGED
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 17 |
"model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
"model.layers.1.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 19 |
"model.layers.1.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -24,6 +25,7 @@
|
|
| 24 |
"model.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 27 |
"model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
"model.layers.10.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 29 |
"model.layers.10.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -34,6 +36,7 @@
|
|
| 34 |
"model.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 37 |
"model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
"model.layers.11.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 39 |
"model.layers.11.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -44,6 +47,7 @@
|
|
| 44 |
"model.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 47 |
"model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
"model.layers.12.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 49 |
"model.layers.12.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -54,6 +58,7 @@
|
|
| 54 |
"model.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 57 |
"model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
"model.layers.13.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 59 |
"model.layers.13.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -64,6 +69,7 @@
|
|
| 64 |
"model.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 65 |
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 67 |
"model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
"model.layers.14.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 69 |
"model.layers.14.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -74,6 +80,7 @@
|
|
| 74 |
"model.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 77 |
"model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 78 |
"model.layers.15.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 79 |
"model.layers.15.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -84,6 +91,7 @@
|
|
| 84 |
"model.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 87 |
"model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 88 |
"model.layers.16.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 89 |
"model.layers.16.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -94,6 +102,7 @@
|
|
| 94 |
"model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 97 |
"model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
"model.layers.17.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 99 |
"model.layers.17.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -104,6 +113,7 @@
|
|
| 104 |
"model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 107 |
"model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
"model.layers.18.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 109 |
"model.layers.18.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -114,6 +124,7 @@
|
|
| 114 |
"model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 117 |
"model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
"model.layers.19.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 119 |
"model.layers.19.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -124,6 +135,7 @@
|
|
| 124 |
"model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 127 |
"model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
"model.layers.2.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 129 |
"model.layers.2.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -134,6 +146,7 @@
|
|
| 134 |
"model.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 137 |
"model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 138 |
"model.layers.20.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 139 |
"model.layers.20.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -144,6 +157,7 @@
|
|
| 144 |
"model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 147 |
"model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
"model.layers.21.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 149 |
"model.layers.21.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -154,6 +168,7 @@
|
|
| 154 |
"model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 155 |
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 157 |
"model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
"model.layers.22.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 159 |
"model.layers.22.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -164,6 +179,7 @@
|
|
| 164 |
"model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 167 |
"model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
"model.layers.23.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 169 |
"model.layers.23.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -174,6 +190,7 @@
|
|
| 174 |
"model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 175 |
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 177 |
"model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
"model.layers.24.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 179 |
"model.layers.24.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -184,6 +201,7 @@
|
|
| 184 |
"model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 185 |
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 187 |
"model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 188 |
"model.layers.25.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 189 |
"model.layers.25.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -194,6 +212,7 @@
|
|
| 194 |
"model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 195 |
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 197 |
"model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 198 |
"model.layers.26.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 199 |
"model.layers.26.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -204,6 +223,7 @@
|
|
| 204 |
"model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 205 |
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 207 |
"model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 208 |
"model.layers.27.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 209 |
"model.layers.27.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -214,6 +234,7 @@
|
|
| 214 |
"model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 215 |
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 217 |
"model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 218 |
"model.layers.28.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 219 |
"model.layers.28.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -224,6 +245,7 @@
|
|
| 224 |
"model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 225 |
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 227 |
"model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 228 |
"model.layers.29.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 229 |
"model.layers.29.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -234,6 +256,7 @@
|
|
| 234 |
"model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 235 |
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 237 |
"model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 238 |
"model.layers.3.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 239 |
"model.layers.3.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -244,6 +267,7 @@
|
|
| 244 |
"model.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 245 |
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 247 |
"model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 248 |
"model.layers.30.attn.g_norm_swish_gate.weight": "model-00002-of-00002.safetensors",
|
| 249 |
"model.layers.30.attn.g_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -254,6 +278,7 @@
|
|
| 254 |
"model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 255 |
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 257 |
"model.layers.30.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
| 258 |
"model.layers.31.attn.g_norm_swish_gate.weight": "model-00002-of-00002.safetensors",
|
| 259 |
"model.layers.31.attn.g_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -264,6 +289,7 @@
|
|
| 264 |
"model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 265 |
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 266 |
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 267 |
"model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
| 268 |
"model.layers.4.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 269 |
"model.layers.4.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -274,6 +300,7 @@
|
|
| 274 |
"model.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 275 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 277 |
"model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
"model.layers.5.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 279 |
"model.layers.5.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -284,6 +311,7 @@
|
|
| 284 |
"model.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 287 |
"model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
"model.layers.6.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 289 |
"model.layers.6.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -294,6 +322,7 @@
|
|
| 294 |
"model.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 295 |
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 297 |
"model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 298 |
"model.layers.7.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 299 |
"model.layers.7.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -304,6 +333,7 @@
|
|
| 304 |
"model.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 305 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 307 |
"model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 308 |
"model.layers.8.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 309 |
