Add files using upload-large-folder tool
Browse files- README.md +12 -8
- osaurus.json +4 -0
- text_encoder/0.safetensors +2 -2
- text_encoder/1.safetensors +2 -2
- text_encoder/model.safetensors.index.json +852 -598
- transformer/0.safetensors +2 -2
- transformer/1.safetensors +2 -2
- transformer/2.safetensors +2 -2
- transformer/model.safetensors.index.json +758 -545
- unconditional_transformer/0.safetensors +2 -2
- unconditional_transformer/1.safetensors +2 -2
- unconditional_transformer/2.safetensors +2 -2
- unconditional_transformer/model.safetensors.index.json +758 -545
- vae/0.safetensors +1 -1
- vae/model.safetensors.index.json +1 -1
README.md
CHANGED
|
@@ -11,18 +11,22 @@ tags: [text-to-image, mflux, ideogram, ideogram-4, quantized, osaurus, non-comme
|
|
| 11 |
|
| 12 |
> # 🚫 NOT FOR COMMERCIAL USE
|
| 13 |
> This model is governed by the **Ideogram-4 Non-Commercial Model Agreement** ([LICENSE.md](LICENSE.md)).
|
| 14 |
-
> Use, reproduction, and distribution are permitted **for Non-Commercial Purposes only**. By downloading you agree to those terms and the use restrictions therein.
|
| 15 |
|
| 16 |
-
# Ideogram-4 · mflux ·
|
| 17 |
|
| 18 |
-
OsaurusAI
|
|
|
|
| 19 |
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
```bash
|
| 22 |
-
mflux-generate-ideogram4 --model OsaurusAI/ideogram-4-mflux-4bit
|
| 23 |
-
--prompt '{"caption":"a small red cube on a white table"}' --steps 20
|
| 24 |
```
|
| 25 |
|
| 26 |
## Provenance & License
|
| 27 |
-
- Base: [ideogram-ai/ideogram-4-fp8](https://huggingface.co/ideogram-ai/ideogram-4-fp8) © Ideogram, Inc. —
|
| 28 |
-
- Quantization: Osaurus · mflux 0.
|
|
|
|
| 11 |
|
| 12 |
> # 🚫 NOT FOR COMMERCIAL USE
|
| 13 |
> This model is governed by the **Ideogram-4 Non-Commercial Model Agreement** ([LICENSE.md](LICENSE.md)).
|
|
|
|
| 14 |
|
| 15 |
+
# Ideogram-4 · mflux · 4bit
|
| 16 |
|
| 17 |
+
OsaurusAI 4bit [mflux](https://github.com/filipstrand/mflux) build of [ideogram-ai/ideogram-4-fp8](https://huggingface.co/ideogram-ai/ideogram-4-fp8) (14 GB).
|
| 18 |
+
Real MLX affine 4-bit (group size 64) across the text encoder, both transformers and the VAE attention projections.
|
| 19 |
|
| 20 |
+
**Use structured JSON captions.** Ideogram 4 was trained on them; plain-text prompts frequently come back as a gray "Image blocked by safety filter" card.
|
| 21 |
+
|
| 22 |
+
## Use in Osaurus
|
| 23 |
+
Download it from the Image models tab and prompt with a JSON caption.
|
| 24 |
+
|
| 25 |
+
## Use with mflux
|
| 26 |
```bash
|
| 27 |
+
mflux-generate-ideogram4 --model OsaurusAI/ideogram-4-mflux-4bit --prompt-file caption.json --steps 20
|
|
|
|
| 28 |
```
|
| 29 |
|
| 30 |
## Provenance & License
|
| 31 |
+
- Base: [ideogram-ai/ideogram-4-fp8](https://huggingface.co/ideogram-ai/ideogram-4-fp8) © Ideogram, Inc. — Ideogram-4 Non-Commercial (LICENSE.md shipped here)
|
| 32 |
+
- Quantization: Osaurus · mflux 0.20 (main 03700b9) · 4bit · eric@osaurus.ai
|
osaurus.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"required_osaurus_version": "0.25.17",
|
| 3 |
+
"model_version": "2"
|
| 4 |
+
}
|
text_encoder/0.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 sha256:276a5fed11a9aae4f52f6e6084625c75dd299dfd9754e042cb6b6f26a79e3dfe
|
| 3 |
+
size 2138739328
|
text_encoder/1.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:c39f2f3b2473415fbcf201bc112ecb8507dcc09d32bd63cb16dea1b35a899abf
|
| 3 |
+
size 2119029339
|
text_encoder/model.safetensors.index.json
CHANGED
|
@@ -1,659 +1,913 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"quantization_level": "4",
|
| 4 |
-
"mflux_version": "0.
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"embed_tokens.weight": "0.safetensors",
|
|
|
|
|
|
|
| 8 |
"layers.0.input_layernorm.weight": "0.safetensors",
|
| 9 |
"layers.0.self_attn.q_proj.weight": "0.safetensors",
|
| 10 |
-
"layers.0.self_attn.q_proj.
|
|
|
|
| 11 |
"layers.0.self_attn.k_proj.weight": "0.safetensors",
|
| 12 |
-
"layers.0.self_attn.k_proj.
|
|
|
|
| 13 |
"layers.0.self_attn.v_proj.weight": "0.safetensors",
|
| 14 |
-
"layers.0.self_attn.v_proj.
|
|
|
|
| 15 |
"layers.0.self_attn.o_proj.weight": "0.safetensors",
|
| 16 |
-
"layers.0.self_attn.o_proj.
|
|
|
|
| 17 |
"layers.0.self_attn.q_norm.weight": "0.safetensors",
|
| 18 |
"layers.0.self_attn.k_norm.weight": "0.safetensors",
|
| 19 |
"layers.0.post_attention_layernorm.weight": "0.safetensors",
|
| 20 |
"layers.0.mlp.gate_proj.weight": "0.safetensors",
|
| 21 |
-
"layers.0.mlp.gate_proj.
|
|
|
|
| 22 |
"layers.0.mlp.up_proj.weight": "0.safetensors",
|
| 23 |
-
"layers.0.mlp.up_proj.
|
|
|
|
| 24 |
"layers.0.mlp.down_proj.weight": "0.safetensors",
|
| 25 |
-
"layers.0.mlp.down_proj.
|
|
|
|
| 26 |
"layers.1.input_layernorm.weight": "0.safetensors",
|
| 27 |
"layers.1.self_attn.q_proj.weight": "0.safetensors",
|
| 28 |
-
"layers.1.self_attn.q_proj.
|
|
|
|
| 29 |
"layers.1.self_attn.k_proj.weight": "0.safetensors",
|
| 30 |
-
"layers.1.self_attn.k_proj.
|
|
|
|
| 31 |
"layers.1.self_attn.v_proj.weight": "0.safetensors",
|
| 32 |
-
"layers.1.self_attn.v_proj.
|
|
|
|
| 33 |
"layers.1.self_attn.o_proj.weight": "0.safetensors",
|
| 34 |
-
"layers.1.self_attn.o_proj.
|
|
|
|
| 35 |
"layers.1.self_attn.q_norm.weight": "0.safetensors",
|
| 36 |
"layers.1.self_attn.k_norm.weight": "0.safetensors",
|
| 37 |
"layers.1.post_attention_layernorm.weight": "0.safetensors",
|
| 38 |
"layers.1.mlp.gate_proj.weight": "0.safetensors",
|
| 39 |
-
"layers.1.mlp.gate_proj.
|
|
|
|
| 40 |
"layers.1.mlp.up_proj.weight": "0.safetensors",
|
| 41 |
-
"layers.1.mlp.up_proj.
|
|
|
|
| 42 |
"layers.1.mlp.down_proj.weight": "0.safetensors",
|
| 43 |
-
"layers.1.mlp.down_proj.
|
|
|
|
| 44 |
"layers.2.input_layernorm.weight": "0.safetensors",
|
| 45 |
"layers.2.self_attn.q_proj.weight": "0.safetensors",
|
| 46 |
-
"layers.2.self_attn.q_proj.
|
|
|
|
| 47 |
"layers.2.self_attn.k_proj.weight": "0.safetensors",
|
| 48 |
-
"layers.2.self_attn.k_proj.
|
|
|
|
| 49 |
"layers.2.self_attn.v_proj.weight": "0.safetensors",
|
| 50 |
-
"layers.2.self_attn.v_proj.
|
|
|
|
| 51 |
"layers.2.self_attn.o_proj.weight": "0.safetensors",
|
| 52 |
-
"layers.2.self_attn.o_proj.
|
|
|
|
| 53 |
"layers.2.self_attn.q_norm.weight": "0.safetensors",
|
| 54 |
"layers.2.self_attn.k_norm.weight": "0.safetensors",
|
| 55 |
"layers.2.post_attention_layernorm.weight": "0.safetensors",
|
| 56 |
"layers.2.mlp.gate_proj.weight": "0.safetensors",
|
| 57 |
-
"layers.2.mlp.gate_proj.
|
|
|
|
| 58 |
"layers.2.mlp.up_proj.weight": "0.safetensors",
|
| 59 |
-
"layers.2.mlp.up_proj.
|
|
|
|
| 60 |
"layers.2.mlp.down_proj.weight": "0.safetensors",
|
| 61 |
-
"layers.2.mlp.down_proj.
|
|
|
|
| 62 |
"layers.3.input_layernorm.weight": "0.safetensors",
|
| 63 |
"layers.3.self_attn.q_proj.weight": "0.safetensors",
|
| 64 |
-
"layers.3.self_attn.q_proj.
|
|
|
|
| 65 |
"layers.3.self_attn.k_proj.weight": "0.safetensors",
|
| 66 |
-
"layers.3.self_attn.k_proj.
|
|
|
|
| 67 |
"layers.3.self_attn.v_proj.weight": "0.safetensors",
|
| 68 |
-
"layers.3.self_attn.v_proj.
|
|
|
|
| 69 |
"layers.3.self_attn.o_proj.weight": "0.safetensors",
|
| 70 |
-
"layers.3.self_attn.o_proj.
|
|
|
|
| 71 |
"layers.3.self_attn.q_norm.weight": "0.safetensors",
|
| 72 |
"layers.3.self_attn.k_norm.weight": "0.safetensors",
|
| 73 |
"layers.3.post_attention_layernorm.weight": "0.safetensors",
|
| 74 |
"layers.3.mlp.gate_proj.weight": "0.safetensors",
|
| 75 |
-
"layers.3.mlp.gate_proj.
|
|
|
|
| 76 |
"layers.3.mlp.up_proj.weight": "0.safetensors",
|
| 77 |
-
"layers.3.mlp.up_proj.
|
|
|
|
| 78 |
"layers.3.mlp.down_proj.weight": "0.safetensors",
|
| 79 |
-
"layers.3.mlp.down_proj.
|
|
|
|
| 80 |
"layers.4.input_layernorm.weight": "0.safetensors",
|
| 81 |
"layers.4.self_attn.q_proj.weight": "0.safetensors",
|
| 82 |
-
"layers.4.self_attn.q_proj.
|
|
|
|
| 83 |
"layers.4.self_attn.k_proj.weight": "0.safetensors",
|
| 84 |
-
"layers.4.self_attn.k_proj.
|
|
|
|
| 85 |
"layers.4.self_attn.v_proj.weight": "0.safetensors",
|
| 86 |
-
"layers.4.self_attn.v_proj.
|
|
|
|
| 87 |
"layers.4.self_attn.o_proj.weight": "0.safetensors",
|
| 88 |
-
"layers.4.self_attn.o_proj.
|
|
|
|
| 89 |
"layers.4.self_attn.q_norm.weight": "0.safetensors",
|
| 90 |
"layers.4.self_attn.k_norm.weight": "0.safetensors",
|
| 91 |
"layers.4.post_attention_layernorm.weight": "0.safetensors",
|
| 92 |
"layers.4.mlp.gate_proj.weight": "0.safetensors",
|
| 93 |
-
"layers.4.mlp.gate_proj.
|
| 94 |
-
"layers.4.mlp.
|
| 95 |
-
"layers.4.mlp.up_proj.
|
| 96 |
-
"layers.4.mlp.
|
| 97 |
-
"layers.4.mlp.
|
| 98 |
-
"layers.
|
| 99 |
-
"layers.
|
| 100 |
-
"layers.
|
| 101 |
-
"layers.5.
|
| 102 |
-
"layers.5.self_attn.
|
| 103 |
-
"layers.5.self_attn.
|
| 104 |
-
"layers.5.self_attn.
|
| 105 |
-
"layers.5.self_attn.
|
| 106 |
-
"layers.5.self_attn.
|
| 107 |
-
"layers.5.self_attn.
|
| 108 |
-
"layers.5.self_attn.
|
| 109 |
-
"layers.5.
|
| 110 |
-
"layers.5.
|
| 111 |
-
"layers.5.
|
| 112 |
-
"layers.5.
|
| 113 |
-
"layers.5.
|
| 114 |
-
"layers.5.
|
| 115 |
-
"layers.5.
|
| 116 |
-
"layers.
|
| 117 |
-
"layers.
|
| 118 |
-
"layers.
|
| 119 |
-
"layers.
|
| 120 |
-
"layers.
|
| 121 |
-
"layers.
|
| 122 |
-
"layers.
|
| 123 |
-
"layers.
|
| 124 |
-
"layers.
|
| 125 |
-
"layers.
|
| 126 |
-
"layers.6.
|
| 127 |
-
"layers.6.
|
| 128 |
-
"layers.6.
|
| 129 |
-
"layers.6.
|
| 130 |
-
"layers.6.
|
| 131 |
-
"layers.6.
|
| 132 |
-
"layers.6.
|
| 133 |
-
"layers.6.
|
| 134 |
-
"layers.
|
| 135 |
-
"layers.
|
| 136 |
-
"layers.
|
| 137 |
-
"layers.
|
| 138 |
-
"layers.
|
| 139 |
-
"layers.
|
| 140 |
-
"layers.
|
| 141 |
-
"layers.
|
| 142 |
-
"layers.
|
| 143 |
-
"layers.
|
| 144 |
-
"layers.
|
| 145 |
-
"layers.
|
| 146 |
-
"layers.
|
| 147 |
-
"layers.
|
| 148 |
-
"layers.
|
| 149 |
-
"layers.
|
| 150 |
-
"layers.
|
| 151 |
-
"layers.7.
|
| 152 |
-
"layers.
|
| 153 |
-
"layers.
|
| 154 |
-
"layers.
|
| 155 |
-
"layers.
|
| 156 |
-
"layers.
|
| 157 |
-
"layers.
|
| 158 |
-
"layers.
|
| 159 |
-
"layers.
|
| 160 |
-
"layers.
|
| 161 |
-
"layers.
|
| 162 |
-
"layers.
|
| 163 |
-
"layers.
|
| 164 |
-
"layers.
|
| 165 |
-
"layers.
|
| 166 |
-
"layers.
|
| 167 |
-
"layers.
|
| 168 |
-
"layers.
|
| 169 |
-
"layers.
|
| 170 |
-
"layers.
|
| 171 |
-
"layers.
|
| 172 |
-
"layers.
|
| 173 |
-
"layers.
|
| 174 |
-
"layers.
|
| 175 |
-
"layers.
|
| 176 |
-
"layers.
|
| 177 |
-
"layers.
|
| 178 |
-
"layers.
|
| 179 |
-
"layers.
|
| 180 |
-
"layers.
|
| 181 |
-
"layers.
|
| 182 |
-
"layers.
|
| 183 |
-
"layers.
|
| 184 |
-
"layers.
|
| 185 |
-
"layers.
|
| 186 |
-
"layers.
|
| 187 |
-
"layers.
|
| 188 |
-
"layers.
|
| 189 |
-
"layers.
|
| 190 |
-
"layers.
|
| 191 |
-
"layers.
|
| 192 |
-
"layers.
|
| 193 |
-
"layers.
|
| 194 |
-
"layers.
|
| 195 |
-
"layers.
|
| 196 |
-
"layers.
|
| 197 |
-
"layers.
|
| 198 |
-
"layers.
|
| 199 |
-
"layers.
|
| 200 |
-
"layers.
|
| 201 |
-
"layers.
|
| 202 |
-
"layers.
|
| 203 |
-
"layers.
|
| 204 |
-
"layers.
|
| 205 |
-
"layers.
|
| 206 |
-
"layers.
|
| 207 |
-
"layers.
|
| 208 |
-
"layers.
|
| 209 |
-
"layers.
|
| 210 |
-
"layers.
|
| 211 |
-
"layers.
|
| 212 |
-
"layers.
|
| 213 |
-
"layers.
|
| 214 |
-
"layers.
|
| 215 |
-
"layers.
|
| 216 |
-
"layers.
|
| 217 |
-
"layers.
|
| 218 |
-
"layers.
|
| 219 |
-
"layers.
|
| 220 |
-
"layers.
|
| 221 |
-
"layers.
|
| 222 |
-
"layers.
|
| 223 |
-
"layers.
|
| 224 |
-
"layers.
|
| 225 |
-
"layers.
|
| 226 |
-
"layers.
|
| 227 |
-
"layers.
|
| 228 |
-
"layers.
|
| 229 |
-
"layers.
|
| 230 |
-
"layers.
|
| 231 |
-
"layers.
|
| 232 |
-
"layers.
|
| 233 |
-
"layers.
|
| 234 |
-
"layers.
|
| 235 |
-
"layers.
|
| 236 |
-
"layers.
|
| 237 |
-
"layers.
|
| 238 |
-
"layers.
|
| 239 |
-
"layers.
|
| 240 |
-
"layers.
|
| 241 |
-
"layers.
|
| 242 |
-
"layers.
|
| 243 |
-
"layers.
|
| 244 |
-
"layers.
|
| 245 |
-
"layers.
|
| 246 |
-
"layers.
|
| 247 |
-
"layers.
|
| 248 |
-
"layers.
|
| 249 |
-
"layers.
|
| 250 |
-
"layers.
|
| 251 |
-
"layers.
|
| 252 |
-
"layers.
|
| 253 |
-
"layers.
|
| 254 |
-
"layers.
|
| 255 |
-
"layers.
|
| 256 |
-
"layers.
|
| 257 |
-
"layers.
|
| 258 |
-
"layers.
|
| 259 |
-
"layers.
|
| 260 |
-
"layers.
|
| 261 |
-
"layers.
|
| 262 |
-
"layers.
|
| 263 |
-
"layers.
|
| 264 |
-
"layers.
|
| 265 |
-
"layers.
|
| 266 |
-
"layers.
|
| 267 |
-
"layers.
|
| 268 |
-
"layers.
|
| 269 |
-
"layers.
|
| 270 |
-
"layers.
|
| 271 |
-
"layers.
|
| 272 |
-
"layers.
|
| 273 |
-
"layers.
|
| 274 |
-
"layers.
|
| 275 |
-
"layers.
|
| 276 |
-
"layers.
|
| 277 |
-
"layers.
|
| 278 |
-
"layers.
|
| 279 |
-
"layers.
|
| 280 |
-
"layers.
|
| 281 |
-
"layers.
|
| 282 |
-
"layers.
|
| 283 |
-
"layers.
|
| 284 |
-
"layers.
|
| 285 |
-
"layers.
|
| 286 |
-
"layers.
|
| 287 |
-
"layers.
|
| 288 |
-
"layers.
|
| 289 |
-
"layers.
|
| 290 |
-
"layers.
|
| 291 |
-
"layers.
|
| 292 |
-
"layers.
|
| 293 |
-
"layers.
|
| 294 |
-
"layers.
|
| 295 |
-
"layers.
|
| 296 |
-
"layers.
|
| 297 |
-
"layers.
|
| 298 |
-
"layers.
|
| 299 |
-
"layers.
|
| 300 |
-
"layers.
|
| 301 |
-
"layers.
|
| 302 |
-
"layers.
|
| 303 |
-
"layers.
|
| 304 |
-
"layers.
|
| 305 |
-
"layers.
|
| 306 |
-
"layers.
|
| 307 |
-
"layers.
|
| 308 |
-
"layers.
|
| 309 |
-
"layers.
|
| 310 |
-
"layers.
|
| 311 |
-
"layers.
|
| 312 |
-
"layers.
|
| 313 |
-
"layers.
|
| 314 |
-
"layers.
|
| 315 |
-
"layers.
|
| 316 |
-
"layers.
|
| 317 |
-
"layers.
|
| 318 |
-
"layers.
|
| 319 |
-
"layers.
|
| 320 |
-
"layers.
|
| 321 |
-
"layers.
|
| 322 |
-
"layers.
|
| 323 |
-
"layers.
|
| 324 |
-
"layers.
|
| 325 |
-
"layers.
|
| 326 |
-
"layers.
|
| 327 |
-
"layers.
|
| 328 |
-
"layers.
|
| 329 |
-
"layers.
|
| 330 |
-
"layers.
|
| 331 |
-
"layers.
|
| 332 |
-
"layers.
|
| 333 |
-
"layers.
|
| 334 |
-
"layers.
|
| 335 |
-
"layers.
|
| 336 |
-
"layers.
|
| 337 |
-
"layers.
|
| 338 |
-
"layers.
|
| 339 |
-
"layers.
|
| 340 |
-
"layers.
|
| 341 |
-
"layers.
|
| 342 |
-
"layers.
|
| 343 |
-
"layers.
|
| 344 |
-
"layers.
|
| 345 |
-
"layers.
|
| 346 |
-
"layers.
|
| 347 |
-
"layers.
|
| 348 |
-
"layers.
|
| 349 |
-
"layers.
|
| 350 |
-
"layers.
|
| 351 |
-
"layers.
|
| 352 |
-
"layers.
|
| 353 |
-
"layers.
|
| 354 |
-
"layers.
|
| 355 |
-
"layers.
|
| 356 |
-
"layers.
|
| 357 |
-
"layers.
|
| 358 |
-
"layers.
|
| 359 |
-
"layers.
|
| 360 |
-
"layers.
|
| 361 |
-
"layers.
|
| 362 |
-
"layers.
|
| 363 |
-
"layers.
|
| 364 |
-
"layers.
|
| 365 |
-
"layers.
|
| 366 |
-
"layers.
|
| 367 |
-
"layers.
|
| 368 |
-
"layers.
|
| 369 |
-
"layers.
|
| 370 |
-
"layers.
|
| 371 |
-
"layers.
|
| 372 |
-
"layers.
|
| 373 |
-
"layers.
|
| 374 |
-
"layers.
|
| 375 |
-
"layers.
|
| 376 |
-
"layers.
|
| 377 |
-
"layers.
|
| 378 |
-
"layers.
|
| 379 |
-
"layers.
|
| 380 |
-
"layers.
|
| 381 |
-
"layers.
|
| 382 |
-
"layers.
|
| 383 |
-
"layers.
|
| 384 |
-
"layers.
|
| 385 |
-
"layers.
|
| 386 |
-
"layers.
|
| 387 |
-
"layers.
|
| 388 |
-
"layers.
|
| 389 |
-
"layers.
|
| 390 |
-
"layers.
|
| 391 |
-
"layers.
|
| 392 |
-
"layers.
|
| 393 |
-
"layers.
|
| 394 |
-
"layers.
|
| 395 |
-
"layers.
|
| 396 |
-
"layers.
|
| 397 |
-
"layers.
|
| 398 |
-
"layers.
|
| 399 |
-
"layers.
|
| 400 |
-
"layers.
|
| 401 |
-
"layers.
|
| 402 |
-
"layers.
|
| 403 |
-
"layers.
|
| 404 |
-
"layers.
|
| 405 |
-
"layers.
|
| 406 |
-
"layers.
|
| 407 |
-
"layers.
|
| 408 |
-
"layers.
|
| 409 |
-
"layers.
|
| 410 |
-
"layers.
|
| 411 |
-
"layers.
|
| 412 |
-
"layers.
|
| 413 |
-
"layers.
|
| 414 |
-
"layers.
|
| 415 |
-
"layers.
|
| 416 |
-
"layers.
|
| 417 |
-
"layers.
|
| 418 |
-
"layers.
|
| 419 |
-
"layers.
|
| 420 |
-
"layers.
|
| 421 |
-
"layers.
|
| 422 |
-
"layers.
|
| 423 |
-
"layers.
|
| 424 |
-
"layers.
|
| 425 |
-
"layers.
|
| 426 |
-
"layers.
|
| 427 |
-
"layers.
|
| 428 |
-
"layers.
|
| 429 |
-
"layers.
|
| 430 |
-
"layers.
|
| 431 |
-
"layers.
|
| 432 |
-
"layers.
|
| 433 |
-
"layers.
|
| 434 |
-
"layers.
|
| 435 |
-
"layers.
|
| 436 |
-
"layers.
|
| 437 |
-
"layers.
|
| 438 |
-
"layers.
|
| 439 |
-
"layers.
|
| 440 |
-
"layers.
|
| 441 |
-
"layers.
|
| 442 |
-
"layers.
|
| 443 |
-
"layers.
|
| 444 |
-
"layers.
|
| 445 |
-
"layers.
|
| 446 |
-
"layers.
|
| 447 |
-
"layers.
|
| 448 |
-
"layers.
|
| 449 |
-
"layers.
|
| 450 |
-
"layers.
|
| 451 |
-
"layers.
|
| 452 |
-
"layers.
|
| 453 |
-
"layers.
|
| 454 |
-
"layers.
|
| 455 |
-
"layers.
|
| 456 |
-
"layers.
|
| 457 |
-
"layers.
|
| 458 |
-
"layers.
|
| 459 |
-
"layers.
|
| 460 |
-
"layers.
|
| 461 |
-
"layers.
|
| 462 |
-
"layers.
|
| 463 |
-
"layers.
|
| 464 |
-
"layers.
|
| 465 |
-
"layers.
|
| 466 |
-
"layers.
|
| 467 |
-
"layers.
|
| 468 |
-
"layers.
|
| 469 |
-
"layers.
|
| 470 |
-
"layers.
|
| 471 |
-
"layers.
|
| 472 |
-
"layers.
|
| 473 |
-
"layers.
|
| 474 |
-
"layers.
|
| 475 |
-
"layers.
|
| 476 |
-
"layers.
|
| 477 |
-
"layers.
|
| 478 |
-
"layers.
|
| 479 |
-
"layers.
|
| 480 |
-
"layers.
|
| 481 |
-
"layers.
|
| 482 |
-
"layers.
|
| 483 |
-
"layers.
|
| 484 |
-
"layers.
|
| 485 |
-
"layers.
|
| 486 |
-
"layers.
|
| 487 |
-
"layers.
|
| 488 |
-
"layers.
|
| 489 |
-
"layers.
|
| 490 |
-
"layers.
|
| 491 |
-
"layers.
|
| 492 |
-
"layers.
|
| 493 |
-
"layers.
|
| 494 |
-
"layers.
|
| 495 |
-
"layers.
|
| 496 |
-
"layers.
|
| 497 |
-
"layers.
|
| 498 |
-
"layers.
|
| 499 |
-
"layers.
|
| 500 |
-
"layers.
|
| 501 |
-
"layers.
|
| 502 |
-
"layers.
|
| 503 |
-
"layers.
|
| 504 |
-
"layers.
|
| 505 |
-
"layers.
|
| 506 |
-
"layers.
|
| 507 |
-
"layers.
|
| 508 |
-
"layers.
|
| 509 |
-
"layers.
|
| 510 |
-
"layers.
|
| 511 |
-
"layers.
|
| 512 |
-
"layers.
|
| 513 |
-
"layers.
|
| 514 |
-
"layers.
|
| 515 |
-
"layers.
|
| 516 |
-
"layers.
|
| 517 |
-
"layers.
|
| 518 |
-
"layers.
|
| 519 |
-
"layers.
|
| 520 |
-
"layers.
|
| 521 |
-
"layers.
|
| 522 |
-
"layers.
|
| 523 |
-
"layers.
|
| 524 |
-
"layers.
|
| 525 |
-
"layers.
|
| 526 |
-
"layers.
|
| 527 |
-
"layers.
|
| 528 |
-
"layers.
|
| 529 |
-
"layers.
|
| 530 |
-
"layers.
|
| 531 |
-
"layers.
|
| 532 |
-
"layers.
|
| 533 |
-
"layers.
|
| 534 |
-
"layers.
|
| 535 |
-
"layers.
|
| 536 |
-
"layers.
|
| 537 |
-
"layers.
|
| 538 |
-
"layers.
|
| 539 |
-
"layers.
|
| 540 |
-
"layers.
|
| 541 |
-
"layers.
|
| 542 |
-
"layers.
|
| 543 |
-
"layers.
|
| 544 |
-
"layers.
|
| 545 |
-
"layers.
|
| 546 |
-
"layers.
|
| 547 |
-
"layers.
|
| 548 |
-
"layers.
|
| 549 |
-
"layers.
|
| 550 |
-
"layers.
|
| 551 |
-
"layers.
|
| 552 |
-
"layers.
|
| 553 |
-
"layers.
|
| 554 |
-
"layers.
|
| 555 |
-
"layers.
|
| 556 |
-
"layers.
|
| 557 |
-
"layers.
|
| 558 |
-
"layers.
|
| 559 |
-
"layers.
|
| 560 |
-
"layers.
|
| 561 |
-
"layers.
|
| 562 |
-
"layers.
|
| 563 |
-
"layers.
|
| 564 |
-
"layers.
|
| 565 |
-
"layers.
|
| 566 |
-
"layers.
|
| 567 |
-
"layers.
|
| 568 |
-
"layers.
|
| 569 |
-
"layers.
|
| 570 |
-
"layers.
|
| 571 |
-
"layers.
|
| 572 |
-
"layers.
|
| 573 |
-
"layers.
|
| 574 |
-
"layers.
|
| 575 |
-
"layers.
|
| 576 |
-
"layers.
|
| 577 |
-
"layers.
|
| 578 |
-
"layers.
|
| 579 |
-
"layers.
|
| 580 |
-
"layers.
|
| 581 |
-
"layers.
|
| 582 |
-
"layers.
|
| 583 |
-
"layers.
|
| 584 |
-
"layers.
|
| 585 |
-
"layers.
|
| 586 |
-
"layers.
|
| 587 |
-
"layers.
|
| 588 |
-
"layers.
|
| 589 |
-
"layers.
|
| 590 |
-
"layers.
|
| 591 |
-
"layers.
|
| 592 |
-
"layers.
|
| 593 |
-
"layers.
|
| 594 |
-
"layers.
|
| 595 |
-
"layers.
|
| 596 |
-
"layers.
|
| 597 |
-
"layers.
|
| 598 |
-
"layers.
|
| 599 |
-
"layers.
|
| 600 |
-
"layers.
|
| 601 |
-
"layers.
|
| 602 |
-
"layers.
|
| 603 |
-
"layers.
|
| 604 |
-
"layers.
|
| 605 |
-
"layers.
|
| 606 |
-
"layers.
|
| 607 |
-
"layers.
|
| 608 |
-
"layers.
|
| 609 |
-
"layers.
|
| 610 |
-
"layers.
|
| 611 |
-
"layers.
|
| 612 |
-
"layers.
|
| 613 |
-
"layers.
|
| 614 |
-
"layers.
|
| 615 |
-
"layers.
|
| 616 |
-
"layers.
|
| 617 |
-
"layers.
|
| 618 |
-
"layers.
|
| 619 |
-
"layers.
|
| 620 |
-
"layers.
|
| 621 |
-
"layers.
|
| 622 |
-
"layers.
|
| 623 |
-
"layers.
|
| 624 |
-
"layers.
|
| 625 |
-
"layers.
|
| 626 |
-
"layers.
|
| 627 |
-
"layers.
|
| 628 |
-
"layers.
|
| 629 |
-
"layers.
|
| 630 |
-
"layers.
|
| 631 |
-
"layers.
|
| 632 |
-
"layers.
|
| 633 |
-
"layers.
|
| 634 |
-
"layers.
|
| 635 |
-
"layers.
|
| 636 |
-
"layers.
|
| 637 |
-
"layers.
|
| 638 |
-
"layers.
|
| 639 |
-
"layers.
|
| 640 |
-
"layers.
|
| 641 |
-
"layers.
|
| 642 |
-
"layers.
|
| 643 |
-
"layers.
|
| 644 |
-
"layers.
|
| 645 |
-
"layers.
|
| 646 |
-
"layers.
|
| 647 |
-
"layers.
|
| 648 |
-
"layers.
|
| 649 |
-
"layers.
|
| 650 |
-
"layers.
|
| 651 |
-
"layers.
|
| 652 |
-
"layers.
|
| 653 |
-
"layers.
|
| 654 |
-
"layers.
|
| 655 |
-
"layers.
|
| 656 |
-
"
|
| 657 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 658 |
}
|
| 659 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"quantization_level": "4",
|
| 4 |
+
"mflux_version": "0.20.0"
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"embed_tokens.weight": "0.safetensors",
|
| 8 |
+
"embed_tokens.scales": "0.safetensors",
|
| 9 |
+
"embed_tokens.biases": "0.safetensors",
|
| 10 |
"layers.0.input_layernorm.weight": "0.safetensors",
|
| 11 |
"layers.0.self_attn.q_proj.weight": "0.safetensors",
|
| 12 |
+
"layers.0.self_attn.q_proj.scales": "0.safetensors",
|
| 13 |
+
"layers.0.self_attn.q_proj.biases": "0.safetensors",
|
| 14 |
"layers.0.self_attn.k_proj.weight": "0.safetensors",
|
| 15 |
+
"layers.0.self_attn.k_proj.scales": "0.safetensors",
|
| 16 |
+
"layers.0.self_attn.k_proj.biases": "0.safetensors",
|
| 17 |
"layers.0.self_attn.v_proj.weight": "0.safetensors",
|
| 18 |
+
"layers.0.self_attn.v_proj.scales": "0.safetensors",
|
| 19 |
+
"layers.0.self_attn.v_proj.biases": "0.safetensors",
|
| 20 |
"layers.0.self_attn.o_proj.weight": "0.safetensors",
|
| 21 |
+
"layers.0.self_attn.o_proj.scales": "0.safetensors",
|
| 22 |
+
"layers.0.self_attn.o_proj.biases": "0.safetensors",
|
| 23 |
"layers.0.self_attn.q_norm.weight": "0.safetensors",
|
| 24 |
"layers.0.self_attn.k_norm.weight": "0.safetensors",
|
| 25 |
"layers.0.post_attention_layernorm.weight": "0.safetensors",
|
| 26 |
"layers.0.mlp.gate_proj.weight": "0.safetensors",
|
| 27 |
+
"layers.0.mlp.gate_proj.scales": "0.safetensors",
|
| 28 |
+
"layers.0.mlp.gate_proj.biases": "0.safetensors",
|
| 29 |
"layers.0.mlp.up_proj.weight": "0.safetensors",
|
| 30 |
+
"layers.0.mlp.up_proj.scales": "0.safetensors",
|
| 31 |
+
"layers.0.mlp.up_proj.biases": "0.safetensors",
|
| 32 |
"layers.0.mlp.down_proj.weight": "0.safetensors",
|
| 33 |
+
"layers.0.mlp.down_proj.scales": "0.safetensors",
|
| 34 |
+
"layers.0.mlp.down_proj.biases": "0.safetensors",
|
| 35 |
"layers.1.input_layernorm.weight": "0.safetensors",
|
| 36 |
"layers.1.self_attn.q_proj.weight": "0.safetensors",
|
| 37 |
+
"layers.1.self_attn.q_proj.scales": "0.safetensors",
|
| 38 |
+
"layers.1.self_attn.q_proj.biases": "0.safetensors",
|
| 39 |
"layers.1.self_attn.k_proj.weight": "0.safetensors",
|
| 40 |
+
"layers.1.self_attn.k_proj.scales": "0.safetensors",
|
| 41 |
+
"layers.1.self_attn.k_proj.biases": "0.safetensors",
|
| 42 |
"layers.1.self_attn.v_proj.weight": "0.safetensors",
|
| 43 |
+
"layers.1.self_attn.v_proj.scales": "0.safetensors",
|
| 44 |
+
"layers.1.self_attn.v_proj.biases": "0.safetensors",
|
| 45 |
"layers.1.self_attn.o_proj.weight": "0.safetensors",
|
| 46 |
+
"layers.1.self_attn.o_proj.scales": "0.safetensors",
|
| 47 |
+
"layers.1.self_attn.o_proj.biases": "0.safetensors",
|
| 48 |
"layers.1.self_attn.q_norm.weight": "0.safetensors",
|
| 49 |
"layers.1.self_attn.k_norm.weight": "0.safetensors",
|
| 50 |
"layers.1.post_attention_layernorm.weight": "0.safetensors",
|
| 51 |
"layers.1.mlp.gate_proj.weight": "0.safetensors",
|
| 52 |
+
"layers.1.mlp.gate_proj.scales": "0.safetensors",
|
| 53 |
+
"layers.1.mlp.gate_proj.biases": "0.safetensors",
|
| 54 |
"layers.1.mlp.up_proj.weight": "0.safetensors",
|
| 55 |
+
"layers.1.mlp.up_proj.scales": "0.safetensors",
|
| 56 |
+
"layers.1.mlp.up_proj.biases": "0.safetensors",
|
| 57 |
"layers.1.mlp.down_proj.weight": "0.safetensors",
|
| 58 |
+
"layers.1.mlp.down_proj.scales": "0.safetensors",
|
| 59 |
+
"layers.1.mlp.down_proj.biases": "0.safetensors",
|
| 60 |
"layers.2.input_layernorm.weight": "0.safetensors",
|
| 61 |
"layers.2.self_attn.q_proj.weight": "0.safetensors",
|
| 62 |
+
"layers.2.self_attn.q_proj.scales": "0.safetensors",
|
| 63 |
+
"layers.2.self_attn.q_proj.biases": "0.safetensors",
|
| 64 |
"layers.2.self_attn.k_proj.weight": "0.safetensors",
|
| 65 |
+
"layers.2.self_attn.k_proj.scales": "0.safetensors",
|
| 66 |
+
"layers.2.self_attn.k_proj.biases": "0.safetensors",
|
| 67 |
"layers.2.self_attn.v_proj.weight": "0.safetensors",
|
| 68 |
+
"layers.2.self_attn.v_proj.scales": "0.safetensors",
|
| 69 |
+
"layers.2.self_attn.v_proj.biases": "0.safetensors",
|
| 70 |
"layers.2.self_attn.o_proj.weight": "0.safetensors",
|
| 71 |
+
"layers.2.self_attn.o_proj.scales": "0.safetensors",
|
| 72 |
+
"layers.2.self_attn.o_proj.biases": "0.safetensors",
|
| 73 |
"layers.2.self_attn.q_norm.weight": "0.safetensors",
|
| 74 |
"layers.2.self_attn.k_norm.weight": "0.safetensors",
|
| 75 |
"layers.2.post_attention_layernorm.weight": "0.safetensors",
|
| 76 |
"layers.2.mlp.gate_proj.weight": "0.safetensors",
|
| 77 |
+
"layers.2.mlp.gate_proj.scales": "0.safetensors",
|
| 78 |
+
"layers.2.mlp.gate_proj.biases": "0.safetensors",
|
| 79 |
"layers.2.mlp.up_proj.weight": "0.safetensors",
|
| 80 |
+
"layers.2.mlp.up_proj.scales": "0.safetensors",
|
| 81 |
+
"layers.2.mlp.up_proj.biases": "0.safetensors",
|
| 82 |
"layers.2.mlp.down_proj.weight": "0.safetensors",
|
| 83 |
+
"layers.2.mlp.down_proj.scales": "0.safetensors",
|
| 84 |
+
"layers.2.mlp.down_proj.biases": "0.safetensors",
|
| 85 |
"layers.3.input_layernorm.weight": "0.safetensors",
|
| 86 |
"layers.3.self_attn.q_proj.weight": "0.safetensors",
|
| 87 |
+
"layers.3.self_attn.q_proj.scales": "0.safetensors",
|
| 88 |
+
"layers.3.self_attn.q_proj.biases": "0.safetensors",
|
| 89 |
"layers.3.self_attn.k_proj.weight": "0.safetensors",
|
| 90 |
+
"layers.3.self_attn.k_proj.scales": "0.safetensors",
|
| 91 |
+
"layers.3.self_attn.k_proj.biases": "0.safetensors",
|
| 92 |
"layers.3.self_attn.v_proj.weight": "0.safetensors",
|
| 93 |
+
"layers.3.self_attn.v_proj.scales": "0.safetensors",
|
| 94 |
+
"layers.3.self_attn.v_proj.biases": "0.safetensors",
|
| 95 |
"layers.3.self_attn.o_proj.weight": "0.safetensors",
|
| 96 |
+
"layers.3.self_attn.o_proj.scales": "0.safetensors",
|
| 97 |
+
"layers.3.self_attn.o_proj.biases": "0.safetensors",
|
| 98 |
"layers.3.self_attn.q_norm.weight": "0.safetensors",
|
| 99 |
"layers.3.self_attn.k_norm.weight": "0.safetensors",
|
| 100 |
"layers.3.post_attention_layernorm.weight": "0.safetensors",
|
| 101 |
"layers.3.mlp.gate_proj.weight": "0.safetensors",
|
| 102 |
+
"layers.3.mlp.gate_proj.scales": "0.safetensors",
|
| 103 |
+
"layers.3.mlp.gate_proj.biases": "0.safetensors",
|
| 104 |
"layers.3.mlp.up_proj.weight": "0.safetensors",
|
| 105 |
+
"layers.3.mlp.up_proj.scales": "0.safetensors",
|
| 106 |
+
"layers.3.mlp.up_proj.biases": "0.safetensors",
|
| 107 |
"layers.3.mlp.down_proj.weight": "0.safetensors",
|
| 108 |
+
"layers.3.mlp.down_proj.scales": "0.safetensors",
|
| 109 |
+
"layers.3.mlp.down_proj.biases": "0.safetensors",
|
| 110 |
"layers.4.input_layernorm.weight": "0.safetensors",
|
| 111 |
"layers.4.self_attn.q_proj.weight": "0.safetensors",
|
| 112 |
+
"layers.4.self_attn.q_proj.scales": "0.safetensors",
|
| 113 |
+
"layers.4.self_attn.q_proj.biases": "0.safetensors",
|
| 114 |
"layers.4.self_attn.k_proj.weight": "0.safetensors",
|
| 115 |
+
"layers.4.self_attn.k_proj.scales": "0.safetensors",
|
| 116 |
+
"layers.4.self_attn.k_proj.biases": "0.safetensors",
|
| 117 |
"layers.4.self_attn.v_proj.weight": "0.safetensors",
|
| 118 |
+
"layers.4.self_attn.v_proj.scales": "0.safetensors",
|
| 119 |
+
"layers.4.self_attn.v_proj.biases": "0.safetensors",
|
| 120 |
"layers.4.self_attn.o_proj.weight": "0.safetensors",
|
| 121 |
+
"layers.4.self_attn.o_proj.scales": "0.safetensors",
|
| 122 |
+
"layers.4.self_attn.o_proj.biases": "0.safetensors",
|
| 123 |
"layers.4.self_attn.q_norm.weight": "0.safetensors",
|
| 124 |
"layers.4.self_attn.k_norm.weight": "0.safetensors",
|
| 125 |
"layers.4.post_attention_layernorm.weight": "0.safetensors",
|
| 126 |
"layers.4.mlp.gate_proj.weight": "0.safetensors",
|
| 127 |
+
"layers.4.mlp.gate_proj.scales": "0.safetensors",
|
| 128 |
+
"layers.4.mlp.gate_proj.biases": "0.safetensors",
|
| 129 |
+
"layers.4.mlp.up_proj.weight": "0.safetensors",
|
| 130 |
+
"layers.4.mlp.up_proj.scales": "0.safetensors",
|
| 131 |
+
"layers.4.mlp.up_proj.biases": "0.safetensors",
|
| 132 |
+
"layers.4.mlp.down_proj.weight": "0.safetensors",
|
| 133 |
+
"layers.4.mlp.down_proj.scales": "0.safetensors",
|
| 134 |
+
"layers.4.mlp.down_proj.biases": "0.safetensors",
|
| 135 |
+
"layers.5.input_layernorm.weight": "0.safetensors",
|
| 136 |
+
"layers.5.self_attn.q_proj.weight": "0.safetensors",
|
| 137 |
+
"layers.5.self_attn.q_proj.scales": "0.safetensors",
|
| 138 |
+
"layers.5.self_attn.q_proj.biases": "0.safetensors",
|
| 139 |
+
"layers.5.self_attn.k_proj.weight": "0.safetensors",
|
| 140 |
+
"layers.5.self_attn.k_proj.scales": "0.safetensors",
|
| 141 |
+
"layers.5.self_attn.k_proj.biases": "0.safetensors",
|
| 142 |
+
"layers.5.self_attn.v_proj.weight": "0.safetensors",
|
| 143 |
+
"layers.5.self_attn.v_proj.scales": "0.safetensors",
|
| 144 |
+
"layers.5.self_attn.v_proj.biases": "0.safetensors",
|
| 145 |
+
"layers.5.self_attn.o_proj.weight": "0.safetensors",
|
| 146 |
+
"layers.5.self_attn.o_proj.scales": "0.safetensors",
|
| 147 |
+
"layers.5.self_attn.o_proj.biases": "0.safetensors",
|
| 148 |
+
"layers.5.self_attn.q_norm.weight": "0.safetensors",
|
| 149 |
+
"layers.5.self_attn.k_norm.weight": "0.safetensors",
|
| 150 |
+
"layers.5.post_attention_layernorm.weight": "0.safetensors",
|
| 151 |
+
"layers.5.mlp.gate_proj.weight": "0.safetensors",
|
| 152 |
+
"layers.5.mlp.gate_proj.scales": "0.safetensors",
|
| 153 |
+
"layers.5.mlp.gate_proj.biases": "0.safetensors",
|
| 154 |
+
"layers.5.mlp.up_proj.weight": "0.safetensors",
|
| 155 |
+
"layers.5.mlp.up_proj.scales": "0.safetensors",
|
| 156 |
+
"layers.5.mlp.up_proj.biases": "0.safetensors",
|
| 157 |
+
"layers.5.mlp.down_proj.weight": "0.safetensors",
|
| 158 |
+
"layers.5.mlp.down_proj.scales": "0.safetensors",
|
| 159 |
+
"layers.5.mlp.down_proj.biases": "0.safetensors",
|
| 160 |
+
"layers.6.input_layernorm.weight": "0.safetensors",
|
| 161 |
+
"layers.6.self_attn.q_proj.weight": "0.safetensors",
|
| 162 |
+
"layers.6.self_attn.q_proj.scales": "0.safetensors",
|
| 163 |
+
"layers.6.self_attn.q_proj.biases": "0.safetensors",
|
| 164 |
+
"layers.6.self_attn.k_proj.weight": "0.safetensors",
|
| 165 |
+
"layers.6.self_attn.k_proj.scales": "0.safetensors",
|
| 166 |
+
"layers.6.self_attn.k_proj.biases": "0.safetensors",
|
| 167 |
+
"layers.6.self_attn.v_proj.weight": "0.safetensors",
|
| 168 |
+
"layers.6.self_attn.v_proj.scales": "0.safetensors",
|
| 169 |
+
"layers.6.self_attn.v_proj.biases": "0.safetensors",
|
| 170 |
+
"layers.6.self_attn.o_proj.weight": "0.safetensors",
|
| 171 |
+
"layers.6.self_attn.o_proj.scales": "0.safetensors",
|
| 172 |
+
"layers.6.self_attn.o_proj.biases": "0.safetensors",
|
| 173 |
+
"layers.6.self_attn.q_norm.weight": "0.safetensors",
|
| 174 |
+
"layers.6.self_attn.k_norm.weight": "0.safetensors",
|
| 175 |
+
"layers.6.post_attention_layernorm.weight": "0.safetensors",
|
| 176 |
+
"layers.6.mlp.gate_proj.weight": "0.safetensors",
|
| 177 |
+
"layers.6.mlp.gate_proj.scales": "0.safetensors",
|
| 178 |
+
"layers.6.mlp.gate_proj.biases": "0.safetensors",
|
| 179 |
+
"layers.6.mlp.up_proj.weight": "0.safetensors",
|
| 180 |
+
"layers.6.mlp.up_proj.scales": "0.safetensors",
|
| 181 |
+
"layers.6.mlp.up_proj.biases": "0.safetensors",
|
| 182 |
+
"layers.6.mlp.down_proj.weight": "0.safetensors",
|
| 183 |
+
"layers.6.mlp.down_proj.scales": "0.safetensors",
|
| 184 |
+
"layers.6.mlp.down_proj.biases": "0.safetensors",
|
| 185 |
+
"layers.7.input_layernorm.weight": "0.safetensors",
|
| 186 |
+
"layers.7.self_attn.q_proj.weight": "0.safetensors",
|
| 187 |
+
"layers.7.self_attn.q_proj.scales": "0.safetensors",
|
| 188 |
+
"layers.7.self_attn.q_proj.biases": "0.safetensors",
|
| 189 |
+
"layers.7.self_attn.k_proj.weight": "0.safetensors",
|
| 190 |
+
"layers.7.self_attn.k_proj.scales": "0.safetensors",
|
| 191 |
+
"layers.7.self_attn.k_proj.biases": "0.safetensors",
|
| 192 |
+
"layers.7.self_attn.v_proj.weight": "0.safetensors",
|
| 193 |
+
"layers.7.self_attn.v_proj.scales": "0.safetensors",
|
| 194 |
+
"layers.7.self_attn.v_proj.biases": "0.safetensors",
|
| 195 |
+
"layers.7.self_attn.o_proj.weight": "0.safetensors",
|
| 196 |
+
"layers.7.self_attn.o_proj.scales": "0.safetensors",
|
| 197 |
+
"layers.7.self_attn.o_proj.biases": "0.safetensors",
|
| 198 |
+
"layers.7.self_attn.q_norm.weight": "0.safetensors",
|
| 199 |
+
"layers.7.self_attn.k_norm.weight": "0.safetensors",
|
| 200 |
+
"layers.7.post_attention_layernorm.weight": "0.safetensors",
|
| 201 |
+
"layers.7.mlp.gate_proj.weight": "0.safetensors",
|
| 202 |
+
"layers.7.mlp.gate_proj.scales": "0.safetensors",
|
| 203 |
+
"layers.7.mlp.gate_proj.biases": "0.safetensors",
|
| 204 |
+
"layers.7.mlp.up_proj.weight": "0.safetensors",
|
| 205 |
+
"layers.7.mlp.up_proj.scales": "0.safetensors",
|
| 206 |
+
"layers.7.mlp.up_proj.biases": "0.safetensors",
|
| 207 |
+
"layers.7.mlp.down_proj.weight": "0.safetensors",
|
| 208 |
+
"layers.7.mlp.down_proj.scales": "0.safetensors",
|
| 209 |
+
"layers.7.mlp.down_proj.biases": "0.safetensors",
|
| 210 |
+
"layers.8.input_layernorm.weight": "0.safetensors",
|
| 211 |
+
"layers.8.self_attn.q_proj.weight": "0.safetensors",
|
| 212 |
+
"layers.8.self_attn.q_proj.scales": "0.safetensors",
|
| 213 |
+
"layers.8.self_attn.q_proj.biases": "0.safetensors",
|
| 214 |
+
"layers.8.self_attn.k_proj.weight": "0.safetensors",
|
| 215 |
+
"layers.8.self_attn.k_proj.scales": "0.safetensors",
|
| 216 |
+
"layers.8.self_attn.k_proj.biases": "0.safetensors",
|
| 217 |
+
"layers.8.self_attn.v_proj.weight": "0.safetensors",
|
| 218 |
+
"layers.8.self_attn.v_proj.scales": "0.safetensors",
|
| 219 |
+
"layers.8.self_attn.v_proj.biases": "0.safetensors",
|
| 220 |
+
"layers.8.self_attn.o_proj.weight": "0.safetensors",
|
| 221 |
+
"layers.8.self_attn.o_proj.scales": "0.safetensors",
|
| 222 |
+
"layers.8.self_attn.o_proj.biases": "0.safetensors",
|
| 223 |
+
"layers.8.self_attn.q_norm.weight": "0.safetensors",
|
| 224 |
+
"layers.8.self_attn.k_norm.weight": "0.safetensors",
|
| 225 |
+
"layers.8.post_attention_layernorm.weight": "0.safetensors",
|
| 226 |
+
"layers.8.mlp.gate_proj.weight": "0.safetensors",
|
| 227 |
+
"layers.8.mlp.gate_proj.scales": "0.safetensors",
|
| 228 |
+
"layers.8.mlp.gate_proj.biases": "0.safetensors",
|
| 229 |
+
"layers.8.mlp.up_proj.weight": "0.safetensors",
|
| 230 |
+
"layers.8.mlp.up_proj.scales": "0.safetensors",
|
| 231 |
+
"layers.8.mlp.up_proj.biases": "0.safetensors",
|
| 232 |
+
"layers.8.mlp.down_proj.weight": "0.safetensors",
|
| 233 |
+
"layers.8.mlp.down_proj.scales": "0.safetensors",
|
| 234 |
+
"layers.8.mlp.down_proj.biases": "0.safetensors",
|
| 235 |
+
"layers.9.input_layernorm.weight": "0.safetensors",
|
| 236 |
+
"layers.9.self_attn.q_proj.weight": "0.safetensors",
|
| 237 |
+
"layers.9.self_attn.q_proj.scales": "0.safetensors",
|
| 238 |
+
"layers.9.self_attn.q_proj.biases": "0.safetensors",
|
| 239 |
+