"model.layers.8.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -314,6 +344,7 @@
|
|
| 314 |
"model.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 317 |
"model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 318 |
"model.layers.9.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 319 |
"model.layers.9.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -324,6 +355,7 @@
|
|
| 324 |
"model.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
"model.layers.9.mlp.gate_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 |
}
|
|
|
|
| 14 |
"model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
"model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
"model.layers.1.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 20 |
"model.layers.1.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 25 |
"model.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
"model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
"model.layers.10.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 31 |
"model.layers.10.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 36 |
"model.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
"model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
"model.layers.11.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 42 |
"model.layers.11.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 47 |
"model.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
"model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 52 |
"model.layers.12.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 53 |
"model.layers.12.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 58 |
"model.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
"model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
"model.layers.13.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 64 |
"model.layers.13.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 69 |
"model.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
"model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
"model.layers.14.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 75 |
"model.layers.14.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 80 |
"model.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
"model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
"model.layers.15.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 86 |
"model.layers.15.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 91 |
"model.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
"model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
"model.layers.16.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 97 |
"model.layers.16.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 102 |
"model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
"model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
"model.layers.17.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 108 |
"model.layers.17.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 113 |
"model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
"model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
"model.layers.18.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 119 |
"model.layers.18.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 124 |
"model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
"model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
"model.layers.19.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 130 |
"model.layers.19.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 135 |
"model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 136 |
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
"model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
"model.layers.2.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 141 |
"model.layers.2.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 146 |
"model.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
"model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 151 |
"model.layers.20.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 152 |
"model.layers.20.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 157 |
"model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
"model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 162 |
"model.layers.21.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 163 |
"model.layers.21.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 168 |
"model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
"model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 173 |
"model.layers.22.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 174 |
"model.layers.22.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 179 |
"model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 180 |
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
"model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 184 |
"model.layers.23.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 185 |
"model.layers.23.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 190 |
"model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 191 |
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 194 |
"model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 195 |
"model.layers.24.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 196 |
"model.layers.24.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 201 |
"model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
"model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 206 |
"model.layers.25.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 207 |
"model.layers.25.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 212 |
"model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 213 |
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
"model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 217 |
"model.layers.26.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 218 |
"model.layers.26.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 223 |
"model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 224 |
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
"model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 228 |
"model.layers.27.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 229 |
"model.layers.27.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 234 |
"model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 235 |
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 238 |
"model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 239 |
"model.layers.28.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 240 |
"model.layers.28.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 245 |
"model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 246 |
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
"model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 250 |
"model.layers.29.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 251 |
"model.layers.29.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 256 |
"model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
"model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
"model.layers.3.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 262 |
"model.layers.3.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 267 |
"model.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 268 |
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
"model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 272 |
"model.layers.30.attn.g_norm_swish_gate.weight": "model-00002-of-00002.safetensors",
|
| 273 |
"model.layers.30.attn.g_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 278 |
"model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
"model.layers.30.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
| 283 |
"model.layers.31.attn.g_norm_swish_gate.weight": "model-00002-of-00002.safetensors",
|
| 284 |
"model.layers.31.attn.g_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 289 |
"model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 290 |
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
"model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
| 294 |
"model.layers.4.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 295 |
"model.layers.4.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 300 |
"model.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
"model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 305 |
"model.layers.5.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 306 |
"model.layers.5.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 311 |
"model.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 312 |
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
"model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 316 |
"model.layers.6.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 317 |
"model.layers.6.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 322 |
"model.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 323 |
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
"model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 327 |
"model.layers.7.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 328 |
"model.layers.7.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 333 |
"model.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 334 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
"model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
"model.layers.8.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 339 |
"model.layers.8.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 344 |
"model.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
"model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 349 |
"model.layers.9.attn.g_norm_swish_gate.weight": "model-00001-of-00002.safetensors",
|
| 350 |
"model.layers.9.attn.g_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 355 |
"model.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
"model.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 361 |
}
|