"layers.9.self_attn.k_proj.weight": "0.safetensors",
|
| 240 |
+
"layers.9.self_attn.k_proj.scales": "0.safetensors",
|
| 241 |
+
"layers.9.self_attn.k_proj.biases": "0.safetensors",
|
| 242 |
+
"layers.9.self_attn.v_proj.weight": "0.safetensors",
|
| 243 |
+
"layers.9.self_attn.v_proj.scales": "0.safetensors",
|
| 244 |
+
"layers.9.self_attn.v_proj.biases": "0.safetensors",
|
| 245 |
+
"layers.9.self_attn.o_proj.weight": "0.safetensors",
|
| 246 |
+
"layers.9.self_attn.o_proj.scales": "0.safetensors",
|
| 247 |
+
"layers.9.self_attn.o_proj.biases": "0.safetensors",
|
| 248 |
+
"layers.9.self_attn.q_norm.weight": "0.safetensors",
|
| 249 |
+
"layers.9.self_attn.k_norm.weight": "0.safetensors",
|
| 250 |
+
"layers.9.post_attention_layernorm.weight": "0.safetensors",
|
| 251 |
+
"layers.9.mlp.gate_proj.weight": "0.safetensors",
|
| 252 |
+
"layers.9.mlp.gate_proj.scales": "0.safetensors",
|
| 253 |
+
"layers.9.mlp.gate_proj.biases": "0.safetensors",
|
| 254 |
+
"layers.9.mlp.up_proj.weight": "0.safetensors",
|
| 255 |
+
"layers.9.mlp.up_proj.scales": "0.safetensors",
|
| 256 |
+
"layers.9.mlp.up_proj.biases": "0.safetensors",
|
| 257 |
+
"layers.9.mlp.down_proj.weight": "0.safetensors",
|
| 258 |
+
"layers.9.mlp.down_proj.scales": "0.safetensors",
|
| 259 |
+
"layers.9.mlp.down_proj.biases": "0.safetensors",
|
| 260 |
+
"layers.10.input_layernorm.weight": "0.safetensors",
|
| 261 |
+
"layers.10.self_attn.q_proj.weight": "0.safetensors",
|
| 262 |
+
"layers.10.self_attn.q_proj.scales": "0.safetensors",
|
| 263 |
+
"layers.10.self_attn.q_proj.biases": "0.safetensors",
|
| 264 |
+
"layers.10.self_attn.k_proj.weight": "0.safetensors",
|
| 265 |
+
"layers.10.self_attn.k_proj.scales": "0.safetensors",
|
| 266 |
+
"layers.10.self_attn.k_proj.biases": "0.safetensors",
|
| 267 |
+
"layers.10.self_attn.v_proj.weight": "0.safetensors",
|
| 268 |
+
"layers.10.self_attn.v_proj.scales": "0.safetensors",
|
| 269 |
+
"layers.10.self_attn.v_proj.biases": "0.safetensors",
|
| 270 |
+
"layers.10.self_attn.o_proj.weight": "0.safetensors",
|
| 271 |
+
"layers.10.self_attn.o_proj.scales": "0.safetensors",
|
| 272 |
+
"layers.10.self_attn.o_proj.biases": "0.safetensors",
|
| 273 |
+
"layers.10.self_attn.q_norm.weight": "0.safetensors",
|
| 274 |
+
"layers.10.self_attn.k_norm.weight": "0.safetensors",
|
| 275 |
+
"layers.10.post_attention_layernorm.weight": "0.safetensors",
|
| 276 |
+
"layers.10.mlp.gate_proj.weight": "0.safetensors",
|
| 277 |
+
"layers.10.mlp.gate_proj.scales": "0.safetensors",
|
| 278 |
+
"layers.10.mlp.gate_proj.biases": "0.safetensors",
|
| 279 |
+
"layers.10.mlp.up_proj.weight": "0.safetensors",
|
| 280 |
+
"layers.10.mlp.up_proj.scales": "0.safetensors",
|
| 281 |
+
"layers.10.mlp.up_proj.biases": "0.safetensors",
|
| 282 |
+
"layers.10.mlp.down_proj.weight": "0.safetensors",
|
| 283 |
+
"layers.10.mlp.down_proj.scales": "0.safetensors",
|
| 284 |
+
"layers.10.mlp.down_proj.biases": "0.safetensors",
|
| 285 |
+
"layers.11.input_layernorm.weight": "0.safetensors",
|
| 286 |
+
"layers.11.self_attn.q_proj.weight": "0.safetensors",
|
| 287 |
+
"layers.11.self_attn.q_proj.scales": "0.safetensors",
|
| 288 |
+
"layers.11.self_attn.q_proj.biases": "0.safetensors",
|
| 289 |
+
"layers.11.self_attn.k_proj.weight": "0.safetensors",
|
| 290 |
+
"layers.11.self_attn.k_proj.scales": "0.safetensors",
|
| 291 |
+
"layers.11.self_attn.k_proj.biases": "0.safetensors",
|
| 292 |
+
"layers.11.self_attn.v_proj.weight": "0.safetensors",
|
| 293 |
+
"layers.11.self_attn.v_proj.scales": "0.safetensors",
|
| 294 |
+
"layers.11.self_attn.v_proj.biases": "0.safetensors",
|
| 295 |
+
"layers.11.self_attn.o_proj.weight": "0.safetensors",
|
| 296 |
+
"layers.11.self_attn.o_proj.scales": "0.safetensors",
|
| 297 |
+
"layers.11.self_attn.o_proj.biases": "0.safetensors",
|
| 298 |
+
"layers.11.self_attn.q_norm.weight": "0.safetensors",
|
| 299 |
+
"layers.11.self_attn.k_norm.weight": "0.safetensors",
|
| 300 |
+
"layers.11.post_attention_layernorm.weight": "0.safetensors",
|
| 301 |
+
"layers.11.mlp.gate_proj.weight": "0.safetensors",
|
| 302 |
+
"layers.11.mlp.gate_proj.scales": "0.safetensors",
|
| 303 |
+
"layers.11.mlp.gate_proj.biases": "0.safetensors",
|
| 304 |
+
"layers.11.mlp.up_proj.weight": "0.safetensors",
|
| 305 |
+
"layers.11.mlp.up_proj.scales": "0.safetensors",
|
| 306 |
+
"layers.11.mlp.up_proj.biases": "0.safetensors",
|
| 307 |
+
"layers.11.mlp.down_proj.weight": "0.safetensors",
|
| 308 |
+
"layers.11.mlp.down_proj.scales": "0.safetensors",
|
| 309 |
+
"layers.11.mlp.down_proj.biases": "0.safetensors",
|
| 310 |
+
"layers.12.input_layernorm.weight": "0.safetensors",
|
| 311 |
+
"layers.12.self_attn.q_proj.weight": "0.safetensors",
|
| 312 |
+
"layers.12.self_attn.q_proj.scales": "0.safetensors",
|
| 313 |
+
"layers.12.self_attn.q_proj.biases": "0.safetensors",
|
| 314 |
+
"layers.12.self_attn.k_proj.weight": "0.safetensors",
|
| 315 |
+
"layers.12.self_attn.k_proj.scales": "0.safetensors",
|
| 316 |
+
"layers.12.self_attn.k_proj.biases": "0.safetensors",
|
| 317 |
+
"layers.12.self_attn.v_proj.weight": "0.safetensors",
|
| 318 |
+
"layers.12.self_attn.v_proj.scales": "0.safetensors",
|
| 319 |
+
"layers.12.self_attn.v_proj.biases": "0.safetensors",
|
| 320 |
+
"layers.12.self_attn.o_proj.weight": "0.safetensors",
|
| 321 |
+
"layers.12.self_attn.o_proj.scales": "0.safetensors",
|
| 322 |
+
"layers.12.self_attn.o_proj.biases": "0.safetensors",
|
| 323 |
+
"layers.12.self_attn.q_norm.weight": "0.safetensors",
|
| 324 |
+
"layers.12.self_attn.k_norm.weight": "0.safetensors",
|
| 325 |
+
"layers.12.post_attention_layernorm.weight": "0.safetensors",
|
| 326 |
+
"layers.12.mlp.gate_proj.weight": "0.safetensors",
|
| 327 |
+
"layers.12.mlp.gate_proj.scales": "0.safetensors",
|
| 328 |
+
"layers.12.mlp.gate_proj.biases": "0.safetensors",
|
| 329 |
+
"layers.12.mlp.up_proj.weight": "0.safetensors",
|
| 330 |
+
"layers.12.mlp.up_proj.scales": "0.safetensors",
|
| 331 |
+
"layers.12.mlp.up_proj.biases": "0.safetensors",
|
| 332 |
+
"layers.12.mlp.down_proj.weight": "0.safetensors",
|
| 333 |
+
"layers.12.mlp.down_proj.scales": "0.safetensors",
|
| 334 |
+
"layers.12.mlp.down_proj.biases": "0.safetensors",
|
| 335 |
+
"layers.13.input_layernorm.weight": "0.safetensors",
|
| 336 |
+
"layers.13.self_attn.q_proj.weight": "0.safetensors",
|
| 337 |
+
"layers.13.self_attn.q_proj.scales": "0.safetensors",
|
| 338 |
+
"layers.13.self_attn.q_proj.biases": "0.safetensors",
|
| 339 |
+
"layers.13.self_attn.k_proj.weight": "0.safetensors",
|
| 340 |
+
"layers.13.self_attn.k_proj.scales": "0.safetensors",
|
| 341 |
+
"layers.13.self_attn.k_proj.biases": "0.safetensors",
|
| 342 |
+
"layers.13.self_attn.v_proj.weight": "0.safetensors",
|
| 343 |
+
"layers.13.self_attn.v_proj.scales": "0.safetensors",
|
| 344 |
+
"layers.13.self_attn.v_proj.biases": "0.safetensors",
|
| 345 |
+
"layers.13.self_attn.o_proj.weight": "0.safetensors",
|
| 346 |
+
"layers.13.self_attn.o_proj.scales": "0.safetensors",
|
| 347 |
+
"layers.13.self_attn.o_proj.biases": "0.safetensors",
|
| 348 |
+
"layers.13.self_attn.q_norm.weight": "0.safetensors",
|
| 349 |
+
"layers.13.self_attn.k_norm.weight": "0.safetensors",
|
| 350 |
+
"layers.13.post_attention_layernorm.weight": "0.safetensors",
|
| 351 |
+
"layers.13.mlp.gate_proj.weight": "0.safetensors",
|
| 352 |
+
"layers.13.mlp.gate_proj.scales": "0.safetensors",
|
| 353 |
+
"layers.13.mlp.gate_proj.biases": "0.safetensors",
|
| 354 |
+
"layers.13.mlp.up_proj.weight": "0.safetensors",
|
| 355 |
+
"layers.13.mlp.up_proj.scales": "0.safetensors",
|
| 356 |
+
"layers.13.mlp.up_proj.biases": "0.safetensors",
|
| 357 |
+
"layers.13.mlp.down_proj.weight": "0.safetensors",
|
| 358 |
+
"layers.13.mlp.down_proj.scales": "0.safetensors",
|
| 359 |
+
"layers.13.mlp.down_proj.biases": "0.safetensors",
|
| 360 |
+
"layers.14.input_layernorm.weight": "0.safetensors",
|
| 361 |
+
"layers.14.self_attn.q_proj.weight": "0.safetensors",
|
| 362 |
+
"layers.14.self_attn.q_proj.scales": "0.safetensors",
|
| 363 |
+
"layers.14.self_attn.q_proj.biases": "0.safetensors",
|
| 364 |
+
"layers.14.self_attn.k_proj.weight": "0.safetensors",
|
| 365 |
+
"layers.14.self_attn.k_proj.scales": "0.safetensors",
|
| 366 |
+
"layers.14.self_attn.k_proj.biases": "0.safetensors",
|
| 367 |
+
"layers.14.self_attn.v_proj.weight": "0.safetensors",
|
| 368 |
+
"layers.14.self_attn.v_proj.scales": "0.safetensors",
|
| 369 |
+
"layers.14.self_attn.v_proj.biases": "0.safetensors",
|
| 370 |
+
"layers.14.self_attn.o_proj.weight": "0.safetensors",
|
| 371 |
+
"layers.14.self_attn.o_proj.scales": "0.safetensors",
|
| 372 |
+
"layers.14.self_attn.o_proj.biases": "0.safetensors",
|
| 373 |
+
"layers.14.self_attn.q_norm.weight": "0.safetensors",
|
| 374 |
+
"layers.14.self_attn.k_norm.weight": "0.safetensors",
|
| 375 |
+
"layers.14.post_attention_layernorm.weight": "0.safetensors",
|
| 376 |
+
"layers.14.mlp.gate_proj.weight": "0.safetensors",
|
| 377 |
+
"layers.14.mlp.gate_proj.scales": "0.safetensors",
|
| 378 |
+
"layers.14.mlp.gate_proj.biases": "0.safetensors",
|
| 379 |
+
"layers.14.mlp.up_proj.weight": "0.safetensors",
|
| 380 |
+
"layers.14.mlp.up_proj.scales": "0.safetensors",
|
| 381 |
+
"layers.14.mlp.up_proj.biases": "0.safetensors",
|
| 382 |
+
"layers.14.mlp.down_proj.weight": "0.safetensors",
|
| 383 |
+
"layers.14.mlp.down_proj.scales": "0.safetensors",
|
| 384 |
+
"layers.14.mlp.down_proj.biases": "0.safetensors",
|
| 385 |
+
"layers.15.input_layernorm.weight": "0.safetensors",
|
| 386 |
+
"layers.15.self_attn.q_proj.weight": "0.safetensors",
|
| 387 |
+
"layers.15.self_attn.q_proj.scales": "0.safetensors",
|
| 388 |
+
"layers.15.self_attn.q_proj.biases": "0.safetensors",
|
| 389 |
+
"layers.15.self_attn.k_proj.weight": "0.safetensors",
|
| 390 |
+
"layers.15.self_attn.k_proj.scales": "0.safetensors",
|
| 391 |
+
"layers.15.self_attn.k_proj.biases": "0.safetensors",
|
| 392 |
+
"layers.15.self_attn.v_proj.weight": "0.safetensors",
|
| 393 |
+
"layers.15.self_attn.v_proj.scales": "0.safetensors",
|
| 394 |
+
"layers.15.self_attn.v_proj.biases": "0.safetensors",
|
| 395 |
+
"layers.15.self_attn.o_proj.weight": "0.safetensors",
|
| 396 |
+
"layers.15.self_attn.o_proj.scales": "0.safetensors",
|
| 397 |
+
"layers.15.self_attn.o_proj.biases": "0.safetensors",
|
| 398 |
+
"layers.15.self_attn.q_norm.weight": "0.safetensors",
|
| 399 |
+
"layers.15.self_attn.k_norm.weight": "0.safetensors",
|
| 400 |
+
"layers.15.post_attention_layernorm.weight": "0.safetensors",
|
| 401 |
+
"layers.15.mlp.gate_proj.weight": "0.safetensors",
|
| 402 |
+
"layers.15.mlp.gate_proj.scales": "0.safetensors",
|
| 403 |
+
"layers.15.mlp.gate_proj.biases": "0.safetensors",
|
| 404 |
+
"layers.15.mlp.up_proj.weight": "0.safetensors",
|
| 405 |
+
"layers.15.mlp.up_proj.scales": "0.safetensors",
|
| 406 |
+
"layers.15.mlp.up_proj.biases": "0.safetensors",
|
| 407 |
+
"layers.15.mlp.down_proj.weight": "0.safetensors",
|
| 408 |
+
"layers.15.mlp.down_proj.scales": "0.safetensors",
|
| 409 |
+
"layers.15.mlp.down_proj.biases": "0.safetensors",
|
| 410 |
+
"layers.16.input_layernorm.weight": "0.safetensors",
|
| 411 |
+
"layers.16.self_attn.q_proj.weight": "0.safetensors",
|
| 412 |
+
"layers.16.self_attn.q_proj.scales": "0.safetensors",
|
| 413 |
+
"layers.16.self_attn.q_proj.biases": "0.safetensors",
|
| 414 |
+
"layers.16.self_attn.k_proj.weight": "0.safetensors",
|
| 415 |
+
"layers.16.self_attn.k_proj.scales": "0.safetensors",
|
| 416 |
+
"layers.16.self_attn.k_proj.biases": "0.safetensors",
|
| 417 |
+
"layers.16.self_attn.v_proj.weight": "0.safetensors",
|
| 418 |
+
"layers.16.self_attn.v_proj.scales": "0.safetensors",
|
| 419 |
+
"layers.16.self_attn.v_proj.biases": "0.safetensors",
|
| 420 |
+
"layers.16.self_attn.o_proj.weight": "0.safetensors",
|
| 421 |
+
"layers.16.self_attn.o_proj.scales": "0.safetensors",
|
| 422 |
+
"layers.16.self_attn.o_proj.biases": "0.safetensors",
|
| 423 |
+
"layers.16.self_attn.q_norm.weight": "0.safetensors",
|
| 424 |
+
"layers.16.self_attn.k_norm.weight": "0.safetensors",
|
| 425 |
+
"layers.16.post_attention_layernorm.weight": "0.safetensors",
|
| 426 |
+
"layers.16.mlp.gate_proj.weight": "0.safetensors",
|
| 427 |
+
"layers.16.mlp.gate_proj.scales": "0.safetensors",
|
| 428 |
+
"layers.16.mlp.gate_proj.biases": "0.safetensors",
|
| 429 |
+
"layers.16.mlp.up_proj.weight": "1.safetensors",
|
| 430 |
+
"layers.16.mlp.up_proj.scales": "1.safetensors",
|
| 431 |
+
"layers.16.mlp.up_proj.biases": "1.safetensors",
|
| 432 |
+
"layers.16.mlp.down_proj.weight": "1.safetensors",
|
| 433 |
+
"layers.16.mlp.down_proj.scales": "1.safetensors",
|
| 434 |
+
"layers.16.mlp.down_proj.biases": "1.safetensors",
|
| 435 |
+
"layers.17.input_layernorm.weight": "1.safetensors",
|
| 436 |
+
"layers.17.self_attn.q_proj.weight": "1.safetensors",
|
| 437 |
+
"layers.17.self_attn.q_proj.scales": "1.safetensors",
|
| 438 |
+
"layers.17.self_attn.q_proj.biases": "1.safetensors",
|
| 439 |
+
"layers.17.self_attn.k_proj.weight": "1.safetensors",
|
| 440 |
+
"layers.17.self_attn.k_proj.scales": "1.safetensors",
|
| 441 |
+
"layers.17.self_attn.k_proj.biases": "1.safetensors",
|
| 442 |
+
"layers.17.self_attn.v_proj.weight": "1.safetensors",
|
| 443 |
+
"layers.17.self_attn.v_proj.scales": "1.safetensors",
|
| 444 |
+
"layers.17.self_attn.v_proj.biases": "1.safetensors",
|
| 445 |
+
"layers.17.self_attn.o_proj.weight": "1.safetensors",
|
| 446 |
+
"layers.17.self_attn.o_proj.scales": "1.safetensors",
|
| 447 |
+
"layers.17.self_attn.o_proj.biases": "1.safetensors",
|
| 448 |
+
"layers.17.self_attn.q_norm.weight": "1.safetensors",
|
| 449 |
+
"layers.17.self_attn.k_norm.weight": "1.safetensors",
|
| 450 |
+
"layers.17.post_attention_layernorm.weight": "1.safetensors",
|
| 451 |
+
"layers.17.mlp.gate_proj.weight": "1.safetensors",
|
| 452 |
+
"layers.17.mlp.gate_proj.scales": "1.safetensors",
|
| 453 |
+
"layers.17.mlp.gate_proj.biases": "1.safetensors",
|
| 454 |
+
"layers.17.mlp.up_proj.weight": "1.safetensors",
|
| 455 |
+
"layers.17.mlp.up_proj.scales": "1.safetensors",
|
| 456 |
+
"layers.17.mlp.up_proj.biases": "1.safetensors",
|
| 457 |
+
"layers.17.mlp.down_proj.weight": "1.safetensors",
|
| 458 |
+
"layers.17.mlp.down_proj.scales": "1.safetensors",
|
| 459 |
+
"layers.17.mlp.down_proj.biases": "1.safetensors",
|
| 460 |
+
"layers.18.input_layernorm.weight": "1.safetensors",
|
| 461 |
+
"layers.18.self_attn.q_proj.weight": "1.safetensors",
|
| 462 |
+
"layers.18.self_attn.q_proj.scales": "1.safetensors",
|
| 463 |
+
"layers.18.self_attn.q_proj.biases": "1.safetensors",
|
| 464 |
+
"layers.18.self_attn.k_proj.weight": "1.safetensors",
|
| 465 |
+
"layers.18.self_attn.k_proj.scales": "1.safetensors",
|
| 466 |
+
"layers.18.self_attn.k_proj.biases": "1.safetensors",
|
| 467 |
+
"layers.18.self_attn.v_proj.weight": "1.safetensors",
|
| 468 |
+
"layers.18.self_attn.v_proj.scales": "1.safetensors",
|
| 469 |
+
"layers.18.self_attn.v_proj.biases": "1.safetensors",
|
| 470 |
+
"layers.18.self_attn.o_proj.weight": "1.safetensors",
|
| 471 |
+
"layers.18.self_attn.o_proj.scales": "1.safetensors",
|
| 472 |
+
"layers.18.self_attn.o_proj.biases": "1.safetensors",
|
| 473 |
+
"layers.18.self_attn.q_norm.weight": "1.safetensors",
|
| 474 |
+
"layers.18.self_attn.k_norm.weight": "1.safetensors",
|
| 475 |
+
"layers.18.post_attention_layernorm.weight": "1.safetensors",
|
| 476 |
+
"layers.18.mlp.gate_proj.weight": "1.safetensors",
|
| 477 |
+
"layers.18.mlp.gate_proj.scales": "1.safetensors",
|
| 478 |
+
"layers.18.mlp.gate_proj.biases": "1.safetensors",
|
| 479 |
+
"layers.18.mlp.up_proj.weight": "1.safetensors",
|
| 480 |
+
"layers.18.mlp.up_proj.scales": "1.safetensors",
|
| 481 |
+
"layers.18.mlp.up_proj.biases": "1.safetensors",
|
| 482 |
+
"layers.18.mlp.down_proj.weight": "1.safetensors",
|
| 483 |
+
"layers.18.mlp.down_proj.scales": "1.safetensors",
|
| 484 |
+
"layers.18.mlp.down_proj.biases": "1.safetensors",
|
| 485 |
+
"layers.19.input_layernorm.weight": "1.safetensors",
|
| 486 |
+
"layers.19.self_attn.q_proj.weight": "1.safetensors",
|
| 487 |
+
"layers.19.self_attn.q_proj.scales": "1.safetensors",
|
| 488 |
+
"layers.19.self_attn.q_proj.biases": "1.safetensors",
|
| 489 |
+
"layers.19.self_attn.k_proj.weight": "1.safetensors",
|
| 490 |
+
"layers.19.self_attn.k_proj.scales": "1.safetensors",
|
| 491 |
+
"layers.19.self_attn.k_proj.biases": "1.safetensors",
|
| 492 |
+
"layers.19.self_attn.v_proj.weight": "1.safetensors",
|
| 493 |
+
"layers.19.self_attn.v_proj.scales": "1.safetensors",
|
| 494 |
+
"layers.19.self_attn.v_proj.biases": "1.safetensors",
|
| 495 |
+
"layers.19.self_attn.o_proj.weight": "1.safetensors",
|
| 496 |
+
"layers.19.self_attn.o_proj.scales": "1.safetensors",
|
| 497 |
+
"layers.19.self_attn.o_proj.biases": "1.safetensors",
|
| 498 |
+
"layers.19.self_attn.q_norm.weight": "1.safetensors",
|
| 499 |
+
"layers.19.self_attn.k_norm.weight": "1.safetensors",
|
| 500 |
+
"layers.19.post_attention_layernorm.weight": "1.safetensors",
|
| 501 |
+
"layers.19.mlp.gate_proj.weight": "1.safetensors",
|
| 502 |
+
"layers.19.mlp.gate_proj.scales": "1.safetensors",
|
| 503 |
+
"layers.19.mlp.gate_proj.biases": "1.safetensors",
|
| 504 |
+
"layers.19.mlp.up_proj.weight": "1.safetensors",
|
| 505 |
+
"layers.19.mlp.up_proj.scales": "1.safetensors",
|
| 506 |
+
"layers.19.mlp.up_proj.biases": "1.safetensors",
|
| 507 |
+
"layers.19.mlp.down_proj.weight": "1.safetensors",
|
| 508 |
+
"layers.19.mlp.down_proj.scales": "1.safetensors",
|
| 509 |
+
"layers.19.mlp.down_proj.biases": "1.safetensors",
|
| 510 |
+
"layers.20.input_layernorm.weight": "1.safetensors",
|
| 511 |
+
"layers.20.self_attn.q_proj.weight": "1.safetensors",
|
| 512 |
+
"layers.20.self_attn.q_proj.scales": "1.safetensors",
|
| 513 |
+
"layers.20.self_attn.q_proj.biases": "1.safetensors",
|
| 514 |
+
"layers.20.self_attn.k_proj.weight": "1.safetensors",
|
| 515 |
+
"layers.20.self_attn.k_proj.scales": "1.safetensors",
|
| 516 |
+
"layers.20.self_attn.k_proj.biases": "1.safetensors",
|
| 517 |
+
"layers.20.self_attn.v_proj.weight": "1.safetensors",
|
| 518 |
+
"layers.20.self_attn.v_proj.scales": "1.safetensors",
|
| 519 |
+
"layers.20.self_attn.v_proj.biases": "1.safetensors",
|
| 520 |
+
"layers.20.self_attn.o_proj.weight": "1.safetensors",
|
| 521 |
+
"layers.20.self_attn.o_proj.scales": "1.safetensors",
|
| 522 |
+
"layers.20.self_attn.o_proj.biases": "1.safetensors",
|
| 523 |
+
"layers.20.self_attn.q_norm.weight": "1.safetensors",
|
| 524 |
+
"layers.20.self_attn.k_norm.weight": "1.safetensors",
|
| 525 |
+
"layers.20.post_attention_layernorm.weight": "1.safetensors",
|
| 526 |
+
"layers.20.mlp.gate_proj.weight": "1.safetensors",
|
| 527 |
+
"layers.20.mlp.gate_proj.scales": "1.safetensors",
|
| 528 |
+
"layers.20.mlp.gate_proj.biases": "1.safetensors",
|
| 529 |
+
"layers.20.mlp.up_proj.weight": "1.safetensors",
|
| 530 |
+
"layers.20.mlp.up_proj.scales": "1.safetensors",
|
| 531 |
+
"layers.20.mlp.up_proj.biases": "1.safetensors",
|
| 532 |
+
"layers.20.mlp.down_proj.weight": "1.safetensors",
|
| 533 |
+
"layers.20.mlp.down_proj.scales": "1.safetensors",
|
| 534 |
+
"layers.20.mlp.down_proj.biases": "1.safetensors",
|
| 535 |
+
"layers.21.input_layernorm.weight": "1.safetensors",
|
| 536 |
+
"layers.21.self_attn.q_proj.weight": "1.safetensors",
|
| 537 |
+
"layers.21.self_attn.q_proj.scales": "1.safetensors",
|
| 538 |
+
"layers.21.self_attn.q_proj.biases": "1.safetensors",
|
| 539 |
+
"layers.21.self_attn.k_proj.weight": "1.safetensors",
|
| 540 |
+
"layers.21.self_attn.k_proj.scales": "1.safetensors",
|
| 541 |
+
"layers.21.self_attn.k_proj.biases": "1.safetensors",
|
| 542 |
+
"layers.21.self_attn.v_proj.weight": "1.safetensors",
|
| 543 |
+
"layers.21.self_attn.v_proj.scales": "1.safetensors",
|
| 544 |
+
"layers.21.self_attn.v_proj.biases": "1.safetensors",
|
| 545 |
+
"layers.21.self_attn.o_proj.weight": "1.safetensors",
|
| 546 |
+
"layers.21.self_attn.o_proj.scales": "1.safetensors",
|
| 547 |
+
"layers.21.self_attn.o_proj.biases": "1.safetensors",
|
| 548 |
+
"layers.21.self_attn.q_norm.weight": "1.safetensors",
|
| 549 |
+
"layers.21.self_attn.k_norm.weight": "1.safetensors",
|
| 550 |
+
"layers.21.post_attention_layernorm.weight": "1.safetensors",
|
| 551 |
+
"layers.21.mlp.gate_proj.weight": "1.safetensors",
|
| 552 |
+
"layers.21.mlp.gate_proj.scales": "1.safetensors",
|
| 553 |
+
"layers.21.mlp.gate_proj.biases": "1.safetensors",
|
| 554 |
+
"layers.21.mlp.up_proj.weight": "1.safetensors",
|
| 555 |
+
"layers.21.mlp.up_proj.scales": "1.safetensors",
|
| 556 |
+
"layers.21.mlp.up_proj.biases": "1.safetensors",
|
| 557 |
+
"layers.21.mlp.down_proj.weight": "1.safetensors",
|
| 558 |
+
"layers.21.mlp.down_proj.scales": "1.safetensors",
|
| 559 |
+
"layers.21.mlp.down_proj.biases": "1.safetensors",
|
| 560 |
+
"layers.22.input_layernorm.weight": "1.safetensors",
|
| 561 |
+
"layers.22.self_attn.q_proj.weight": "1.safetensors",
|
| 562 |
+
"layers.22.self_attn.q_proj.scales": "1.safetensors",
|
| 563 |
+
"layers.22.self_attn.q_proj.biases": "1.safetensors",
|
| 564 |
+
"layers.22.self_attn.k_proj.weight": "1.safetensors",
|
| 565 |
+
"layers.22.self_attn.k_proj.scales": "1.safetensors",
|
| 566 |
+
"layers.22.self_attn.k_proj.biases": "1.safetensors",
|
| 567 |
+
"layers.22.self_attn.v_proj.weight": "1.safetensors",
|
| 568 |
+
"layers.22.self_attn.v_proj.scales": "1.safetensors",
|
| 569 |
+
"layers.22.self_attn.v_proj.biases": "1.safetensors",
|
| 570 |
+
"layers.22.self_attn.o_proj.weight": "1.safetensors",
|
| 571 |
+
"layers.22.self_attn.o_proj.scales": "1.safetensors",
|
| 572 |
+
"layers.22.self_attn.o_proj.biases": "1.safetensors",
|
| 573 |
+
"layers.22.self_attn.q_norm.weight": "1.safetensors",
|
| 574 |
+
"layers.22.self_attn.k_norm.weight": "1.safetensors",
|
| 575 |
+
"layers.22.post_attention_layernorm.weight": "1.safetensors",
|
| 576 |
+
"layers.22.mlp.gate_proj.weight": "1.safetensors",
|
| 577 |
+
"layers.22.mlp.gate_proj.scales": "1.safetensors",
|
| 578 |
+
"layers.22.mlp.gate_proj.biases": "1.safetensors",
|
| 579 |
+
"layers.22.mlp.up_proj.weight": "1.safetensors",
|
| 580 |
+
"layers.22.mlp.up_proj.scales": "1.safetensors",
|
| 581 |
+
"layers.22.mlp.up_proj.biases": "1.safetensors",
|
| 582 |
+
"layers.22.mlp.down_proj.weight": "1.safetensors",
|
| 583 |
+
"layers.22.mlp.down_proj.scales": "1.safetensors",
|
| 584 |
+
"layers.22.mlp.down_proj.biases": "1.safetensors",
|
| 585 |
+
"layers.23.input_layernorm.weight": "1.safetensors",
|
| 586 |
+
"layers.23.self_attn.q_proj.weight": "1.safetensors",
|
| 587 |
+
"layers.23.self_attn.q_proj.scales": "1.safetensors",
|
| 588 |
+
"layers.23.self_attn.q_proj.biases": "1.safetensors",
|
| 589 |
+
"layers.23.self_attn.k_proj.weight": "1.safetensors",
|
| 590 |
+
"layers.23.self_attn.k_proj.scales": "1.safetensors",
|
| 591 |
+
"layers.23.self_attn.k_proj.biases": "1.safetensors",
|
| 592 |
+
"layers.23.self_attn.v_proj.weight": "1.safetensors",
|
| 593 |
+
"layers.23.self_attn.v_proj.scales": "1.safetensors",
|
| 594 |
+
"layers.23.self_attn.v_proj.biases": "1.safetensors",
|
| 595 |
+
"layers.23.self_attn.o_proj.weight": "1.safetensors",
|
| 596 |
+
"layers.23.self_attn.o_proj.scales": "1.safetensors",
|
| 597 |
+
"layers.23.self_attn.o_proj.biases": "1.safetensors",
|
| 598 |
+
"layers.23.self_attn.q_norm.weight": "1.safetensors",
|
| 599 |
+
"layers.23.self_attn.k_norm.weight": "1.safetensors",
|
| 600 |
+
"layers.23.post_attention_layernorm.weight": "1.safetensors",
|
| 601 |
+
"layers.23.mlp.gate_proj.weight": "1.safetensors",
|
| 602 |
+
"layers.23.mlp.gate_proj.scales": "1.safetensors",
|
| 603 |
+
"layers.23.mlp.gate_proj.biases": "1.safetensors",
|
| 604 |
+
"layers.23.mlp.up_proj.weight": "1.safetensors",
|
| 605 |
+
"layers.23.mlp.up_proj.scales": "1.safetensors",
|
| 606 |
+
"layers.23.mlp.up_proj.biases": "1.safetensors",
|
| 607 |
+
"layers.23.mlp.down_proj.weight": "1.safetensors",
|
| 608 |
+
"layers.23.mlp.down_proj.scales": "1.safetensors",
|
| 609 |
+
"layers.23.mlp.down_proj.biases": "1.safetensors",
|
| 610 |
+
"layers.24.input_layernorm.weight": "1.safetensors",
|
| 611 |
+
"layers.24.self_attn.q_proj.weight": "1.safetensors",
|
| 612 |
+
"layers.24.self_attn.q_proj.scales": "1.safetensors",
|
| 613 |
+
"layers.24.self_attn.q_proj.biases": "1.safetensors",
|
| 614 |
+
"layers.24.self_attn.k_proj.weight": "1.safetensors",
|
| 615 |
+
"layers.24.self_attn.k_proj.scales": "1.safetensors",
|
| 616 |
+
"layers.24.self_attn.k_proj.biases": "1.safetensors",
|
| 617 |
+
"layers.24.self_attn.v_proj.weight": "1.safetensors",
|
| 618 |
+
"layers.24.self_attn.v_proj.scales": "1.safetensors",
|
| 619 |
+
"layers.24.self_attn.v_proj.biases": "1.safetensors",
|
| 620 |
+
"layers.24.self_attn.o_proj.weight": "1.safetensors",
|
| 621 |
+
"layers.24.self_attn.o_proj.scales": "1.safetensors",
|
| 622 |
+
"layers.24.self_attn.o_proj.biases": "1.safetensors",
|
| 623 |
+
"layers.24.self_attn.q_norm.weight": "1.safetensors",
|
| 624 |
+
"layers.24.self_attn.k_norm.weight": "1.safetensors",
|
| 625 |
+
"layers.24.post_attention_layernorm.weight": "1.safetensors",
|
| 626 |
+
"layers.24.mlp.gate_proj.weight": "1.safetensors",
|
| 627 |
+
"layers.24.mlp.gate_proj.scales": "1.safetensors",
|
| 628 |
+
"layers.24.mlp.gate_proj.biases": "1.safetensors",
|
| 629 |
+
"layers.24.mlp.up_proj.weight": "1.safetensors",
|
| 630 |
+
"layers.24.mlp.up_proj.scales": "1.safetensors",
|
| 631 |
+
"layers.24.mlp.up_proj.biases": "1.safetensors",
|
| 632 |
+
"layers.24.mlp.down_proj.weight": "1.safetensors",
|
| 633 |
+
"layers.24.mlp.down_proj.scales": "1.safetensors",
|
| 634 |
+
"layers.24.mlp.down_proj.biases": "1.safetensors",
|
| 635 |
+
"layers.25.input_layernorm.weight": "1.safetensors",
|
| 636 |
+
"layers.25.self_attn.q_proj.weight": "1.safetensors",
|
| 637 |
+
"layers.25.self_attn.q_proj.scales": "1.safetensors",
|
| 638 |
+
"layers.25.self_attn.q_proj.biases": "1.safetensors",
|
| 639 |
+
"layers.25.self_attn.k_proj.weight": "1.safetensors",
|
| 640 |
+
"layers.25.self_attn.k_proj.scales": "1.safetensors",
|
| 641 |
+
"layers.25.self_attn.k_proj.biases": "1.safetensors",
|
| 642 |
+
"layers.25.self_attn.v_proj.weight": "1.safetensors",
|
| 643 |
+
"layers.25.self_attn.v_proj.scales": "1.safetensors",
|
| 644 |
+
"layers.25.self_attn.v_proj.biases": "1.safetensors",
|
| 645 |
+
"layers.25.self_attn.o_proj.weight": "1.safetensors",
|
| 646 |
+
"layers.25.self_attn.o_proj.scales": "1.safetensors",
|
| 647 |
+
"layers.25.self_attn.o_proj.biases": "1.safetensors",
|
| 648 |
+
"layers.25.self_attn.q_norm.weight": "1.safetensors",
|
| 649 |
+
"layers.25.self_attn.k_norm.weight": "1.safetensors",
|
| 650 |
+
"layers.25.post_attention_layernorm.weight": "1.safetensors",
|
| 651 |
+
"layers.25.mlp.gate_proj.weight": "1.safetensors",
|
| 652 |
+
"layers.25.mlp.gate_proj.scales": "1.safetensors",
|
| 653 |
+
"layers.25.mlp.gate_proj.biases": "1.safetensors",
|
| 654 |
+
"layers.25.mlp.up_proj.weight": "1.safetensors",
|
| 655 |
+
"layers.25.mlp.up_proj.scales": "1.safetensors",
|
| 656 |
+
"layers.25.mlp.up_proj.biases": "1.safetensors",
|
| 657 |
+
"layers.25.mlp.down_proj.weight": "1.safetensors",
|
| 658 |
+
"layers.25.mlp.down_proj.scales": "1.safetensors",
|
| 659 |
+
"layers.25.mlp.down_proj.biases": "1.safetensors",
|
| 660 |
+
"layers.26.input_layernorm.weight": "1.safetensors",
|
| 661 |
+
"layers.26.self_attn.q_proj.weight": "1.safetensors",
|
| 662 |
+
"layers.26.self_attn.q_proj.scales": "1.safetensors",
|
| 663 |
+
"layers.26.self_attn.q_proj.biases": "1.safetensors",
|
| 664 |
+
"layers.26.self_attn.k_proj.weight": "1.safetensors",
|
| 665 |
+
"layers.26.self_attn.k_proj.scales": "1.safetensors",
|
| 666 |
+
"layers.26.self_attn.k_proj.biases": "1.safetensors",
|
| 667 |
+
"layers.26.self_attn.v_proj.weight": "1.safetensors",
|
| 668 |
+
"layers.26.self_attn.v_proj.scales": "1.safetensors",
|
| 669 |
+
"layers.26.self_attn.v_proj.biases": "1.safetensors",
|
| 670 |
+
"layers.26.self_attn.o_proj.weight": "1.safetensors",
|
| 671 |
+
"layers.26.self_attn.o_proj.scales": "1.safetensors",
|
| 672 |
+
"layers.26.self_attn.o_proj.biases": "1.safetensors",
|
| 673 |
+
"layers.26.self_attn.q_norm.weight": "1.safetensors",
|
| 674 |
+
"layers.26.self_attn.k_norm.weight": "1.safetensors",
|
| 675 |
+
"layers.26.post_attention_layernorm.weight": "1.safetensors",
|
| 676 |
+
"layers.26.mlp.gate_proj.weight": "1.safetensors",
|
| 677 |
+
"layers.26.mlp.gate_proj.scales": "1.safetensors",
|
| 678 |
+
"layers.26.mlp.gate_proj.biases": "1.safetensors",
|
| 679 |
+
"layers.26.mlp.up_proj.weight": "1.safetensors",
|
| 680 |
+
"layers.26.mlp.up_proj.scales": "1.safetensors",
|
| 681 |
+
"layers.26.mlp.up_proj.biases": "1.safetensors",
|
| 682 |
+
"layers.26.mlp.down_proj.weight": "1.safetensors",
|
| 683 |
+
"layers.26.mlp.down_proj.scales": "1.safetensors",
|
| 684 |
+
"layers.26.mlp.down_proj.biases": "1.safetensors",
|
| 685 |
+
"layers.27.input_layernorm.weight": "1.safetensors",
|
| 686 |
+
"layers.27.self_attn.q_proj.weight": "1.safetensors",
|
| 687 |
+
"layers.27.self_attn.q_proj.scales": "1.safetensors",
|
| 688 |
+
"layers.27.self_attn.q_proj.biases": "1.safetensors",
|
| 689 |
+
"layers.27.self_attn.k_proj.weight": "1.safetensors",
|
| 690 |
+
"layers.27.self_attn.k_proj.scales": "1.safetensors",
|
| 691 |
+
"layers.27.self_attn.k_proj.biases": "1.safetensors",
|
| 692 |
+
"layers.27.self_attn.v_proj.weight": "1.safetensors",
|
| 693 |
+
"layers.27.self_attn.v_proj.scales": "1.safetensors",
|
| 694 |
+
"layers.27.self_attn.v_proj.biases": "1.safetensors",
|
| 695 |
+
"layers.27.self_attn.o_proj.weight": "1.safetensors",
|
| 696 |
+
"layers.27.self_attn.o_proj.scales": "1.safetensors",
|
| 697 |
+
"layers.27.self_attn.o_proj.biases": "1.safetensors",
|
| 698 |
+
"layers.27.self_attn.q_norm.weight": "1.safetensors",
|
| 699 |
+
"layers.27.self_attn.k_norm.weight": "1.safetensors",
|
| 700 |
+
"layers.27.post_attention_layernorm.weight": "1.safetensors",
|
| 701 |
+
"layers.27.mlp.gate_proj.weight": "1.safetensors",
|
| 702 |
+
"layers.27.mlp.gate_proj.scales": "1.safetensors",
|
| 703 |
+
"layers.27.mlp.gate_proj.biases": "1.safetensors",
|
| 704 |
+
"layers.27.mlp.up_proj.weight": "1.safetensors",
|
| 705 |
+
"layers.27.mlp.up_proj.scales": "1.safetensors",
|
| 706 |
+
"layers.27.mlp.up_proj.biases": "1.safetensors",
|
| 707 |
+
"layers.27.mlp.down_proj.weight": "1.safetensors",
|
| 708 |
+
"layers.27.mlp.down_proj.scales": "1.safetensors",
|
| 709 |
+
"layers.27.mlp.down_proj.biases": "1.safetensors",
|
| 710 |
+
"layers.28.input_layernorm.weight": "1.safetensors",
|
| 711 |
+
"layers.28.self_attn.q_proj.weight": "1.safetensors",
|
| 712 |
+
"layers.28.self_attn.q_proj.scales": "1.safetensors",
|
| 713 |
+
"layers.28.self_attn.q_proj.biases": "1.safetensors",
|
| 714 |
+
"layers.28.self_attn.k_proj.weight": "1.safetensors",
|
| 715 |
+
"layers.28.self_attn.k_proj.scales": "1.safetensors",
|
| 716 |
+
"layers.28.self_attn.k_proj.biases": "1.safetensors",
|
| 717 |
+
"layers.28.self_attn.v_proj.weight": "1.safetensors",
|
| 718 |
+
"layers.28.self_attn.v_proj.scales": "1.safetensors",
|
| 719 |
+
"layers.28.self_attn.v_proj.biases": "1.safetensors",
|
| 720 |
+
"layers.28.self_attn.o_proj.weight": "1.safetensors",
|
| 721 |
+
"layers.28.self_attn.o_proj.scales": "1.safetensors",
|
| 722 |
+
"layers.28.self_attn.o_proj.biases": "1.safetensors",
|
| 723 |
+
"layers.28.self_attn.q_norm.weight": "1.safetensors",
|
| 724 |
+
"layers.28.self_attn.k_norm.weight": "1.safetensors",
|
| 725 |
+
"layers.28.post_attention_layernorm.weight": "1.safetensors",
|
| 726 |
+
"layers.28.mlp.gate_proj.weight": "1.safetensors",
|
| 727 |
+
"layers.28.mlp.gate_proj.scales": "1.safetensors",
|
| 728 |
+
"layers.28.mlp.gate_proj.biases": "1.safetensors",
|
| 729 |
+
"layers.28.mlp.up_proj.weight": "1.safetensors",
|
| 730 |
+
"layers.28.mlp.up_proj.scales": "1.safetensors",
|
| 731 |
+
"layers.28.mlp.up_proj.biases": "1.safetensors",
|
| 732 |
+
"layers.28.mlp.down_proj.weight": "1.safetensors",
|
| 733 |
+
"layers.28.mlp.down_proj.scales": "1.safetensors",
|
| 734 |
+
"layers.28.mlp.down_proj.biases": "1.safetensors",
|
| 735 |
+
"layers.29.input_layernorm.weight": "1.safetensors",
|
| 736 |
+
"layers.29.self_attn.q_proj.weight": "1.safetensors",
|
| 737 |
+
"layers.29.self_attn.q_proj.scales": "1.safetensors",
|
| 738 |
+
"layers.29.self_attn.q_proj.biases": "1.safetensors",
|
| 739 |
+
"layers.29.self_attn.k_proj.weight": "1.safetensors",
|
| 740 |
+
"layers.29.self_attn.k_proj.scales": "1.safetensors",
|
| 741 |
+
"layers.29.self_attn.k_proj.biases": "1.safetensors",
|
| 742 |
+
"layers.29.self_attn.v_proj.weight": "1.safetensors",
|
| 743 |
+
"layers.29.self_attn.v_proj.scales": "1.safetensors",
|
| 744 |
+
"layers.29.self_attn.v_proj.biases": "1.safetensors",
|
| 745 |
+
"layers.29.self_attn.o_proj.weight": "1.safetensors",
|
| 746 |
+
"layers.29.self_attn.o_proj.scales": "1.safetensors",
|
| 747 |
+
"layers.29.self_attn.o_proj.biases": "1.safetensors",
|
| 748 |
+
"layers.29.self_attn.q_norm.weight": "1.safetensors",
|
| 749 |
+
"layers.29.self_attn.k_norm.weight": "1.safetensors",
|
| 750 |
+
"layers.29.post_attention_layernorm.weight": "1.safetensors",
|
| 751 |
+
"layers.29.mlp.gate_proj.weight": "1.safetensors",
|
| 752 |
+
"layers.29.mlp.gate_proj.scales": "1.safetensors",
|
| 753 |
+
"layers.29.mlp.gate_proj.biases": "1.safetensors",
|
| 754 |
+
"layers.29.mlp.up_proj.weight": "1.safetensors",
|
| 755 |
+
"layers.29.mlp.up_proj.scales": "1.safetensors",
|
| 756 |
+
"layers.29.mlp.up_proj.biases": "1.safetensors",
|
| 757 |
+
"layers.29.mlp.down_proj.weight": "1.safetensors",
|
| 758 |
+
"layers.29.mlp.down_proj.scales": "1.safetensors",
|
| 759 |
+
"layers.29.mlp.down_proj.biases": "1.safetensors",
|
| 760 |
+
"layers.30.input_layernorm.weight": "1.safetensors",
|
| 761 |
+
"layers.30.self_attn.q_proj.weight": "1.safetensors",
|
| 762 |
+
"layers.30.self_attn.q_proj.scales": "1.safetensors",
|
| 763 |
+
"layers.30.self_attn.q_proj.biases": "1.safetensors",
|
| 764 |
+
"layers.30.self_attn.k_proj.weight": "1.safetensors",
|
| 765 |
+
"layers.30.self_attn.k_proj.scales": "1.safetensors",
|
| 766 |
+
"layers.30.self_attn.k_proj.biases": "1.safetensors",
|
| 767 |
+
"layers.30.self_attn.v_proj.weight": "1.safetensors",
|
| 768 |
+
"layers.30.self_attn.v_proj.scales": "1.safetensors",
|
| 769 |
+
"layers.30.self_attn.v_proj.biases": "1.safetensors",
|
| 770 |
+
"layers.30.self_attn.o_proj.weight": "1.safetensors",
|
| 771 |
+
"layers.30.self_attn.o_proj.scales": "1.safetensors",
|
| 772 |
+
"layers.30.self_attn.o_proj.biases": "1.safetensors",
|
| 773 |
+
"layers.30.self_attn.q_norm.weight": "1.safetensors",
|
| 774 |
+
"layers.30.self_attn.k_norm.weight": "1.safetensors",
|
| 775 |
+
"layers.30.post_attention_layernorm.weight": "1.safetensors",
|
| 776 |
+
"layers.30.mlp.gate_proj.weight": "1.safetensors",
|
| 777 |
+
"layers.30.mlp.gate_proj.scales": "1.safetensors",
|
| 778 |
+
"layers.30.mlp.gate_proj.biases": "1.safetensors",
|
| 779 |
+
"layers.30.mlp.up_proj.weight": "1.safetensors",
|
| 780 |
+
"layers.30.mlp.up_proj.scales": "1.safetensors",
|
| 781 |
+
"layers.30.mlp.up_proj.biases": "1.safetensors",
|
| 782 |
+
"layers.30.mlp.down_proj.weight": "1.safetensors",
|
| 783 |
+
"layers.30.mlp.down_proj.scales": "1.safetensors",
|
| 784 |
+
"layers.30.mlp.down_proj.biases": "1.safetensors",
|
| 785 |
+
"layers.31.input_layernorm.weight": "1.safetensors",
|
| 786 |
+
"layers.31.self_attn.q_proj.weight": "1.safetensors",
|
| 787 |
+
"layers.31.self_attn.q_proj.scales": "1.safetensors",
|
| 788 |
+
"layers.31.self_attn.q_proj.biases": "1.safetensors",
|
| 789 |
+
"layers.31.self_attn.k_proj.weight": "1.safetensors",
|
| 790 |
+
"layers.31.self_attn.k_proj.scales": "1.safetensors",
|
| 791 |
+
"layers.31.self_attn.k_proj.biases": "1.safetensors",
|
| 792 |
+
"layers.31.self_attn.v_proj.weight": "1.safetensors",
|
| 793 |
+
"layers.31.self_attn.v_proj.scales": "1.safetensors",
|
| 794 |
+
"layers.31.self_attn.v_proj.biases": "1.safetensors",
|
| 795 |
+
"layers.31.self_attn.o_proj.weight": "1.safetensors",
|
| 796 |
+
"layers.31.self_attn.o_proj.scales": "1.safetensors",
|
| 797 |
+
"layers.31.self_attn.o_proj.biases": "1.safetensors",
|
| 798 |
+
"layers.31.self_attn.q_norm.weight": "1.safetensors",
|
| 799 |
+
"layers.31.self_attn.k_norm.weight": "1.safetensors",
|
| 800 |
+
"layers.31.post_attention_layernorm.weight": "1.safetensors",
|
| 801 |
+
"layers.31.mlp.gate_proj.weight": "1.safetensors",
|
| 802 |
+
"layers.31.mlp.gate_proj.scales": "1.safetensors",
|
| 803 |
+
"layers.31.mlp.gate_proj.biases": "1.safetensors",
|
| 804 |
+
"layers.31.mlp.up_proj.weight": "1.safetensors",
|
| 805 |
+
"layers.31.mlp.up_proj.scales": "1.safetensors",
|
| 806 |
+
"layers.31.mlp.up_proj.biases": "1.safetensors",
|
| 807 |
+
"layers.31.mlp.down_proj.weight": "1.safetensors",
|
| 808 |
+
"layers.31.mlp.down_proj.scales": "1.safetensors",
|
| 809 |
+
"layers.31.mlp.down_proj.biases": "1.safetensors",
|
| 810 |
+
"layers.32.input_layernorm.weight": "1.safetensors",
|
| 811 |
+
"layers.32.self_attn.q_proj.weight": "1.safetensors",
|
| 812 |
+
"layers.32.self_attn.q_proj.scales": "1.safetensors",
|
| 813 |
+
"layers.32.self_attn.q_proj.biases": "1.safetensors",
|
| 814 |
+
"layers.32.self_attn.k_proj.weight": "1.safetensors",
|
| 815 |
+
"layers.32.self_attn.k_proj.scales": "1.safetensors",
|
| 816 |
+
"layers.32.self_attn.k_proj.biases": "1.safetensors",
|
| 817 |
+
"layers.32.self_attn.v_proj.weight": "1.safetensors",
|
| 818 |
+
"layers.32.self_attn.v_proj.scales": "1.safetensors",
|
| 819 |
+
"layers.32.self_attn.v_proj.biases": "1.safetensors",
|
| 820 |
+
"layers.32.self_attn.o_proj.weight": "1.safetensors",
|
| 821 |
+
"layers.32.self_attn.o_proj.scales": "1.safetensors",
|
| 822 |
+
"layers.32.self_attn.o_proj.biases": "1.safetensors",
|
| 823 |
+
"layers.32.self_attn.q_norm.weight": "1.safetensors",
|
| 824 |
+
"layers.32.self_attn.k_norm.weight": "1.safetensors",
|
| 825 |
+
"layers.32.post_attention_layernorm.weight": "1.safetensors",
|
| 826 |
+
"layers.32.mlp.gate_proj.weight": "1.safetensors",
|
| 827 |
+
"layers.32.mlp.gate_proj.scales": "1.safetensors",
|
| 828 |
+
"layers.32.mlp.gate_proj.biases": "1.safetensors",
|
| 829 |
+
"layers.32.mlp.up_proj.weight": "1.safetensors",
|
| 830 |
+
"layers.32.mlp.up_proj.scales": "1.safetensors",
|
| 831 |
+
"layers.32.mlp.up_proj.biases": "1.safetensors",
|
| 832 |
+
"layers.32.mlp.down_proj.weight": "1.safetensors",
|
| 833 |
+
"layers.32.mlp.down_proj.scales": "1.safetensors",
|
| 834 |
+
"layers.32.mlp.down_proj.biases": "1.safetensors",
|
| 835 |
+
"layers.33.input_layernorm.weight": "1.safetensors",
|
| 836 |
+
"layers.33.self_attn.q_proj.weight": "1.safetensors",
|
| 837 |
+
"layers.33.self_attn.q_proj.scales": "1.safetensors",
|
| 838 |
+
"layers.33.self_attn.q_proj.biases": "1.safetensors",
|
| 839 |
+
"layers.33.self_attn.k_proj.weight": "1.safetensors",
|
| 840 |
+
"layers.33.self_attn.k_proj.scales": "1.safetensors",
|
| 841 |
+
"layers.33.self_attn.k_proj.biases": "1.safetensors",
|
| 842 |
+
"layers.33.self_attn.v_proj.weight": "1.safetensors",
|
| 843 |
+
"layers.33.self_attn.v_proj.scales": "1.safetensors",
|
| 844 |
+
"layers.33.self_attn.v_proj.biases": "1.safetensors",
|
| 845 |
+
"layers.33.self_attn.o_proj.weight": "1.safetensors",
|
| 846 |
+
"layers.33.self_attn.o_proj.scales": "1.safetensors",
|
| 847 |
+
"layers.33.self_attn.o_proj.biases": "1.safetensors",
|
| 848 |
+
"layers.33.self_attn.q_norm.weight": "1.safetensors",
|
| 849 |
+
"layers.33.self_attn.k_norm.weight": "1.safetensors",
|
| 850 |
+
"layers.33.post_attention_layernorm.weight": "1.safetensors",
|
| 851 |
+
"layers.33.mlp.gate_proj.weight": "1.safetensors",
|
| 852 |
+
"layers.33.mlp.gate_proj.scales": "1.safetensors",
|
| 853 |
+
"layers.33.mlp.gate_proj.biases": "1.safetensors",
|
| 854 |
+
"layers.33.mlp.up_proj.weight": "1.safetensors",
|
| 855 |
+
"layers.33.mlp.up_proj.scales": "1.safetensors",
|
| 856 |
+
"layers.33.mlp.up_proj.biases": "1.safetensors",
|
| 857 |
+
"layers.33.mlp.down_proj.weight": "1.safetensors",
|
| 858 |
+
"layers.33.mlp.down_proj.scales": "1.safetensors",
|
| 859 |
+
"layers.33.mlp.down_proj.biases": "1.safetensors",
|
| 860 |
+
"layers.34.input_layernorm.weight": "1.safetensors",
|
| 861 |
+
"layers.34.self_attn.q_proj.weight": "1.safetensors",
|
| 862 |
+
"layers.34.self_attn.q_proj.scales": "1.safetensors",
|
| 863 |
+
"layers.34.self_attn.q_proj.biases": "1.safetensors",
|
| 864 |
+
"layers.34.self_attn.k_proj.weight": "1.safetensors",
|
| 865 |
+
"layers.34.self_attn.k_proj.scales": "1.safetensors",
|
| 866 |
+
"layers.34.self_attn.k_proj.biases": "1.safetensors",
|
| 867 |
+
"layers.34.self_attn.v_proj.weight": "1.safetensors",
|
| 868 |
+
"layers.34.self_attn.v_proj.scales": "1.safetensors",
|
| 869 |
+
"layers.34.self_attn.v_proj.biases": "1.safetensors",
|
| 870 |
+
"layers.34.self_attn.o_proj.weight": "1.safetensors",
|
| 871 |
+
"layers.34.self_attn.o_proj.scales": "1.safetensors",
|
| 872 |
+
"layers.34.self_attn.o_proj.biases": "1.safetensors",
|
| 873 |
+
"layers.34.self_attn.q_norm.weight": "1.safetensors",
|
| 874 |
+
"layers.34.self_attn.k_norm.weight": "1.safetensors",
|
| 875 |
+
"layers.34.post_attention_layernorm.weight": "1.safetensors",
|
| 876 |
+
"layers.34.mlp.gate_proj.weight": "1.safetensors",
|
| 877 |
+
"layers.34.mlp.gate_proj.scales": "1.safetensors",
|
| 878 |
+
"layers.34.mlp.gate_proj.biases": "1.safetensors",
|
| 879 |
+
"layers.34.mlp.up_proj.weight": "1.safetensors",
|
| 880 |
+
"layers.34.mlp.up_proj.scales": "1.safetensors",
|
| 881 |
+
"layers.34.mlp.up_proj.biases": "1.safetensors",
|
| 882 |
+
"layers.34.mlp.down_proj.weight": "1.safetensors",
|
| 883 |
+
"layers.34.mlp.down_proj.scales": "1.safetensors",
|
| 884 |
+
"layers.34.mlp.down_proj.biases": "1.safetensors",
|
| 885 |
+
"layers.35.input_layernorm.weight": "1.safetensors",
|
| 886 |
+
"layers.35.self_attn.q_proj.weight": "1.safetensors",
|
| 887 |
+
"layers.35.self_attn.q_proj.scales": "1.safetensors",
|
| 888 |
+
"layers.35.self_attn.q_proj.biases": "1.safetensors",
|
| 889 |
+
"layers.35.self_attn.k_proj.weight": "1.safetensors",
|
| 890 |
+
"layers.35.self_attn.k_proj.scales": "1.safetensors",
|
| 891 |
+
"layers.35.self_attn.k_proj.biases": "1.safetensors",
|
| 892 |
+
"layers.35.self_attn.v_proj.weight": "1.safetensors",
|
| 893 |
+
"layers.35.self_attn.v_proj.scales": "1.safetensors",
|
| 894 |
+
"layers.35.self_attn.v_proj.biases": "1.safetensors",
|
| 895 |
+
"layers.35.self_attn.o_proj.weight": "1.safetensors",
|
| 896 |
+
"layers.35.self_attn.o_proj.scales": "1.safetensors",
|
| 897 |
+
"layers.35.self_attn.o_proj.biases": "1.safetensors",
|
| 898 |
+
"layers.35.self_attn.q_norm.weight": "1.safetensors",
|
| 899 |
+
"layers.35.self_attn.k_norm.weight": "1.safetensors",
|
| 900 |
+
"layers.35.post_attention_layernorm.weight": "1.safetensors",
|
| 901 |
+
"layers.35.mlp.gate_proj.weight": "1.safetensors",
|
| 902 |
+
"layers.35.mlp.gate_proj.scales": "1.safetensors",
|
| 903 |
+
"layers.35.mlp.gate_proj.biases": "1.safetensors",
|
| 904 |
+
"layers.35.mlp.up_proj.weight": "1.safetensors",
|
| 905 |
+
"layers.35.mlp.up_proj.scales": "1.safetensors",
|
| 906 |
+
"layers.35.mlp.up_proj.biases": "1.safetensors",
|
| 907 |
+
"layers.35.mlp.down_proj.weight": "1.safetensors",
|
| 908 |
+
"layers.35.mlp.down_proj.scales": "1.safetensors",
|
| 909 |
+
"layers.35.mlp.down_proj.biases": "1.safetensors",
|
| 910 |
+
"norm.weight": "1.safetensors",
|
| 911 |
+
"rotary_emb.inv_freq": "1.safetensors"
|
| 912 |
}
|
| 913 |
}
|
transformer/0.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 sha256:759c871e9cb5ce5bd6f3a2f048b8b82a04c9a2f887036614215c3dd8004d527e
|
| 3 |
+
size 2144765248
|
transformer/1.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 sha256:1d925f6587dd10b29e082e3c4f5d00709eb7c657f13e56270092df3615746726
|
| 3 |
+
size 2145684605
|
transformer/2.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 sha256:4257a7ea491232afa35c35117509abdffac3cfaf4e94e0c801fcfb2f40032716
|
| 3 |
+
size 931181187
|
transformer/model.safetensors.index.json
CHANGED
|
@@ -1,678 +1,891 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"quantization_level": "4",
|
| 4 |
-
"mflux_version": "0.
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"input_proj.weight": "0.safetensors",
|
| 8 |
-
"input_proj.
|
|
|
|
| 9 |
"input_proj.bias": "0.safetensors",
|
| 10 |
"llm_cond_norm.weight": "0.safetensors",
|
| 11 |
"llm_cond_proj.weight": "0.safetensors",
|
| 12 |
-
"llm_cond_proj.
|
|
|
|
| 13 |
"llm_cond_proj.bias": "0.safetensors",
|
| 14 |
"t_embedding.mlp_in.weight": "0.safetensors",
|
| 15 |
-
"t_embedding.mlp_in.
|
|
|
|
| 16 |
"t_embedding.mlp_in.bias": "0.safetensors",
|
| 17 |
"t_embedding.mlp_out.weight": "0.safetensors",
|
| 18 |
-
"t_embedding.mlp_out.
|
|
|
|
| 19 |
"t_embedding.mlp_out.bias": "0.safetensors",
|
| 20 |
"adaln_proj.weight": "0.safetensors",
|
| 21 |
-
"adaln_proj.
|
|
|
|
| 22 |
"adaln_proj.bias": "0.safetensors",
|
| 23 |
"embed_image_indicator.weight": "0.safetensors",
|
|
|
|
|
|
|
| 24 |
"rotary_emb.inv_freq": "0.safetensors",
|
| 25 |
"layers.0.attention.qkv.weight": "0.safetensors",
|
| 26 |
-
"layers.0.attention.qkv.
|
|
|
|
| 27 |
"layers.0.attention.norm_q.weight": "0.safetensors",
|
| 28 |
"layers.0.attention.norm_k.weight": "0.safetensors",
|
| 29 |
"layers.0.attention.o.weight": "0.safetensors",
|
| 30 |
-
"layers.0.attention.o.
|
|
|
|
| 31 |
"layers.0.feed_forward.w1.weight": "0.safetensors",
|
| 32 |
-
"layers.0.feed_forward.w1.
|
|
|
|
| 33 |
"layers.0.feed_forward.w2.weight": "0.safetensors",
|
| 34 |
-
"layers.0.feed_forward.w2.
|
|
|
|
| 35 |
"layers.0.feed_forward.w3.weight": "0.safetensors",
|
| 36 |
-
"layers.0.feed_forward.w3.
|
|
|
|
| 37 |
"layers.0.attention_norm1.weight": "0.safetensors",
|
| 38 |
"layers.0.ffn_norm1.weight": "0.safetensors",
|
| 39 |
"layers.0.attention_norm2.weight": "0.safetensors",
|
| 40 |
"layers.0.ffn_norm2.weight": "0.safetensors",
|
| 41 |
"layers.0.adaln_modulation.weight": "0.safetensors",
|
| 42 |
-
"layers.0.adaln_modulation.
|
|
|
|
| 43 |
"layers.0.adaln_modulation.bias": "0.safetensors",
|
| 44 |
"layers.1.attention.qkv.weight": "0.safetensors",
|
| 45 |
-
"layers.1.attention.qkv.
|
|
|
|
| 46 |
"layers.1.attention.norm_q.weight": "0.safetensors",
|
| 47 |
"layers.1.attention.norm_k.weight": "0.safetensors",
|
| 48 |
"layers.1.attention.o.weight": "0.safetensors",
|
| 49 |
-
"layers.1.attention.o.
|
|
|
|
| 50 |
"layers.1.feed_forward.w1.weight": "0.safetensors",
|
| 51 |
-
"layers.1.feed_forward.w1.
|
|
|
|
| 52 |
"layers.1.feed_forward.w2.weight": "0.safetensors",
|
| 53 |
-
"layers.1.feed_forward.w2.
|
|
|
|
| 54 |
"layers.1.feed_forward.w3.weight": "0.safetensors",
|
| 55 |
-
"layers.1.feed_forward.w3.
|
|
|
|
| 56 |
"layers.1.attention_norm1.weight": "0.safetensors",
|
| 57 |
"layers.1.ffn_norm1.weight": "0.safetensors",
|
| 58 |
"layers.1.attention_norm2.weight": "0.safetensors",
|
| 59 |
"layers.1.ffn_norm2.weight": "0.safetensors",
|
| 60 |
"layers.1.adaln_modulation.weight": "0.safetensors",
|
| 61 |
-
"layers.1.adaln_modulation.
|
|
|
|
| 62 |
"layers.1.adaln_modulation.bias": "0.safetensors",
|
| 63 |
"layers.2.attention.qkv.weight": "0.safetensors",
|
| 64 |
-
"layers.2.attention.qkv.
|
|
|
|
| 65 |
"layers.2.attention.norm_q.weight": "0.safetensors",
|
| 66 |
"layers.2.attention.norm_k.weight": "0.safetensors",
|
| 67 |
"layers.2.attention.o.weight": "0.safetensors",
|
| 68 |
-
"layers.2.attention.o.
|
|
|
|
| 69 |
"layers.2.feed_forward.w1.weight": "0.safetensors",
|
| 70 |
-
"layers.2.feed_forward.w1.
|
|
|
|
| 71 |
"layers.2.feed_forward.w2.weight": "0.safetensors",
|
| 72 |
-
"layers.2.feed_forward.w2.
|
|
|
|
| 73 |
"layers.2.feed_forward.w3.weight": "0.safetensors",
|
| 74 |
-
"layers.2.feed_forward.w3.
|
|
|
|
| 75 |
"layers.2.attention_norm1.weight": "0.safetensors",
|
| 76 |
"layers.2.ffn_norm1.weight": "0.safetensors",
|
| 77 |
"layers.2.attention_norm2.weight": "0.safetensors",
|
| 78 |
"layers.2.ffn_norm2.weight": "0.safetensors",
|
| 79 |
"layers.2.adaln_modulation.weight": "0.safetensors",
|
| 80 |
-
"layers.2.adaln_modulation.
|
|
|
|
| 81 |
"layers.2.adaln_modulation.bias": "0.safetensors",
|
| 82 |
"layers.3.attention.qkv.weight": "0.safetensors",
|
| 83 |
-
"layers.3.attention.qkv.
|
|
|
|
| 84 |
"layers.3.attention.norm_q.weight": "0.safetensors",
|
| 85 |
"layers.3.attention.norm_k.weight": "0.safetensors",
|
| 86 |
"layers.3.attention.o.weight": "0.safetensors",
|
| 87 |
-
"layers.3.attention.o.
|
|
|
|
| 88 |
"layers.3.feed_forward.w1.weight": "0.safetensors",
|
| 89 |
-
"layers.3.feed_forward.w1.
|
|
|
|
| 90 |
"layers.3.feed_forward.w2.weight": "0.safetensors",
|
| 91 |
-
"layers.3.feed_forward.w2.
|
|
|
|
| 92 |
"layers.3.feed_forward.w3.weight": "0.safetensors",
|
| 93 |
-
"layers.3.feed_forward.w3.
|
|
|
|
| 94 |
"layers.3.attention_norm1.weight": "0.safetensors",
|
| 95 |
"layers.3.ffn_norm1.weight": "0.safetensors",
|
| 96 |
"layers.3.attention_norm2.weight": "0.safetensors",
|
| 97 |
"layers.3.ffn_norm2.weight": "0.safetensors",
|
| 98 |
"layers.3.adaln_modulation.weight": "0.safetensors",
|
| 99 |
-
"layers.3.adaln_modulation.
|
|
|
|
| 100 |
"layers.3.adaln_modulation.bias": "0.safetensors",
|
| 101 |
"layers.4.attention.qkv.weight": "0.safetensors",
|
| 102 |
-
"layers.4.attention.qkv.
|
|
|
|
| 103 |
"layers.4.attention.norm_q.weight": "0.safetensors",
|
| 104 |
"layers.4.attention.norm_k.weight": "0.safetensors",
|
| 105 |
"layers.4.attention.o.weight": "0.safetensors",
|
| 106 |
-
"layers.4.attention.o.
|
|
|
|
| 107 |
"layers.4.feed_forward.w1.weight": "0.safetensors",
|
| 108 |
-
"layers.4.feed_forward.w1.
|
|
|
|
| 109 |
"layers.4.feed_forward.w2.weight": "0.safetensors",
|
| 110 |
-
"layers.4.feed_forward.w2.
|
|
|
|
| 111 |
"layers.4.feed_forward.w3.weight": "0.safetensors",
|
| 112 |
-
"layers.4.feed_forward.w3.
|
|
|
|
| 113 |
"layers.4.attention_norm1.weight": "0.safetensors",
|
| 114 |
"layers.4.ffn_norm1.weight": "0.safetensors",
|
| 115 |
"layers.4.attention_norm2.weight": "0.safetensors",
|
| 116 |
"layers.4.ffn_norm2.weight": "0.safetensors",
|
| 117 |
"layers.4.adaln_modulation.weight": "0.safetensors",
|
| 118 |
-
"layers.4.adaln_modulation.
|
|
|
|
| 119 |
"layers.4.adaln_modulation.bias": "0.safetensors",
|
| 120 |
"layers.5.attention.qkv.weight": "0.safetensors",
|
| 121 |
-
"layers.5.attention.qkv.
|
|
|
|
| 122 |
"layers.5.attention.norm_q.weight": "0.safetensors",
|
| 123 |
"layers.5.attention.norm_k.weight": "0.safetensors",
|
| 124 |
"layers.5.attention.o.weight": "0.safetensors",
|
| 125 |
-
"layers.5.attention.o.
|
|
|
|
| 126 |
"layers.5.feed_forward.w1.weight": "0.safetensors",
|
| 127 |
-
"layers.5.feed_forward.w1.
|
|
|
|
| 128 |
"layers.5.feed_forward.w2.weight": "0.safetensors",
|
| 129 |
-
"layers.5.feed_forward.w2.
|
|
|
|
| 130 |
"layers.5.feed_forward.w3.weight": "0.safetensors",
|
| 131 |
-
"layers.5.feed_forward.w3.
|
|
|
|
| 132 |
"layers.5.attention_norm1.weight": "0.safetensors",
|
| 133 |
"layers.5.ffn_norm1.weight": "0.safetensors",
|
| 134 |
"layers.5.attention_norm2.weight": "0.safetensors",
|
| 135 |
"layers.5.ffn_norm2.weight": "0.safetensors",
|
| 136 |
"layers.5.adaln_modulation.weight": "0.safetensors",
|
| 137 |
-
"layers.5.adaln_modulation.
|
|
|
|
| 138 |
"layers.5.adaln_modulation.bias": "0.safetensors",
|
| 139 |
"layers.6.attention.qkv.weight": "0.safetensors",
|
| 140 |
-
"layers.6.attention.qkv.
|
|
|
|
| 141 |
"layers.6.attention.norm_q.weight": "0.safetensors",
|
| 142 |
"layers.6.attention.norm_k.weight": "0.safetensors",
|
| 143 |
"layers.6.attention.o.weight": "0.safetensors",
|
| 144 |
-
"layers.6.attention.o.
|
|
|
|
| 145 |
"layers.6.feed_forward.w1.weight": "0.safetensors",
|
| 146 |
-
"layers.6.feed_forward.w1.
|
|
|
|
| 147 |
"layers.6.feed_forward.w2.weight": "0.safetensors",
|
| 148 |
-
"layers.6.feed_forward.w2.
|
|
|
|
| 149 |
"layers.6.feed_forward.w3.weight": "0.safetensors",
|
| 150 |
-
"layers.6.feed_forward.w3.
|
|
|
|
| 151 |
"layers.6.attention_norm1.weight": "0.safetensors",
|
| 152 |
"layers.6.ffn_norm1.weight": "0.safetensors",
|
| 153 |
"layers.6.attention_norm2.weight": "0.safetensors",
|
| 154 |
"layers.6.ffn_norm2.weight": "0.safetensors",
|
| 155 |
"layers.6.adaln_modulation.weight": "0.safetensors",
|
| 156 |
-
"layers.6.adaln_modulation.
|
|
|
|
| 157 |
"layers.6.adaln_modulation.bias": "0.safetensors",
|
| 158 |
-
"layers.7.attention.qkv.weight": "
|
| 159 |
-
"layers.7.attention.qkv.
|
| 160 |
-
"layers.7.attention.
|
| 161 |
-
"layers.7.attention.
|
| 162 |
-
"layers.7.attention.
|
| 163 |
-
"layers.7.attention.o.
|
| 164 |
-
"layers.7.
|
| 165 |
-
"layers.7.
|
| 166 |
-
"layers.7.feed_forward.
|
| 167 |
-
"layers.7.feed_forward.
|
| 168 |
-
"layers.7.feed_forward.
|
| 169 |
-
"layers.7.feed_forward.
|
| 170 |
-
"layers.7.
|
| 171 |
-
"layers.7.
|
| 172 |
-
"layers.7.
|
| 173 |
-
"layers.7.
|
| 174 |
-
"layers.7.
|
| 175 |
-
"layers.7.
|
| 176 |
-
"layers.7.
|
| 177 |
-
"layers.
|
| 178 |
-
"layers.
|
| 179 |
-
"layers.
|
| 180 |
-
"layers.
|
| 181 |
-
"layers.
|
| 182 |
-
"layers.
|
| 183 |
-
"layers.8.
|
| 184 |
-
"layers.8.
|
| 185 |
-
"layers.8.
|
| 186 |
-
"layers.8.
|
| 187 |
-
"layers.8.
|
| 188 |
-
"layers.8.
|
| 189 |
-
"layers.8.
|
| 190 |
-
"layers.8.
|
| 191 |
-
"layers.8.
|
| 192 |
-
"layers.8.
|
| 193 |
-
"layers.8.
|
| 194 |
-
"layers.8.
|
| 195 |
-
"layers.8.
|
| 196 |
-
"layers.
|
| 197 |
-
"layers.
|
| 198 |
-
"layers.
|
| 199 |
-
"layers.
|
| 200 |
-
"layers.
|
| 201 |
-
"layers.
|
| 202 |
-
"layers.
|
| 203 |
-
"layers.
|
| 204 |
-
"layers.
|
| 205 |
-
"layers.
|
| 206 |
-
"layers.
|
| 207 |
-
"layers.
|
| 208 |
-
"layers.9.
|
| 209 |
-
"layers.9.
|
| 210 |
-
"layers.9.
|
| 211 |
-
"layers.9.
|
| 212 |
-
"layers.9.
|
| 213 |
-
"layers.9.
|
| 214 |
-
"layers.9.
|
| 215 |
-
"layers.
|
| 216 |
-
"layers.
|
| 217 |
-
"layers.
|
| 218 |
-
"layers.
|
| 219 |
-
"layers.
|
| 220 |
-
"layers.
|
| 221 |
-
"layers.
|
| 222 |
-
"layers.
|
| 223 |
-
"layers.
|
| 224 |
-
"layers.
|
| 225 |
-
"layers.
|
| 226 |
-
"layers.
|
| 227 |
-
"layers.
|
| 228 |
-
"layers.
|
| 229 |
-
"layers.
|
| 230 |
-
"layers.
|
| 231 |
-
"layers.
|
| 232 |
-
"layers.
|
| 233 |
-
"layers.10.
|
| 234 |
-
"layers.
|
| 235 |
-
"layers.
|
| 236 |
-
"layers.
|
| 237 |
-
"layers.
|
| 238 |
-
"layers.
|
| 239 |
-
"layers.
|
| 240 |
-
"layers.
|
| 241 |
-
"layers.
|
| 242 |
-
"layers.
|
| 243 |
-
"layers.
|
| 244 |
-
"layers.
|
| 245 |
-
"layers.
|
| 246 |
-
"layers.
|
| 247 |
-
"layers.
|
| 248 |
-
"layers.
|
| 249 |
-
"layers.
|
| 250 |
-
"layers.
|
| 251 |
-
"layers.
|
| 252 |
-
"layers.
|
| 253 |
-
"layers.
|
| 254 |
-
"layers.
|
| 255 |
-
"layers.
|
| 256 |
-
"layers.
|
| 257 |
-
"layers.
|
| 258 |
-
"layers.
|
| 259 |
-
"layers.
|
| 260 |
-
"layers.
|
| 261 |
-
"layers.
|
| 262 |
-
"layers.
|
| 263 |
-
"layers.
|
| 264 |
-
"layers.
|
| 265 |
-
"layers.
|
| 266 |
-
"layers.
|
| 267 |
-
"layers.
|
| 268 |
-
"layers.
|
| 269 |
-
"layers.
|
| 270 |
-
"layers.
|
| 271 |
-
"layers.
|
| 272 |
-
"layers.
|
| 273 |
-
"layers.
|
| 274 |
-
"layers.
|
| 275 |
-
"layers.
|
| 276 |
-
"layers.
|
| 277 |
-
"layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 278 |
"layers.13.feed_forward.w1.weight": "1.safetensors",
|
| 279 |
-
"layers.13.feed_forward.w1.
|
|
|
|
| 280 |
"layers.13.feed_forward.w2.weight": "1.safetensors",
|
| 281 |
-
"layers.13.feed_forward.w2.
|
|
|
|
| 282 |
"layers.13.feed_forward.w3.weight": "1.safetensors",
|
| 283 |
-
"layers.13.feed_forward.w3.
|
|
|
|
| 284 |
"layers.13.attention_norm1.weight": "1.safetensors",
|
| 285 |
"layers.13.ffn_norm1.weight": "1.safetensors",
|
| 286 |
"layers.13.attention_norm2.weight": "1.safetensors",
|
| 287 |
"layers.13.ffn_norm2.weight": "1.safetensors",
|
| 288 |
"layers.13.adaln_modulation.weight": "1.safetensors",
|
| 289 |
-
"layers.13.adaln_modulation.
|
|
|
|
| 290 |
"layers.13.adaln_modulation.bias": "1.safetensors",
|
| 291 |
"layers.14.attention.qkv.weight": "1.safetensors",
|
| 292 |
-
"layers.14.attention.qkv.
|
|
|
|
| 293 |
"layers.14.attention.norm_q.weight": "1.safetensors",
|
| 294 |
"layers.14.attention.norm_k.weight": "1.safetensors",
|
| 295 |
"layers.14.attention.o.weight": "1.safetensors",
|
| 296 |
-
"layers.14.attention.o.
|
|
|
|
| 297 |
"layers.14.feed_forward.w1.weight": "1.safetensors",
|
| 298 |
-
"layers.14.feed_forward.w1.
|
|
|
|
| 299 |
"layers.14.feed_forward.w2.weight": "1.safetensors",
|
| 300 |
-
"layers.14.feed_forward.w2.
|
|
|
|
| 301 |
"layers.14.feed_forward.w3.weight": "1.safetensors",
|
| 302 |
-
"layers.14.feed_forward.w3.
|
|
|
|
| 303 |
"layers.14.attention_norm1.weight": "1.safetensors",
|
| 304 |
"layers.14.ffn_norm1.weight": "1.safetensors",
|
| 305 |
"layers.14.attention_norm2.weight": "1.safetensors",
|
| 306 |
"layers.14.ffn_norm2.weight": "1.safetensors",
|
| 307 |
"layers.14.adaln_modulation.weight": "1.safetensors",
|
| 308 |
-
"layers.14.adaln_modulation.
|
|
|
|
| 309 |
"layers.14.adaln_modulation.bias": "1.safetensors",
|
| 310 |
-
"layers.15.attention.qkv.weight": "
|
| 311 |
-
"layers.15.attention.qkv.
|
| 312 |
-
"layers.15.attention.
|
| 313 |
-
"layers.15.attention.
|
| 314 |
-
"layers.15.attention.
|
| 315 |
-
"layers.15.attention.o.
|
| 316 |
-
"layers.15.
|
| 317 |
-
"layers.15.
|
| 318 |
-
"layers.15.feed_forward.
|
| 319 |
-
"layers.15.feed_forward.
|
| 320 |
-
"layers.15.feed_forward.
|
| 321 |
-
"layers.15.feed_forward.
|
| 322 |
-
"layers.15.
|
| 323 |
-
"layers.15.
|
| 324 |
-
"layers.15.
|
| 325 |
-
"layers.15.
|
| 326 |
-
"layers.15.
|
| 327 |
-
"layers.15.
|
| 328 |
-
"layers.15.
|
| 329 |
-
"layers.
|
| 330 |
-
"layers.
|
| 331 |
-
"layers.
|
| 332 |
-
"layers.
|
| 333 |
-
"layers.
|
| 334 |
-
"layers.
|
| 335 |
-
"layers.16.
|
| 336 |
-
"layers.16.
|
| 337 |
-
"layers.16.
|
| 338 |
-
"layers.16.
|
| 339 |
-
"layers.16.
|
| 340 |
-
"layers.16.
|
| 341 |
-
"layers.16.
|
| 342 |
-
"layers.16.
|
| 343 |
-
"layers.16.
|
| 344 |
-
"layers.16.
|
| 345 |
-
"layers.16.
|
| 346 |
-
"layers.16.
|
| 347 |
-
"layers.16.
|
| 348 |
-
"layers.
|
| 349 |
-
"layers.
|
| 350 |
-
"layers.
|
| 351 |
-
"layers.
|
| 352 |
-
"layers.
|
| 353 |
-
"layers.
|
| 354 |
-
"layers.
|
| 355 |
-
"layers.
|
| 356 |
-
"layers.
|
| 357 |
-
"layers.
|
| 358 |
-
"layers.
|
| 359 |
-
"layers.
|
| 360 |
-
"layers.17.
|
| 361 |
-
"layers.17.
|
| 362 |
-
"layers.17.
|
| 363 |
-
"layers.17.
|
| 364 |
-
"layers.17.
|
| 365 |
-
"layers.17.
|
| 366 |
-
"layers.17.
|
| 367 |
-
"layers.
|
| 368 |
-
"layers.
|
| 369 |
-
"layers.
|
| 370 |
-
"layers.
|
| 371 |
-
"layers.
|
| 372 |
-
"layers.
|
| 373 |
-
"layers.
|
| 374 |
-
"layers.
|
| 375 |
-
"layers.
|
| 376 |
-
"layers.
|
| 377 |
-
"layers.
|
| 378 |
-
"layers.
|
| 379 |
-
"layers.
|
| 380 |
-
"layers.
|
| 381 |
-
"layers.
|
| 382 |
-
"layers.
|
| 383 |
-
"layers.
|
| 384 |
-
"layers.
|
| 385 |
-
"layers.18.
|
| 386 |
-
"layers.
|
| 387 |
-
"layers.
|
| 388 |
-
"layers.
|
| 389 |
-
"layers.
|
| 390 |
-
"layers.
|
| 391 |
-
"layers.
|
| 392 |
-
"layers.
|
| 393 |
-
"layers.
|
| 394 |
-
"layers.
|
| 395 |
-
"layers.
|
| 396 |
-
"layers.
|
| 397 |
-
"layers.
|
| 398 |
-
"layers.
|
| 399 |
-
"layers.
|
| 400 |
-
"layers.
|
| 401 |
-
"layers.
|
| 402 |
-
"layers.
|
| 403 |
-
"layers.
|
| 404 |
-
"layers.
|
| 405 |
-
"layers.
|
| 406 |
-
"layers.
|
| 407 |
-
"layers.
|
| 408 |
-
"layers.
|
| 409 |
-
"layers.
|
| 410 |
-
"layers.
|
| 411 |
-
"layers.
|
| 412 |
-
"layers.
|
| 413 |
-
"layers.
|
| 414 |
-
"layers.
|
| 415 |
-
"layers.
|
| 416 |
-
"layers.
|
| 417 |
-
"layers.
|
| 418 |
-
"layers.
|
| 419 |
-
"layers.
|
| 420 |
-
"layers.
|
| 421 |
-
"layers.
|
| 422 |
-
"layers.
|
| 423 |
-
"layers.
|
| 424 |
-
"layers.
|
| 425 |
-
"layers.
|
| 426 |
-
"layers.
|
| 427 |
-
"layers.
|
| 428 |
-
"layers.
|
| 429 |
-
"layers.
|
| 430 |
-
"layers.
|
| 431 |
-
"layers.
|
| 432 |
-
"layers.
|
| 433 |
-
"layers.
|
| 434 |
-
"layers.
|
| 435 |
-
"layers.
|
| 436 |
-
"layers.
|
| 437 |
-
"layers.
|
| 438 |
-
"layers.
|
| 439 |
-
"layers.
|
| 440 |
-
"layers.
|
| 441 |
-
"layers.
|
| 442 |
-
"layers.
|
| 443 |
-
"layers.
|
| 444 |
-
"layers.
|
| 445 |
-
"layers.
|
| 446 |
-
"layers.
|
| 447 |
-
"layers.
|
| 448 |
-
"layers.
|
| 449 |
-
"layers.
|
| 450 |
-
"layers.
|
| 451 |
-
"layers.
|
| 452 |
-
"layers.
|
| 453 |
-
"layers.
|
| 454 |
-
"layers.
|
| 455 |
-
"layers.
|
| 456 |
-
"layers.
|
| 457 |
-
"layers.
|
| 458 |
-
"layers.
|
| 459 |
-
"layers.
|
| 460 |
-
"layers.
|
| 461 |
-
"layers.
|
| 462 |
-
"layers.
|
| 463 |
-
"layers.
|
| 464 |
-
"layers.
|
| 465 |
-
"layers.
|
| 466 |
-
"layers.
|
| 467 |
-
"layers.
|
| 468 |
-
"layers.
|
| 469 |
-
"layers.
|
| 470 |
-
"layers.
|
| 471 |
-
"layers.
|
| 472 |
-
"layers.
|
| 473 |
-
"layers.
|
| 474 |
-
"layers.
|
| 475 |
-
"layers.
|
| 476 |
-
"layers.
|
| 477 |
-
"layers.
|
| 478 |
-
"layers.
|
| 479 |
-
"layers.
|
| 480 |
-
"layers.
|
| 481 |
-
"layers.
|
| 482 |
-
"layers.
|
| 483 |
-
"layers.
|
| 484 |
-
"layers.
|
| 485 |
-
"layers.
|
| 486 |
-
"layers.
|
| 487 |
-
"layers.
|
| 488 |
-
"layers.
|
| 489 |
-
"layers.
|
| 490 |
-
"layers.
|
| 491 |
-
"layers.
|
| 492 |
-
"layers.
|
| 493 |
-
"layers.
|
| 494 |
-
"layers.
|
| 495 |
-
"layers.
|
| 496 |
-
"layers.
|
| 497 |
-
"layers.
|
| 498 |
-
"layers.
|
| 499 |
-
"layers.
|
| 500 |
-
"layers.
|
| 501 |
-
"layers.
|
| 502 |
-
"layers.
|
| 503 |
-
"layers.
|
| 504 |
-
"layers.
|
| 505 |
-
"layers.
|
| 506 |
-
"layers.
|
| 507 |
-
"layers.
|
| 508 |
-
"layers.
|
| 509 |
-
"layers.
|
| 510 |
-
"layers.
|
| 511 |
-
"layers.
|
| 512 |
-
"layers.
|
| 513 |
-
"layers.
|
| 514 |
-
"layers.
|
| 515 |
-
"layers.
|
| 516 |
-
"layers.
|
| 517 |
-
"layers.
|
| 518 |
-
"layers.
|
| 519 |
-
"layers.
|
| 520 |
-
"layers.
|
| 521 |
-
"layers.
|
| 522 |
-
"layers.
|
| 523 |
-
"layers.
|
| 524 |
-
"layers.
|
| 525 |
-
"layers.
|
| 526 |
-
"layers.
|
| 527 |
-
"layers.
|
| 528 |
-
"layers.
|
| 529 |
-
"layers.
|
| 530 |
-
"layers.
|
| 531 |
-
"layers.
|
| 532 |
-
"layers.
|
| 533 |
-
"layers.
|
| 534 |
-
"layers.
|
| 535 |
-
"layers.
|
| 536 |
-
"layers.
|
| 537 |
-
"layers.
|
| 538 |
-
"layers.
|
| 539 |
-
"layers.
|
| 540 |
-
"layers.
|
| 541 |
-
"layers.
|
| 542 |
-
"layers.
|
| 543 |
-
"layers.
|
| 544 |
-
"layers.
|
| 545 |
-
"layers.
|
| 546 |
-
"layers.
|
| 547 |
-
"layers.
|
| 548 |
-
"layers.
|
| 549 |
-
"layers.
|
| 550 |
-
"layers.
|
| 551 |
-
"layers.
|
| 552 |
-
"layers.
|
| 553 |
-
"layers.
|
| 554 |
-
"layers.
|
| 555 |
-
"layers.
|
| 556 |
-
"layers.
|
| 557 |
-
"layers.
|
| 558 |
-
"layers.
|
| 559 |
-
"layers.
|
| 560 |
-
"layers.
|
| 561 |
-
"layers.
|
| 562 |
-
"layers.
|
| 563 |
-
"layers.
|
| 564 |
-
"layers.
|
| 565 |
-
"layers.
|
| 566 |
-
"layers.
|
| 567 |
-
"layers.
|
| 568 |
-
"layers.
|
| 569 |
-
"layers.
|
| 570 |
-
"layers.
|
| 571 |
-
"layers.
|
| 572 |
-
"layers.
|
| 573 |
-
"layers.
|
| 574 |
-
"layers.
|
| 575 |
-
"layers.
|
| 576 |
-
"layers.
|
| 577 |
-
"layers.
|
| 578 |
-
"layers.
|
| 579 |
-
"layers.
|
| 580 |
-
"layers.
|
| 581 |
-
"layers.
|
| 582 |
-
"layers.
|
| 583 |
-
"layers.
|
| 584 |
-
"layers.
|
| 585 |
-
"layers.
|
| 586 |
-
"layers.
|
| 587 |
-
"layers.
|
| 588 |
-
"layers.
|
| 589 |
-
"layers.
|
| 590 |
-
"layers.
|
| 591 |
-
"layers.
|
| 592 |
-
"layers.
|
| 593 |
-
"layers.
|
| 594 |
-
"layers.
|
| 595 |
-
"layers.
|
| 596 |
-
"layers.
|
| 597 |
-
"layers.
|
| 598 |
-
"layers.
|
| 599 |
-
"layers.
|
| 600 |
-
"layers.
|
| 601 |
-
"layers.
|
| 602 |
-
"layers.
|
| 603 |
-
"layers.
|
| 604 |
-
"layers.
|
| 605 |
-
"layers.
|
| 606 |
-
"layers.
|
| 607 |
-
"layers.
|
| 608 |
-
"layers.
|
| 609 |
-
"layers.
|
| 610 |
-
"layers.
|
| 611 |
-
"layers.
|
| 612 |
-
"layers.
|
| 613 |
-
"layers.
|
| 614 |
-
"layers.
|
| 615 |
-
"layers.
|
| 616 |
-
"layers.
|
| 617 |
-
"layers.
|
| 618 |
-
"layers.
|
| 619 |
-
"layers.
|
| 620 |
-
"layers.
|
| 621 |
-
"layers.
|
| 622 |
-
"layers.
|
| 623 |
-
"layers.
|
| 624 |
-
"layers.
|
| 625 |
-
"layers.
|
| 626 |
-
"layers.
|
| 627 |
-
"layers.
|
| 628 |
-
"layers.
|
| 629 |
-
"layers.
|
| 630 |
-
"layers.
|
| 631 |
-
"layers.
|
| 632 |
-
"layers.
|
| 633 |
-
"layers.
|
| 634 |
-
"layers.
|
| 635 |
-
"layers.
|
| 636 |
-
"layers.
|
| 637 |
-
"layers.
|
| 638 |
-
"layers.
|
| 639 |
-
"layers.
|
| 640 |
-
"layers.
|
| 641 |
-
"layers.
|
| 642 |
-
"layers.
|
| 643 |
-
"layers.
|
| 644 |
-
"layers.
|
| 645 |
-
"layers.
|
| 646 |
-
"layers.
|
| 647 |
-
"layers.
|
| 648 |
-
"layers.
|
| 649 |
-
"layers.
|
| 650 |
-
"layers.
|
| 651 |
-
"layers.
|
| 652 |
-
"layers.
|
| 653 |
-
"layers.
|
| 654 |
-
"layers.
|
| 655 |
-
"layers.
|
| 656 |
-
"layers.
|
| 657 |
-
"layers.
|
| 658 |
-
"layers.
|
| 659 |
-
"layers.
|
| 660 |
-
"layers.
|
| 661 |
-
"layers.
|
| 662 |
-
"layers.
|
| 663 |
-
"layers.
|
| 664 |
-
"layers.
|
| 665 |
-
"layers.
|
| 666 |
-
"layers.
|
| 667 |
-
"layers.
|
| 668 |
-
"layers.
|
| 669 |
-
"layers.
|
| 670 |
-
"layers.
|
| 671 |
-
"
|
| 672 |
-
"
|
| 673 |
-
"
|
| 674 |
-
"
|
| 675 |
-
"
|
| 676 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 677 |
}
|
| 678 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"quantization_level": "4",
|
| 4 |
+
"mflux_version": "0.20.0"
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"input_proj.weight": "0.safetensors",
|
| 8 |
+
"input_proj.scales": "0.safetensors",
|
| 9 |
+
"input_proj.biases": "0.safetensors",
|
| 10 |
"input_proj.bias": "0.safetensors",
|
| 11 |
"llm_cond_norm.weight": "0.safetensors",
|
| 12 |
"llm_cond_proj.weight": "0.safetensors",
|
| 13 |
+
"llm_cond_proj.scales": "0.safetensors",
|
| 14 |
+
"llm_cond_proj.biases": "0.safetensors",
|
| 15 |
"llm_cond_proj.bias": "0.safetensors",
|
| 16 |
"t_embedding.mlp_in.weight": "0.safetensors",
|
| 17 |
+
"t_embedding.mlp_in.scales": "0.safetensors",
|
| 18 |
+
"t_embedding.mlp_in.biases": "0.safetensors",
|
| 19 |
"t_embedding.mlp_in.bias": "0.safetensors",
|
| 20 |
"t_embedding.mlp_out.weight": "0.safetensors",
|
| 21 |
+
"t_embedding.mlp_out.scales": "0.safetensors",
|
| 22 |
+
"t_embedding.mlp_out.biases": "0.safetensors",
|
| 23 |
"t_embedding.mlp_out.bias": "0.safetensors",
|
| 24 |
"adaln_proj.weight": "0.safetensors",
|
| 25 |
+
"adaln_proj.scales": "0.safetensors",
|
| 26 |
+
"adaln_proj.biases": "0.safetensors",
|
| 27 |
"adaln_proj.bias": "0.safetensors",
|
| 28 |
"embed_image_indicator.weight": "0.safetensors",
|
| 29 |
+
"embed_image_indicator.scales": "0.safetensors",
|
| 30 |
+
"embed_image_indicator.biases": "0.safetensors",
|
| 31 |
"rotary_emb.inv_freq": "0.safetensors",
|
| 32 |
"layers.0.attention.qkv.weight": "0.safetensors",
|
| 33 |
+
"layers.0.attention.qkv.scales": "0.safetensors",
|
| 34 |
+
"layers.0.attention.qkv.biases": "0.safetensors",
|
| 35 |
"layers.0.attention.norm_q.weight": "0.safetensors",
|
| 36 |
"layers.0.attention.norm_k.weight": "0.safetensors",
|
| 37 |
"layers.0.attention.o.weight": "0.safetensors",
|
| 38 |
+
"layers.0.attention.o.scales": "0.safetensors",
|
| 39 |
+
"layers.0.attention.o.biases": "0.safetensors",
|
| 40 |
"layers.0.feed_forward.w1.weight": "0.safetensors",
|
| 41 |
+
"layers.0.feed_forward.w1.scales": "0.safetensors",
|
| 42 |
+
"layers.0.feed_forward.w1.biases": "0.safetensors",
|
| 43 |
"layers.0.feed_forward.w2.weight": "0.safetensors",
|
| 44 |
+
"layers.0.feed_forward.w2.scales": "0.safetensors",
|
| 45 |
+
"layers.0.feed_forward.w2.biases": "0.safetensors",
|
| 46 |
"layers.0.feed_forward.w3.weight": "0.safetensors",
|
| 47 |
+
"layers.0.feed_forward.w3.scales": "0.safetensors",
|
| 48 |
+
"layers.0.feed_forward.w3.biases": "0.safetensors",
|
| 49 |
"layers.0.attention_norm1.weight": "0.safetensors",
|
| 50 |
"layers.0.ffn_norm1.weight": "0.safetensors",
|
| 51 |
"layers.0.attention_norm2.weight": "0.safetensors",
|
| 52 |
"layers.0.ffn_norm2.weight": "0.safetensors",
|
| 53 |
"layers.0.adaln_modulation.weight": "0.safetensors",
|
| 54 |
+
"layers.0.adaln_modulation.scales": "0.safetensors",
|
| 55 |
+
"layers.0.adaln_modulation.biases": "0.safetensors",
|
| 56 |
"layers.0.adaln_modulation.bias": "0.safetensors",
|
| 57 |
"layers.1.attention.qkv.weight": "0.safetensors",
|
| 58 |
+
"layers.1.attention.qkv.scales": "0.safetensors",
|
| 59 |
+
"layers.1.attention.qkv.biases": "0.safetensors",
|
| 60 |
"layers.1.attention.norm_q.weight": "0.safetensors",
|
| 61 |
"layers.1.attention.norm_k.weight": "0.safetensors",
|
| 62 |
"layers.1.attention.o.weight": "0.safetensors",
|
| 63 |
+
"layers.1.attention.o.scales": "0.safetensors",
|
| 64 |
+
"layers.1.attention.o.biases": "0.safetensors",
|
| 65 |
"layers.1.feed_forward.w1.weight": "0.safetensors",
|
| 66 |
+
"layers.1.feed_forward.w1.scales": "0.safetensors",
|
| 67 |
+
"layers.1.feed_forward.w1.biases": "0.safetensors",
|
| 68 |
"layers.1.feed_forward.w2.weight": "0.safetensors",
|
| 69 |
+
"layers.1.feed_forward.w2.scales": "0.safetensors",
|
| 70 |
+
"layers.1.feed_forward.w2.biases": "0.safetensors",
|
| 71 |
"layers.1.feed_forward.w3.weight": "0.safetensors",
|
| 72 |
+
"layers.1.feed_forward.w3.scales": "0.safetensors",
|
| 73 |
+
"layers.1.feed_forward.w3.biases": "0.safetensors",
|
| 74 |
"layers.1.attention_norm1.weight": "0.safetensors",
|
| 75 |
"layers.1.ffn_norm1.weight": "0.safetensors",
|
| 76 |
"layers.1.attention_norm2.weight": "0.safetensors",
|
| 77 |
"layers.1.ffn_norm2.weight": "0.safetensors",
|
| 78 |
"layers.1.adaln_modulation.weight": "0.safetensors",
|
| 79 |
+
"layers.1.adaln_modulation.scales": "0.safetensors",
|
| 80 |
+
"layers.1.adaln_modulation.biases": "0.safetensors",
|
| 81 |
"layers.1.adaln_modulation.bias": "0.safetensors",
|
| 82 |
"layers.2.attention.qkv.weight": "0.safetensors",
|
| 83 |
+
"layers.2.attention.qkv.scales": "0.safetensors",
|
| 84 |
+
"layers.2.attention.qkv.biases": "0.safetensors",
|
| 85 |
"layers.2.attention.norm_q.weight": "0.safetensors",
|
| 86 |
"layers.2.attention.norm_k.weight": "0.safetensors",
|
| 87 |
"layers.2.attention.o.weight": "0.safetensors",
|
| 88 |
+
"layers.2.attention.o.scales": "0.safetensors",
|
| 89 |
+
"layers.2.attention.o.biases": "0.safetensors",
|
| 90 |
"layers.2.feed_forward.w1.weight": "0.safetensors",
|
| 91 |
+
"layers.2.feed_forward.w1.scales": "0.safetensors",
|
| 92 |
+
"layers.2.feed_forward.w1.biases": "0.safetensors",
|
| 93 |
"layers.2.feed_forward.w2.weight": "0.safetensors",
|
| 94 |
+
"layers.2.feed_forward.w2.scales": "0.safetensors",
|
| 95 |
+
"layers.2.feed_forward.w2.biases": "0.safetensors",
|
| 96 |
"layers.2.feed_forward.w3.weight": "0.safetensors",
|
| 97 |
+
"layers.2.feed_forward.w3.scales": "0.safetensors",
|
| 98 |
+
"layers.2.feed_forward.w3.biases": "0.safetensors",
|
| 99 |
"layers.2.attention_norm1.weight": "0.safetensors",
|
| 100 |
"layers.2.ffn_norm1.weight": "0.safetensors",
|
| 101 |
"layers.2.attention_norm2.weight": "0.safetensors",
|
| 102 |
"layers.2.ffn_norm2.weight": "0.safetensors",
|
| 103 |
"layers.2.adaln_modulation.weight": "0.safetensors",
|
| 104 |
+
"layers.2.adaln_modulation.scales": "0.safetensors",
|
| 105 |
+
"layers.2.adaln_modulation.biases": "0.safetensors",
|
| 106 |
"layers.2.adaln_modulation.bias": "0.safetensors",
|
| 107 |
"layers.3.attention.qkv.weight": "0.safetensors",
|
| 108 |
+
"layers.3.attention.qkv.scales": "0.safetensors",
|
| 109 |
+
"layers.3.attention.qkv.biases": "0.safetensors",
|
| 110 |
"layers.3.attention.norm_q.weight": "0.safetensors",
|
| 111 |
"layers.3.attention.norm_k.weight": "0.safetensors",
|
| 112 |
"layers.3.attention.o.weight": "0.safetensors",
|
| 113 |
+
"layers.3.attention.o.scales": "0.safetensors",
|
| 114 |
+
"layers.3.attention.o.biases": "0.safetensors",
|
| 115 |
"layers.3.feed_forward.w1.weight": "0.safetensors",
|
| 116 |
+
"layers.3.feed_forward.w1.scales": "0.safetensors",
|
| 117 |
+
"layers.3.feed_forward.w1.biases": "0.safetensors",
|
| 118 |
"layers.3.feed_forward.w2.weight": "0.safetensors",
|
| 119 |
+
"layers.3.feed_forward.w2.scales": "0.safetensors",
|
| 120 |
+
"layers.3.feed_forward.w2.biases": "0.safetensors",
|
| 121 |
"layers.3.feed_forward.w3.weight": "0.safetensors",
|
| 122 |
+
"layers.3.feed_forward.w3.scales": "0.safetensors",
|
| 123 |
+
"layers.3.feed_forward.w3.biases": "0.safetensors",
|
| 124 |
"layers.3.attention_norm1.weight": "0.safetensors",
|
| 125 |
"layers.3.ffn_norm1.weight": "0.safetensors",
|
| 126 |
"layers.3.attention_norm2.weight": "0.safetensors",
|
| 127 |
"layers.3.ffn_norm2.weight": "0.safetensors",
|
| 128 |
"layers.3.adaln_modulation.weight": "0.safetensors",
|
| 129 |
+
"layers.3.adaln_modulation.scales": "0.safetensors",
|
| 130 |
+
"layers.3.adaln_modulation.biases": "0.safetensors",
|
| 131 |
"layers.3.adaln_modulation.bias": "0.safetensors",
|
| 132 |
"layers.4.attention.qkv.weight": "0.safetensors",
|
| 133 |
+
"layers.4.attention.qkv.scales": "0.safetensors",
|
| 134 |
+
"layers.4.attention.qkv.biases": "0.safetensors",
|
| 135 |
"layers.4.attention.norm_q.weight": "0.safetensors",
|
| 136 |
"layers.4.attention.norm_k.weight": "0.safetensors",
|
| 137 |
"layers.4.attention.o.weight": "0.safetensors",
|
| 138 |
+
"layers.4.attention.o.scales": "0.safetensors",
|
| 139 |
+
"layers.4.attention.o.biases": "0.safetensors",
|
| 140 |
"layers.4.feed_forward.w1.weight": "0.safetensors",
|
| 141 |
+
"layers.4.feed_forward.w1.scales": "0.safetensors",
|
| 142 |
+
"layers.4.feed_forward.w1.biases": "0.safetensors",
|
| 143 |
"layers.4.feed_forward.w2.weight": "0.safetensors",
|
| 144 |
+
"layers.4.feed_forward.w2.scales": "0.safetensors",
|
| 145 |
+
"layers.4.feed_forward.w2.biases": "0.safetensors",
|
| 146 |
"layers.4.feed_forward.w3.weight": "0.safetensors",
|
| 147 |
+
"layers.4.feed_forward.w3.scales": "0.safetensors",
|
| 148 |
+
"layers.4.feed_forward.w3.biases": "0.safetensors",
|
| 149 |
"layers.4.attention_norm1.weight": "0.safetensors",
|
| 150 |
"layers.4.ffn_norm1.weight": "0.safetensors",
|
| 151 |
"layers.4.attention_norm2.weight": "0.safetensors",
|
| 152 |
"layers.4.ffn_norm2.weight": "0.safetensors",
|
| 153 |
"layers.4.adaln_modulation.weight": "0.safetensors",
|
| 154 |
+
"layers.4.adaln_modulation.scales": "0.safetensors",
|
| 155 |
+
"layers.4.adaln_modulation.biases": "0.safetensors",
|
| 156 |
"layers.4.adaln_modulation.bias": "0.safetensors",
|
| 157 |
"layers.5.attention.qkv.weight": "0.safetensors",
|
| 158 |
+
"layers.5.attention.qkv.scales": "0.safetensors",
|
| 159 |
+
"layers.5.attention.qkv.biases": "0.safetensors",
|
| 160 |
"layers.5.attention.norm_q.weight": "0.safetensors",
|
| 161 |
"layers.5.attention.norm_k.weight": "0.safetensors",
|
| 162 |
"layers.5.attention.o.weight": "0.safetensors",
|
| 163 |
+
"layers.5.attention.o.scales": "0.safetensors",
|
| 164 |
+
"layers.5.attention.o.biases": "0.safetensors",
|
| 165 |
"layers.5.feed_forward.w1.weight": "0.safetensors",
|
| 166 |
+
"layers.5.feed_forward.w1.scales": "0.safetensors",
|
| 167 |
+
"layers.5.feed_forward.w1.biases": "0.safetensors",
|
| 168 |
"layers.5.feed_forward.w2.weight": "0.safetensors",
|
| 169 |
+
"layers.5.feed_forward.w2.scales": "0.safetensors",
|
| 170 |
+
"layers.5.feed_forward.w2.biases": "0.safetensors",
|
| 171 |
"layers.5.feed_forward.w3.weight": "0.safetensors",
|
| 172 |
+
"layers.5.feed_forward.w3.scales": "0.safetensors",
|
| 173 |
+
"layers.5.feed_forward.w3.biases": "0.safetensors",
|
| 174 |
"layers.5.attention_norm1.weight": "0.safetensors",
|
| 175 |
"layers.5.ffn_norm1.weight": "0.safetensors",
|
| 176 |
"layers.5.attention_norm2.weight": "0.safetensors",
|
| 177 |
"layers.5.ffn_norm2.weight": "0.safetensors",
|
| 178 |
"layers.5.adaln_modulation.weight": "0.safetensors",
|
| 179 |
+
"layers.5.adaln_modulation.scales": "0.safetensors",
|
| 180 |
+
"layers.5.adaln_modulation.biases": "0.safetensors",
|
| 181 |
"layers.5.adaln_modulation.bias": "0.safetensors",
|
| 182 |
"layers.6.attention.qkv.weight": "0.safetensors",
|
| 183 |
+
"layers.6.attention.qkv.scales": "0.safetensors",
|
| 184 |
+
"layers.6.attention.qkv.biases": "0.safetensors",
|
| 185 |
"layers.6.attention.norm_q.weight": "0.safetensors",
|
| 186 |
"layers.6.attention.norm_k.weight": "0.safetensors",
|
| 187 |
"layers.6.attention.o.weight": "0.safetensors",
|
| 188 |
+
"layers.6.attention.o.scales": "0.safetensors",
|
| 189 |
+
"layers.6.attention.o.biases": "0.safetensors",
|
| 190 |
"layers.6.feed_forward.w1.weight": "0.safetensors",
|
| 191 |
+
"layers.6.feed_forward.w1.scales": "0.safetensors",
|
| 192 |
+
"layers.6.feed_forward.w1.biases": "0.safetensors",
|
| 193 |
"layers.6.feed_forward.w2.weight": "0.safetensors",
|
| 194 |
+
"layers.6.feed_forward.w2.scales": "0.safetensors",
|
| 195 |
+
"layers.6.feed_forward.w2.biases": "0.safetensors",
|
| 196 |
"layers.6.feed_forward.w3.weight": "0.safetensors",
|
| 197 |
+
"layers.6.feed_forward.w3.scales": "0.safetensors",
|
| 198 |
+
"layers.6.feed_forward.w3.biases": "0.safetensors",
|
| 199 |
"layers.6.attention_norm1.weight": "0.safetensors",
|
| 200 |
"layers.6.ffn_norm1.weight": "0.safetensors",
|
| 201 |
"layers.6.attention_norm2.weight": "0.safetensors",
|
| 202 |
"layers.6.ffn_norm2.weight": "0.safetensors",
|
| 203 |
"layers.6.adaln_modulation.weight": "0.safetensors",
|
| 204 |
+
"layers.6.adaln_modulation.scales": "0.safetensors",
|
| 205 |
+
"layers.6.adaln_modulation.biases": "0.safetensors",
|
| 206 |
"layers.6.adaln_modulation.bias": "0.safetensors",
|
| 207 |
+
"layers.7.attention.qkv.weight": "0.safetensors",
|
| 208 |
+
"layers.7.attention.qkv.scales": "0.safetensors",
|
| 209 |
+
"layers.7.attention.qkv.biases": "0.safetensors",
|
| 210 |
+
"layers.7.attention.norm_q.weight": "0.safetensors",
|
| 211 |
+
"layers.7.attention.norm_k.weight": "0.safetensors",
|
| 212 |
+
"layers.7.attention.o.weight": "0.safetensors",
|
| 213 |
+
"layers.7.attention.o.scales": "0.safetensors",
|
| 214 |
+
"layers.7.attention.o.biases": "0.safetensors",
|
| 215 |
+
"layers.7.feed_forward.w1.weight": "0.safetensors",
|
| 216 |
+
"layers.7.feed_forward.w1.scales": "0.safetensors",
|
| 217 |
+
"layers.7.feed_forward.w1.biases": "0.safetensors",
|
| 218 |
+
"layers.7.feed_forward.w2.weight": "0.safetensors",
|
| 219 |
+
"layers.7.feed_forward.w2.scales": "0.safetensors",
|
| 220 |
+
"layers.7.feed_forward.w2.biases": "0.safetensors",
|
| 221 |
+
"layers.7.feed_forward.w3.weight": "0.safetensors",
|
| 222 |
+
"layers.7.feed_forward.w3.scales": "0.safetensors",
|
| 223 |
+
"layers.7.feed_forward.w3.biases": "0.safetensors",
|
| 224 |
+
"layers.7.attention_norm1.weight": "0.safetensors",
|
| 225 |
+
"layers.7.ffn_norm1.weight": "0.safetensors",
|
| 226 |
+
"layers.7.attention_norm2.weight": "0.safetensors",
|
| 227 |
+
"layers.7.ffn_norm2.weight": "0.safetensors",
|
| 228 |
+
"layers.7.adaln_modulation.weight": "0.safetensors",
|
| 229 |
+
"layers.7.adaln_modulation.scales": "0.safetensors",
|
| 230 |
+
"layers.7.adaln_modulation.biases": "0.safetensors",
|
| 231 |
+
"layers.7.adaln_modulation.bias": "0.safetensors",
|
| 232 |
+
"layers.8.attention.qkv.weight": "0.safetensors",
|
| 233 |
+
"layers.8.attention.qkv.scales": "0.safetensors",
|
| 234 |
+
"layers.8.attention.qkv.biases": "0.safetensors",
|
| 235 |
+
"layers.8.attention.norm_q.weight": "0.safetensors",
|
| 236 |
+
"layers.8.attention.norm_k.weight": "0.safetensors",
|
| 237 |
+
"layers.8.attention.o.weight": "0.safetensors",
|
| 238 |
+
"layers.8.attention.o.scales": "0.safetensors",
|
| 239 |
+
"layers.8.attention.o.biases": "0.safetensors",
|
| 240 |
+
"layers.8.feed_forward.w1.weight": "0.safetensors",
|
| 241 |
+
"layers.8.feed_forward.w1.scales": "0.safetensors",
|
| 242 |
+
"layers.8.feed_forward.w1.biases": "0.safetensors",
|
| 243 |
+
"layers.8.feed_forward.w2.weight": "0.safetensors",
|
| 244 |
+
"layers.8.feed_forward.w2.scales": "0.safetensors",
|
| 245 |
+
"layers.8.feed_forward.w2.biases": "0.safetensors",
|
| 246 |
+
"layers.8.feed_forward.w3.weight": "0.safetensors",
|
| 247 |
+
"layers.8.feed_forward.w3.scales": "0.safetensors",
|
| 248 |
+
"layers.8.feed_forward.w3.biases": "0.safetensors",
|
| 249 |
+
"layers.8.attention_norm1.weight": "0.safetensors",
|
| 250 |
+
"layers.8.ffn_norm1.weight": "0.safetensors",
|
| 251 |
+
"layers.8.attention_norm2.weight": "0.safetensors",
|
| 252 |
+
"layers.8.ffn_norm2.weight": "0.safetensors",
|
| 253 |
+
"layers.8.adaln_modulation.weight": "0.safetensors",
|
| 254 |
+
"layers.8.adaln_modulation.scales": "0.safetensors",
|
| 255 |
+
"layers.8.adaln_modulation.biases": "0.safetensors",
|
| 256 |
+
"layers.8.adaln_modulation.bias": "0.safetensors",
|
| 257 |
+
"layers.9.attention.qkv.weight": "0.safetensors",
|
| 258 |
+
"layers.9.attention.qkv.scales": "0.safetensors",
|
| 259 |
+
"layers.9.attention.qkv.biases": "0.safetensors",
|
| 260 |
+
"layers.9.attention.norm_q.weight": "0.safetensors",
|
| 261 |
+
"layers.9.attention.norm_k.weight": "0.safetensors",
|
| 262 |
+
"layers.9.attention.o.weight": "0.safetensors",
|
| 263 |
+
"layers.9.attention.o.scales": "0.safetensors",
|
| 264 |
+
"layers.9.attention.o.biases": "0.safetensors",
|
| 265 |
+
"layers.9.feed_forward.w1.weight": "0.safetensors",
|
| 266 |
+
"layers.9.feed_forward.w1.scales": "0.safetensors",
|
| 267 |
+
"layers.9.feed_forward.w1.biases": "0.safetensors",
|
| 268 |
+
"layers.9.feed_forward.w2.weight": "0.safetensors",
|
| 269 |
+
"layers.9.feed_forward.w2.scales": "0.safetensors",
|
| 270 |
+
"layers.9.feed_forward.w2.biases": "0.safetensors",
|
| 271 |
+
"layers.9.feed_forward.w3.weight": "0.safetensors",
|
| 272 |
+
"layers.9.feed_forward.w3.scales": "0.safetensors",
|
| 273 |
+
"layers.9.feed_forward.w3.biases": "0.safetensors",
|
| 274 |
+
"layers.9.attention_norm1.weight": "0.safetensors",
|
| 275 |
+
"layers.9.ffn_norm1.weight": "0.safetensors",
|
| 276 |
+
"layers.9.attention_norm2.weight": "0.safetensors",
|
| 277 |
+
"layers.9.ffn_norm2.weight": "0.safetensors",
|
| 278 |
+
"layers.9.adaln_modulation.weight": "0.safetensors",
|
| 279 |
+
"layers.9.adaln_modulation.scales": "0.safetensors",
|
| 280 |
+
"layers.9.adaln_modulation.biases": "0.safetensors",
|
| 281 |
+
"layers.9.adaln_modulation.bias": "0.safetensors",
|
| 282 |
+
"layers.10.attention.qkv.weight": "0.safetensors",
|
| 283 |
+
"layers.10.attention.qkv.scales": "0.safetensors",
|
| 284 |
+
"layers.10.attention.qkv.biases": "0.safetensors",
|
| 285 |
+
"layers.10.attention.norm_q.weight": "0.safetensors",
|
| 286 |
+
"layers.10.attention.norm_k.weight": "0.safetensors",
|
| 287 |
+
"layers.10.attention.o.weight": "0.safetensors",
|
| 288 |
+
"layers.10.attention.o.scales": "0.safetensors",
|
| 289 |
+
"layers.10.attention.o.biases": "0.safetensors",
|
| 290 |
+
"layers.10.feed_forward.w1.weight": "0.safetensors",
|
| 291 |
+
"layers.10.feed_forward.w1.scales": "0.safetensors",
|
| 292 |
+
"layers.10.feed_forward.w1.biases": "0.safetensors",
|
| 293 |
+
"layers.10.feed_forward.w2.weight": "0.safetensors",
|
| 294 |
+
"layers.10.feed_forward.w2.scales": "0.safetensors",
|
| 295 |
+
"layers.10.feed_forward.w2.biases": "0.safetensors",
|
| 296 |
+
"layers.10.feed_forward.w3.weight": "0.safetensors",
|
| 297 |
+
"layers.10.feed_forward.w3.scales": "0.safetensors",
|
| 298 |
+
"layers.10.feed_forward.w3.biases": "0.safetensors",
|
| 299 |
+
"layers.10.attention_norm1.weight": "0.safetensors",
|
| 300 |
+
"layers.10.ffn_norm1.weight": "0.safetensors",
|
| 301 |
+
"layers.10.attention_norm2.weight": "0.safetensors",
|
| 302 |
+
"layers.10.ffn_norm2.weight": "0.safetensors",
|
| 303 |
+
"layers.10.adaln_modulation.weight": "0.safetensors",
|
| 304 |
+
"layers.10.adaln_modulation.scales": "0.safetensors",
|
| 305 |
+
"layers.10.adaln_modulation.biases": "0.safetensors",
|
| 306 |
+
"layers.10.adaln_modulation.bias": "0.safetensors",
|
| 307 |
+
"layers.11.attention.qkv.weight": "0.safetensors",
|
| 308 |
+
"layers.11.attention.qkv.scales": "0.safetensors",
|
| 309 |
+
"layers.11.attention.qkv.biases": "0.safetensors",
|
| 310 |
+
"layers.11.attention.norm_q.weight": "0.safetensors",
|
| 311 |
+
"layers.11.attention.norm_k.weight": "0.safetensors",
|
| 312 |
+
"layers.11.attention.o.weight": "0.safetensors",
|
| 313 |
+
"layers.11.attention.o.scales": "0.safetensors",
|
| 314 |
+
"layers.11.attention.o.biases": "0.safetensors",
|
| 315 |
+
"layers.11.feed_forward.w1.weight": "0.safetensors",
|
| 316 |
+
"layers.11.feed_forward.w1.scales": "0.safetensors",
|
| 317 |
+
"layers.11.feed_forward.w1.biases": "0.safetensors",
|
| 318 |
+
"layers.11.feed_forward.w2.weight": "0.safetensors",
|
| 319 |
+
"layers.11.feed_forward.w2.scales": "0.safetensors",
|
| 320 |
+
"layers.11.feed_forward.w2.biases": "0.safetensors",
|
| 321 |
+
"layers.11.feed_forward.w3.weight": "0.safetensors",
|
| 322 |
+
"layers.11.feed_forward.w3.scales": "0.safetensors",
|
| 323 |
+
"layers.11.feed_forward.w3.biases": "0.safetensors",
|
| 324 |
+
"layers.11.attention_norm1.weight": "0.safetensors",
|
| 325 |
+
"layers.11.ffn_norm1.weight": "0.safetensors",
|
| 326 |
+
"layers.11.attention_norm2.weight": "0.safetensors",
|
| 327 |
+
"layers.11.ffn_norm2.weight": "0.safetensors",
|
| 328 |
+
"layers.11.adaln_modulation.weight": "0.safetensors",
|
| 329 |
+
"layers.11.adaln_modulation.scales": "0.safetensors",
|
| 330 |
+
"layers.11.adaln_modulation.biases": "0.safetensors",
|
| 331 |
+
"layers.11.adaln_modulation.bias": "0.safetensors",
|
| 332 |
+
"layers.12.attention.qkv.weight": "0.safetensors",
|
| 333 |
+
"layers.12.attention.qkv.scales": "0.safetensors",
|
| 334 |
+
"layers.12.attention.qkv.biases": "0.safetensors",
|
| 335 |
+
"layers.12.attention.norm_q.weight": "0.safetensors",
|
| 336 |
+
"layers.12.attention.norm_k.weight": "0.safetensors",
|
| 337 |
+
"layers.12.attention.o.weight": "0.safetensors",
|
| 338 |
+
"layers.12.attention.o.scales": "0.safetensors",
|
| 339 |
+
"layers.12.attention.o.biases": "0.safetensors",
|
| 340 |
+
"layers.12.feed_forward.w1.weight": "0.safetensors",
|
| 341 |
+
"layers.12.feed_forward.w1.scales": "0.safetensors",
|
| 342 |
+
"layers.12.feed_forward.w1.biases": "0.safetensors",
|
| 343 |
+
"layers.12.feed_forward.w2.weight": "0.safetensors",
|
| 344 |
+
"layers.12.feed_forward.w2.scales": "0.safetensors",
|
| 345 |
+
"layers.12.feed_forward.w2.biases": "0.safetensors",
|
| 346 |
+
"layers.12.feed_forward.w3.weight": "0.safetensors",
|
| 347 |
+
"layers.12.feed_forward.w3.scales": "0.safetensors",
|
| 348 |
+
"layers.12.feed_forward.w3.biases": "0.safetensors",
|
| 349 |
+
"layers.12.attention_norm1.weight": "0.safetensors",
|
| 350 |
+
"layers.12.ffn_norm1.weight": "0.safetensors",
|
| 351 |
+
"layers.12.attention_norm2.weight": "0.safetensors",
|
| 352 |
+
"layers.12.ffn_norm2.weight": "0.safetensors",
|
| 353 |
+
"layers.12.adaln_modulation.weight": "0.safetensors",
|
| 354 |
+
"layers.12.adaln_modulation.scales": "0.safetensors",
|
| 355 |
+
"layers.12.adaln_modulation.biases": "0.safetensors",
|
| 356 |
+
"layers.12.adaln_modulation.bias": "0.safetensors",
|
| 357 |
+
"layers.13.attention.qkv.weight": "0.safetensors",
|
| 358 |
+
"layers.13.attention.qkv.scales": "0.safetensors",
|
| 359 |
+
"layers.13.attention.qkv.biases": "0.safetensors",
|
| 360 |
+
"layers.13.attention.norm_q.weight": "0.safetensors",
|
| 361 |
+
"layers.13.attention.norm_k.weight": "0.safetensors",
|
| 362 |
+
"layers.13.attention.o.weight": "0.safetensors",
|
| 363 |
+
"layers.13.attention.o.scales": "0.safetensors",
|
| 364 |
+
"layers.13.attention.o.biases": "0.safetensors",
|
| 365 |
"layers.13.feed_forward.w1.weight": "1.safetensors",
|
| 366 |
+
"layers.13.feed_forward.w1.scales": "1.safetensors",
|
| 367 |
+
"layers.13.feed_forward.w1.biases": "1.safetensors",
|
| 368 |
"layers.13.feed_forward.w2.weight": "1.safetensors",
|
| 369 |
+
"layers.13.feed_forward.w2.scales": "1.safetensors",
|
| 370 |
+
"layers.13.feed_forward.w2.biases": "1.safetensors",
|
| 371 |
"layers.13.feed_forward.w3.weight": "1.safetensors",
|
| 372 |
+
"layers.13.feed_forward.w3.scales": "1.safetensors",
|
| 373 |
+
"layers.13.feed_forward.w3.biases": "1.safetensors",
|
| 374 |
"layers.13.attention_norm1.weight": "1.safetensors",
|
| 375 |
"layers.13.ffn_norm1.weight": "1.safetensors",
|
| 376 |
"layers.13.attention_norm2.weight": "1.safetensors",
|
| 377 |
"layers.13.ffn_norm2.weight": "1.safetensors",
|
| 378 |
"layers.13.adaln_modulation.weight": "1.safetensors",
|
| 379 |
+
"layers.13.adaln_modulation.scales": "1.safetensors",
|
| 380 |
+
"layers.13.adaln_modulation.biases": "1.safetensors",
|
| 381 |
"layers.13.adaln_modulation.bias": "1.safetensors",
|
| 382 |
"layers.14.attention.qkv.weight": "1.safetensors",
|
| 383 |
+
"layers.14.attention.qkv.scales": "1.safetensors",
|
| 384 |
+
"layers.14.attention.qkv.biases": "1.safetensors",
|
| 385 |
"layers.14.attention.norm_q.weight": "1.safetensors",
|
| 386 |
"layers.14.attention.norm_k.weight": "1.safetensors",
|
| 387 |
"layers.14.attention.o.weight": "1.safetensors",
|
| 388 |
+
"layers.14.attention.o.scales": "1.safetensors",
|
| 389 |
+
"layers.14.attention.o.biases": "1.safetensors",
|
| 390 |
"layers.14.feed_forward.w1.weight": "1.safetensors",
|
| 391 |
+
"layers.14.feed_forward.w1.scales": "1.safetensors",
|
| 392 |
+
"layers.14.feed_forward.w1.biases": "1.safetensors",
|
| 393 |
"layers.14.feed_forward.w2.weight": "1.safetensors",
|
| 394 |
+
"layers.14.feed_forward.w2.scales": "1.safetensors",
|
| 395 |
+
"layers.14.feed_forward.w2.biases": "1.safetensors",
|
| 396 |
"layers.14.feed_forward.w3.weight": "1.safetensors",
|
| 397 |
+
"layers.14.feed_forward.w3.scales": "1.safetensors",
|
| 398 |
+
"layers.14.feed_forward.w3.biases": "1.safetensors",
|
| 399 |
"layers.14.attention_norm1.weight": "1.safetensors",
|
| 400 |
"layers.14.ffn_norm1.weight": "1.safetensors",
|
| 401 |
"layers.14.attention_norm2.weight": "1.safetensors",
|
| 402 |
"layers.14.ffn_norm2.weight": "1.safetensors",
|
| 403 |
"layers.14.adaln_modulation.weight": "1.safetensors",
|
| 404 |
+
"layers.14.adaln_modulation.scales": "1.safetensors",
|
| 405 |
+
"layers.14.adaln_modulation.biases": "1.safetensors",
|
| 406 |
"layers.14.adaln_modulation.bias": "1.safetensors",
|
| 407 |
+
"layers.15.attention.qkv.weight": "1.safetensors",
|
| 408 |
+
"layers.15.attention.qkv.scales": "1.safetensors",
|
| 409 |
+
"layers.15.attention.qkv.biases": "1.safetensors",
|
| 410 |
+
"layers.15.attention.norm_q.weight": "1.safetensors",
|
| 411 |
+
"layers.15.attention.norm_k.weight": "1.safetensors",
|
| 412 |
+
"layers.15.attention.o.weight": "1.safetensors",
|
| 413 |
+
"layers.15.attention.o.scales": "1.safetensors",
|
| 414 |
+
"layers.15.attention.o.biases": "1.safetensors",
|
| 415 |
+
"layers.15.feed_forward.w1.weight": "1.safetensors",
|
| 416 |
+
"layers.15.feed_forward.w1.scales": "1.safetensors",
|
| 417 |
+
"layers.15.feed_forward.w1.biases": "1.safetensors",
|
| 418 |
+
"layers.15.feed_forward.w2.weight": "1.safetensors",
|
| 419 |
+
"layers.15.feed_forward.w2.scales": "1.safetensors",
|
| 420 |
+
"layers.15.feed_forward.w2.biases": "1.safetensors",
|
| 421 |
+
"layers.15.feed_forward.w3.weight": "1.safetensors",
|
| 422 |
+
"layers.15.feed_forward.w3.scales": "1.safetensors",
|
| 423 |
+
"layers.15.feed_forward.w3.biases": "1.safetensors",
|
| 424 |
+
"layers.15.attention_norm1.weight": "1.safetensors",
|
| 425 |
+
"layers.15.ffn_norm1.weight": "1.safetensors",
|
| 426 |
+
"layers.15.attention_norm2.weight": "1.safetensors",
|
| 427 |
+
"layers.15.ffn_norm2.weight": "1.safetensors",
|
| 428 |
+
"layers.15.adaln_modulation.weight": "1.safetensors",
|
| 429 |
+
"layers.15.adaln_modulation.scales": "1.safetensors",
|
| 430 |
+
"layers.15.adaln_modulation.biases": "1.safetensors",
|
| 431 |
+
"layers.15.adaln_modulation.bias": "1.safetensors",
|
| 432 |
+
"layers.16.attention.qkv.weight": "1.safetensors",
|
| 433 |
+
"layers.16.attention.qkv.scales": "1.safetensors",
|
| 434 |
+
"layers.16.attention.qkv.biases": "1.safetensors",
|
| 435 |
+
"layers.16.attention.norm_q.weight": "1.safetensors",
|
| 436 |
+
"layers.16.attention.norm_k.weight": "1.safetensors",
|
| 437 |
+
"layers.16.attention.o.weight": "1.safetensors",
|
| 438 |
+
"layers.16.attention.o.scales": "1.safetensors",
|
| 439 |
+
"layers.16.attention.o.biases": "1.safetensors",
|
| 440 |
+
"layers.16.feed_forward.w1.weight": "1.safetensors",
|
| 441 |
+
"layers.16.feed_forward.w1.scales": "1.safetensors",
|
| 442 |
+
"layers.16.feed_forward.w1.biases": "1.safetensors",
|
| 443 |
+
"layers.16.feed_forward.w2.weight": "1.safetensors",
|
| 444 |
+
"layers.16.feed_forward.w2.scales": "1.safetensors",
|
| 445 |
+
"layers.16.feed_forward.w2.biases": "1.safetensors",
|
| 446 |
+
"layers.16.feed_forward.w3.weight": "1.safetensors",
|
| 447 |
+
"layers.16.feed_forward.w3.scales": "1.safetensors",
|
| 448 |
+
"layers.16.feed_forward.w3.biases": "1.safetensors",
|
| 449 |
+
"layers.16.attention_norm1.weight": "1.safetensors",
|
| 450 |
+
"layers.16.ffn_norm1.weight": "1.safetensors",
|
| 451 |
+
"layers.16.attention_norm2.weight": "1.safetensors",
|
| 452 |
+
"layers.16.ffn_norm2.weight": "1.safetensors",
|
| 453 |
+
"layers.16.adaln_modulation.weight": "1.safetensors",
|
| 454 |
+
"layers.16.adaln_modulation.scales": "1.safetensors",
|
| 455 |
+
"layers.16.adaln_modulation.biases": "1.safetensors",
|
| 456 |
+
"layers.16.adaln_modulation.bias": "1.safetensors",
|
| 457 |
+
"layers.17.attention.qkv.weight": "1.safetensors",
|
| 458 |
+
"layers.17.attention.qkv.scales": "1.safetensors",
|
| 459 |
+
"layers.17.attention.qkv.biases": "1.safetensors",
|
| 460 |
+
"layers.17.attention.norm_q.weight": "1.safetensors",
|
| 461 |
+
"layers.17.attention.norm_k.weight": "1.safetensors",
|
| 462 |
+
"layers.17.attention.o.weight": "1.safetensors",
|
| 463 |
+
"layers.17.attention.o.scales": "1.safetensors",
|
| 464 |
+
"layers.17.attention.o.biases": "1.safetensors",
|
| 465 |
+
"layers.17.feed_forward.w1.weight": "1.safetensors",
|
| 466 |
+
"layers.17.feed_forward.w1.scales": "1.safetensors",
|
| 467 |
+
"layers.17.feed_forward.w1.biases": "1.safetensors",
|
| 468 |
+
"layers.17.feed_forward.w2.weight": "1.safetensors",
|
| 469 |
+
"layers.17.feed_forward.w2.scales": "1.safetensors",
|
| 470 |
+
"layers.17.feed_forward.w2.biases": "1.safetensors",
|
| 471 |
+
"layers.17.feed_forward.w3.weight": "1.safetensors",
|
| 472 |
+
"layers.17.feed_forward.w3.scales": "1.safetensors",
|
| 473 |
+
"layers.17.feed_forward.w3.biases": "1.safetensors",
|
| 474 |
+
"layers.17.attention_norm1.weight": "1.safetensors",
|
| 475 |
+
"layers.17.ffn_norm1.weight": "1.safetensors",
|
| 476 |
+
"layers.17.attention_norm2.weight": "1.safetensors",
|
| 477 |
+
"layers.17.ffn_norm2.weight": "1.safetensors",
|
| 478 |
+
"layers.17.adaln_modulation.weight": "1.safetensors",
|
| 479 |
+
"layers.17.adaln_modulation.scales": "1.safetensors",
|
| 480 |
+
"layers.17.adaln_modulation.biases": "1.safetensors",
|
| 481 |
+
"layers.17.adaln_modulation.bias": "1.safetensors",
|
| 482 |
+
"layers.18.attention.qkv.weight": "1.safetensors",
|
| 483 |
+
"layers.18.attention.qkv.scales": "1.safetensors",
|
| 484 |
+
"layers.18.attention.qkv.biases": "1.safetensors",
|
| 485 |
+
"layers.18.attention.norm_q.weight": "1.safetensors",
|
| 486 |
+
"layers.18.attention.norm_k.weight": "1.safetensors",
|
| 487 |
+
"layers.18.attention.o.weight": "1.safetensors",
|
| 488 |
+
"layers.18.attention.o.scales": "1.safetensors",
|
| 489 |
+
"layers.18.attention.o.biases": "1.safetensors",
|
| 490 |
+
"layers.18.feed_forward.w1.weight": "1.safetensors",
|
| 491 |
+
"layers.18.feed_forward.w1.scales": "1.safetensors",
|
| 492 |
+
"layers.18.feed_forward.w1.biases": "1.safetensors",
|
| 493 |
+
"layers.18.feed_forward.w2.weight": "1.safetensors",
|
| 494 |
+
"layers.18.feed_forward.w2.scales": "1.safetensors",
|
| 495 |
+
"layers.18.feed_forward.w2.biases": "1.safetensors",
|
| 496 |
+
"layers.18.feed_forward.w3.weight": "1.safetensors",
|
| 497 |
+
"layers.18.feed_forward.w3.scales": "1.safetensors",
|
| 498 |
+
"layers.18.feed_forward.w3.biases": "1.safetensors",
|
| 499 |
+
"layers.18.attention_norm1.weight": "1.safetensors",
|
| 500 |
+
"layers.18.ffn_norm1.weight": "1.safetensors",
|
| 501 |
+
"layers.18.attention_norm2.weight": "1.safetensors",
|
| 502 |
+
"layers.18.ffn_norm2.weight": "1.safetensors",
|
| 503 |
+
"layers.18.adaln_modulation.weight": "1.safetensors",
|
| 504 |
+
"layers.18.adaln_modulation.scales": "1.safetensors",
|
| 505 |
+
"layers.18.adaln_modulation.biases": "1.safetensors",
|
| 506 |
+
"layers.18.adaln_modulation.bias": "1.safetensors",
|
| 507 |
+
"layers.19.attention.qkv.weight": "1.safetensors",
|
| 508 |
+
"layers.19.attention.qkv.scales": "1.safetensors",
|
| 509 |
+
"layers.19.attention.qkv.biases": "1.safetensors",
|
| 510 |
+
"layers.19.attention.norm_q.weight": "1.safetensors",
|
| 511 |
+
"layers.19.attention.norm_k.weight": "1.safetensors",
|
| 512 |
+
"layers.19.attention.o.weight": "1.safetensors",
|
| 513 |
+
"layers.19.attention.o.scales": "1.safetensors",
|
| 514 |
+
"layers.19.attention.o.biases": "1.safetensors",
|
| 515 |
+
"layers.19.feed_forward.w1.weight": "1.safetensors",
|
| 516 |
+
"layers.19.feed_forward.w1.scales": "1.safetensors",
|
| 517 |
+
"layers.19.feed_forward.w1.biases": "1.safetensors",
|
| 518 |
+
"layers.19.feed_forward.w2.weight": "1.safetensors",
|
| 519 |
+
"layers.19.feed_forward.w2.scales": "1.safetensors",
|
| 520 |
+
"layers.19.feed_forward.w2.biases": "1.safetensors",
|
| 521 |
+
"layers.19.feed_forward.w3.weight": "1.safetensors",
|
| 522 |
+
"layers.19.feed_forward.w3.scales": "1.safetensors",
|
| 523 |
+
"layers.19.feed_forward.w3.biases": "1.safetensors",
|
| 524 |
+
"layers.19.attention_norm1.weight": "1.safetensors",
|
| 525 |
+
"layers.19.ffn_norm1.weight": "1.safetensors",
|
| 526 |
+
"layers.19.attention_norm2.weight": "1.safetensors",
|
| 527 |
+
"layers.19.ffn_norm2.weight": "1.safetensors",
|
| 528 |
+
"layers.19.adaln_modulation.weight": "1.safetensors",
|
| 529 |
+
"layers.19.adaln_modulation.scales": "1.safetensors",
|
| 530 |
+
"layers.19.adaln_modulation.biases": "1.safetensors",
|
| 531 |
+
"layers.19.adaln_modulation.bias": "1.safetensors",
|
| 532 |
+
"layers.20.attention.qkv.weight": "1.safetensors",
|
| 533 |
+
"layers.20.attention.qkv.scales": "1.safetensors",
|
| 534 |
+
"layers.20.attention.qkv.biases": "1.safetensors",
|
| 535 |
+
"layers.20.attention.norm_q.weight": "1.safetensors",
|
| 536 |
+
"layers.20.attention.norm_k.weight": "1.safetensors",
|
| 537 |
+
"layers.20.attention.o.weight": "1.safetensors",
|
| 538 |
+
"layers.20.attention.o.scales": "1.safetensors",
|
| 539 |
+
"layers.20.attention.o.biases": "1.safetensors",
|
| 540 |
+
"layers.20.feed_forward.w1.weight": "1.safetensors",
|
| 541 |
+
"layers.20.feed_forward.w1.scales": "1.safetensors",
|
| 542 |
+
"layers.20.feed_forward.w1.biases": "1.safetensors",
|
| 543 |
+
"layers.20.feed_forward.w2.weight": "1.safetensors",
|
| 544 |
+
"layers.20.feed_forward.w2.scales": "1.safetensors",
|
| 545 |
+
"layers.20.feed_forward.w2.biases": "1.safetensors",
|
| 546 |
+
"layers.20.feed_forward.w3.weight": "1.safetensors",
|
| 547 |
+
"layers.20.feed_forward.w3.scales": "1.safetensors",
|
| 548 |
+
"layers.20.feed_forward.w3.biases": "1.safetensors",
|
| 549 |
+
"layers.20.attention_norm1.weight": "1.safetensors",
|
| 550 |
+
"layers.20.ffn_norm1.weight": "1.safetensors",
|
| 551 |
+
"layers.20.attention_norm2.weight": "1.safetensors",
|
| 552 |
+
"layers.20.ffn_norm2.weight": "1.safetensors",
|
| 553 |
+
"layers.20.adaln_modulation.weight": "1.safetensors",
|
| 554 |
+
"layers.20.adaln_modulation.scales": "1.safetensors",
|
| 555 |
+
"layers.20.adaln_modulation.biases": "1.safetensors",
|
| 556 |
+
"layers.20.adaln_modulation.bias": "1.safetensors",
|
| 557 |
+
"layers.21.attention.qkv.weight": "1.safetensors",
|
| 558 |
+
"layers.21.attention.qkv.scales": "1.safetensors",
|
| 559 |
+
"layers.21.attention.qkv.biases": "1.safetensors",
|
| 560 |
+
"layers.21.attention.norm_q.weight": "1.safetensors",
|
| 561 |
+
"layers.21.attention.norm_k.weight": "1.safetensors",
|
| 562 |
+
"layers.21.attention.o.weight": "1.safetensors",
|
| 563 |
+
"layers.21.attention.o.scales": "1.safetensors",
|
| 564 |
+
"layers.21.attention.o.biases": "1.safetensors",
|
| 565 |
+
"layers.21.feed_forward.w1.weight": "1.safetensors",
|
| 566 |
+
"layers.21.feed_forward.w1.scales": "1.safetensors",
|
| 567 |
+
"layers.21.feed_forward.w1.biases": "1.safetensors",
|
| 568 |
+
"layers.21.feed_forward.w2.weight": "1.safetensors",
|
| 569 |
+
"layers.21.feed_forward.w2.scales": "1.safetensors",
|
| 570 |
+
"layers.21.feed_forward.w2.biases": "1.safetensors",
|
| 571 |
+
"layers.21.feed_forward.w3.weight": "1.safetensors",
|
| 572 |
+
"layers.21.feed_forward.w3.scales": "1.safetensors",
|
| 573 |
+
"layers.21.feed_forward.w3.biases": "1.safetensors",
|
| 574 |
+
"layers.21.attention_norm1.weight": "1.safetensors",
|
| 575 |
+
"layers.21.ffn_norm1.weight": "1.safetensors",
|
| 576 |
+
"layers.21.attention_norm2.weight": "1.safetensors",
|
| 577 |
+
"layers.21.ffn_norm2.weight": "1.safetensors",
|
| 578 |
+
"layers.21.adaln_modulation.weight": "1.safetensors",
|
| 579 |
+
"layers.21.adaln_modulation.scales": "1.safetensors",
|
| 580 |
+
"layers.21.adaln_modulation.biases": "1.safetensors",
|
| 581 |
+
"layers.21.adaln_modulation.bias": "1.safetensors",
|
| 582 |
+
"layers.22.attention.qkv.weight": "1.safetensors",
|
| 583 |
+
"layers.22.attention.qkv.scales": "1.safetensors",
|
| 584 |
+
"layers.22.attention.qkv.biases": "1.safetensors",
|
| 585 |
+
"layers.22.attention.norm_q.weight": "1.safetensors",
|
| 586 |
+
"layers.22.attention.norm_k.weight": "1.safetensors",
|
| 587 |
+
"layers.22.attention.o.weight": "1.safetensors",
|
| 588 |
+
"layers.22.attention.o.scales": "1.safetensors",
|
| 589 |
+
"layers.22.attention.o.biases": "1.safetensors",
|
| 590 |
+
"layers.22.feed_forward.w1.weight": "1.safetensors",
|
| 591 |
+
"layers.22.feed_forward.w1.scales": "1.safetensors",
|
| 592 |
+
"layers.22.feed_forward.w1.biases": "1.safetensors",
|
| 593 |
+
"layers.22.feed_forward.w2.weight": "1.safetensors",
|
| 594 |
+
"layers.22.feed_forward.w2.scales": "1.safetensors",
|
| 595 |
+
"layers.22.feed_forward.w2.biases": "1.safetensors",
|
| 596 |
+
"layers.22.feed_forward.w3.weight": "1.safetensors",
|
| 597 |
+
"layers.22.feed_forward.w3.scales": "1.safetensors",
|
| 598 |
+
"layers.22.feed_forward.w3.biases": "1.safetensors",
|
| 599 |
+
"layers.22.attention_norm1.weight": "1.safetensors",
|
| 600 |
+
"layers.22.ffn_norm1.weight": "1.safetensors",
|
| 601 |
+
"layers.22.attention_norm2.weight": "1.safetensors",
|
| 602 |
+
"layers.22.ffn_norm2.weight": "1.safetensors",
|
| 603 |
+
"layers.22.adaln_modulation.weight": "1.safetensors",
|
| 604 |
+
"layers.22.adaln_modulation.scales": "1.safetensors",
|
| 605 |
+
"layers.22.adaln_modulation.biases": "1.safetensors",
|
| 606 |
+
"layers.22.adaln_modulation.bias": "1.safetensors",
|
| 607 |
+
"layers.23.attention.qkv.weight": "1.safetensors",
|
| 608 |
+
"layers.23.attention.qkv.scales": "1.safetensors",
|
| 609 |
+
"layers.23.attention.qkv.biases": "1.safetensors",
|
| 610 |
+
"layers.23.attention.norm_q.weight": "1.safetensors",
|
| 611 |
+
"layers.23.attention.norm_k.weight": "1.safetensors",
|
| 612 |
+
"layers.23.attention.o.weight": "1.safetensors",
|
| 613 |
+
"layers.23.attention.o.scales": "1.safetensors",
|
| 614 |
+
"layers.23.attention.o.biases": "1.safetensors",
|
| 615 |
+
"layers.23.feed_forward.w1.weight": "1.safetensors",
|
| 616 |
+
"layers.23.feed_forward.w1.scales": "1.safetensors",
|
| 617 |
+
"layers.23.feed_forward.w1.biases": "1.safetensors",
|
| 618 |
+
"layers.23.feed_forward.w2.weight": "1.safetensors",
|
| 619 |
+
"layers.23.feed_forward.w2.scales": "1.safetensors",
|
| 620 |
+
"layers.23.feed_forward.w2.biases": "1.safetensors",
|
| 621 |
+
"layers.23.feed_forward.w3.weight": "1.safetensors",
|
| 622 |
+
"layers.23.feed_forward.w3.scales": "1.safetensors",
|
| 623 |
+
"layers.23.feed_forward.w3.biases": "1.safetensors",
|
| 624 |
+
"layers.23.attention_norm1.weight": "1.safetensors",
|
| 625 |
+
"layers.23.ffn_norm1.weight": "1.safetensors",
|
| 626 |
+
"layers.23.attention_norm2.weight": "1.safetensors",
|
| 627 |
+
"layers.23.ffn_norm2.weight": "1.safetensors",
|
| 628 |
+
"layers.23.adaln_modulation.weight": "1.safetensors",
|
| 629 |
+
"layers.23.adaln_modulation.scales": "1.safetensors",
|
| 630 |
+
"layers.23.adaln_modulation.biases": "1.safetensors",
|
| 631 |
+
"layers.23.adaln_modulation.bias": "1.safetensors",
|
| 632 |
+
"layers.24.attention.qkv.weight": "1.safetensors",
|
| 633 |
+
"layers.24.attention.qkv.scales": "1.safetensors",
|
| 634 |
+
"layers.24.attention.qkv.biases": "1.safetensors",
|
| 635 |
+
"layers.24.attention.norm_q.weight": "1.safetensors",
|
| 636 |
+
"layers.24.attention.norm_k.weight": "1.safetensors",
|
| 637 |
+
"layers.24.attention.o.weight": "1.safetensors",
|
| 638 |
+
"layers.24.attention.o.scales": "1.safetensors",
|
| 639 |
+
"layers.24.attention.o.biases": "1.safetensors",
|
| 640 |
+
"layers.24.feed_forward.w1.weight": "1.safetensors",
|
| 641 |
+
"layers.24.feed_forward.w1.scales": "1.safetensors",
|
| 642 |
+
"layers.24.feed_forward.w1.biases": "1.safetensors",
|
| 643 |
+
"layers.24.feed_forward.w2.weight": "1.safetensors",
|
| 644 |
+
"layers.24.feed_forward.w2.scales": "1.safetensors",
|
| 645 |
+
"layers.24.feed_forward.w2.biases": "1.safetensors",
|
| 646 |
+
"layers.24.feed_forward.w3.weight": "1.safetensors",
|
| 647 |
+
"layers.24.feed_forward.w3.scales": "1.safetensors",
|
| 648 |
+
"layers.24.feed_forward.w3.biases": "1.safetensors",
|
| 649 |
+
"layers.24.attention_norm1.weight": "1.safetensors",
|
| 650 |
+
"layers.24.ffn_norm1.weight": "1.safetensors",
|
| 651 |
+
"layers.24.attention_norm2.weight": "1.safetensors",
|
| 652 |
+
"layers.24.ffn_norm2.weight": "1.safetensors",
|
| 653 |
+
"layers.24.adaln_modulation.weight": "1.safetensors",
|
| 654 |
+
"layers.24.adaln_modulation.scales": "1.safetensors",
|
| 655 |
+
"layers.24.adaln_modulation.biases": "1.safetensors",
|
| 656 |
+
"layers.24.adaln_modulation.bias": "1.safetensors",
|
| 657 |
+
"layers.25.attention.qkv.weight": "1.safetensors",
|
| 658 |
+
"layers.25.attention.qkv.scales": "1.safetensors",
|
| 659 |
+
"layers.25.attention.qkv.biases": "1.safetensors",
|
| 660 |
+
"layers.25.attention.norm_q.weight": "1.safetensors",
|
| 661 |
+
"layers.25.attention.norm_k.weight": "1.safetensors",
|
| 662 |
+
"layers.25.attention.o.weight": "1.safetensors",
|
| 663 |
+
"layers.25.attention.o.scales": "1.safetensors",
|
| 664 |
+
"layers.25.attention.o.biases": "1.safetensors",
|
| 665 |
+
"layers.25.feed_forward.w1.weight": "1.safetensors",
|
| 666 |
+
"layers.25.feed_forward.w1.scales": "1.safetensors",
|
| 667 |
+
"layers.25.feed_forward.w1.biases": "1.safetensors",
|
| 668 |
+
"layers.25.feed_forward.w2.weight": "1.safetensors",
|
| 669 |
+
"layers.25.feed_forward.w2.scales": "1.safetensors",
|
| 670 |
+
"layers.25.feed_forward.w2.biases": "1.safetensors",
|
| 671 |
+
"layers.25.feed_forward.w3.weight": "1.safetensors",
|
| 672 |
+
"layers.25.feed_forward.w3.scales": "1.safetensors",
|
| 673 |
+
"layers.25.feed_forward.w3.biases": "1.safetensors",
|
| 674 |
+
"layers.25.attention_norm1.weight": "1.safetensors",
|
| 675 |
+
"layers.25.ffn_norm1.weight": "1.safetensors",
|
| 676 |
+
"layers.25.attention_norm2.weight": "1.safetensors",
|
| 677 |
+
"layers.25.ffn_norm2.weight": "1.safetensors",
|
| 678 |
+
"layers.25.adaln_modulation.weight": "1.safetensors",
|
| 679 |
+
"layers.25.adaln_modulation.scales": "1.safetensors",
|
| 680 |
+
"layers.25.adaln_modulation.biases": "1.safetensors",
|
| 681 |
+
"layers.25.adaln_modulation.bias": "1.safetensors",
|
| 682 |
+
"layers.26.attention.qkv.weight": "1.safetensors",
|
| 683 |
+
"layers.26.attention.qkv.scales": "1.safetensors",
|
| 684 |
+
"layers.26.attention.qkv.biases": "1.safetensors",
|
| 685 |
+
"layers.26.attention.norm_q.weight": "1.safetensors",
|
| 686 |
+
"layers.26.attention.norm_k.weight": "1.safetensors",
|
| 687 |
+
"layers.26.attention.o.weight": "1.safetensors",
|
| 688 |
+
"layers.26.attention.o.scales": "1.safetensors",
|
| 689 |
+
"layers.26.attention.o.biases": "1.safetensors",
|
| 690 |
+
"layers.26.feed_forward.w1.weight": "1.safetensors",
|
| 691 |
+
"layers.26.feed_forward.w1.scales": "1.safetensors",
|
| 692 |
+
"layers.26.feed_forward.w1.biases": "1.safetensors",
|
| 693 |
+
"layers.26.feed_forward.w2.weight": "1.safetensors",
|
| 694 |
+
"layers.26.feed_forward.w2.scales": "1.safetensors",
|
| 695 |
+
"layers.26.feed_forward.w2.biases": "1.safetensors",
|
| 696 |
+
"layers.26.feed_forward.w3.weight": "1.safetensors",
|
| 697 |
+
"layers.26.feed_forward.w3.scales": "1.safetensors",
|
| 698 |
+
"layers.26.feed_forward.w3.biases": "1.safetensors",
|
| 699 |
+
"layers.26.attention_norm1.weight": "1.safetensors",
|
| 700 |
+
"layers.26.ffn_norm1.weight": "1.safetensors",
|
| 701 |
+
"layers.26.attention_norm2.weight": "1.safetensors",
|
| 702 |
+
"layers.26.ffn_norm2.weight": "1.safetensors",
|
| 703 |
+
"layers.26.adaln_modulation.weight": "1.safetensors",
|
| 704 |
+
"layers.26.adaln_modulation.scales": "1.safetensors",
|
| 705 |
+
"layers.26.adaln_modulation.biases": "1.safetensors",
|
| 706 |
+
"layers.26.adaln_modulation.bias": "1.safetensors",
|
| 707 |
+
"layers.27.attention.qkv.weight": "1.safetensors",
|
| 708 |
+
"layers.27.attention.qkv.scales": "1.safetensors",
|
| 709 |
+
"layers.27.attention.qkv.biases": "1.safetensors",
|
| 710 |
+
"layers.27.attention.norm_q.weight": "1.safetensors",
|
| 711 |
+
"layers.27.attention.norm_k.weight": "1.safetensors",
|
| 712 |
+
"layers.27.attention.o.weight": "1.safetensors",
|
| 713 |
+
"layers.27.attention.o.scales": "1.safetensors",
|
| 714 |
+
"layers.27.attention.o.biases": "1.safetensors",
|
| 715 |
+
"layers.27.feed_forward.w1.weight": "1.safetensors",
|
| 716 |
+
"layers.27.feed_forward.w1.scales": "1.safetensors",
|
| 717 |
+
"layers.27.feed_forward.w1.biases": "1.safetensors",
|
| 718 |
+
"layers.27.feed_forward.w2.weight": "1.safetensors",
|
| 719 |
+
"layers.27.feed_forward.w2.scales": "1.safetensors",
|
| 720 |
+
"layers.27.feed_forward.w2.biases": "1.safetensors",
|
| 721 |
+
"layers.27.feed_forward.w3.weight": "2.safetensors",
|
| 722 |
+
"layers.27.feed_forward.w3.scales": "2.safetensors",
|
| 723 |
+
"layers.27.feed_forward.w3.biases": "2.safetensors",
|
| 724 |
+
"layers.27.attention_norm1.weight": "2.safetensors",
|
| 725 |
+
"layers.27.ffn_norm1.weight": "2.safetensors",
|
| 726 |
+
"layers.27.attention_norm2.weight": "2.safetensors",
|
| 727 |
+
"layers.27.ffn_norm2.weight": "2.safetensors",
|
| 728 |
+
"layers.27.adaln_modulation.weight": "2.safetensors",
|
| 729 |
+
"layers.27.adaln_modulation.scales": "2.safetensors",
|
| 730 |
+
"layers.27.adaln_modulation.biases": "2.safetensors",
|
| 731 |
+
"layers.27.adaln_modulation.bias": "2.safetensors",
|
| 732 |
+
"layers.28.attention.qkv.weight": "2.safetensors",
|
| 733 |
+
"layers.28.attention.qkv.scales": "2.safetensors",
|
| 734 |
+
"layers.28.attention.qkv.biases": "2.safetensors",
|
| 735 |
+
"layers.28.attention.norm_q.weight": "2.safetensors",
|
| 736 |
+
"layers.28.attention.norm_k.weight": "2.safetensors",
|
| 737 |
+
"layers.28.attention.o.weight": "2.safetensors",
|
| 738 |
+
"layers.28.attention.o.scales": "2.safetensors",
|
| 739 |
+
"layers.28.attention.o.biases": "2.safetensors",
|
| 740 |
+
"layers.28.feed_forward.w1.weight": "2.safetensors",
|
| 741 |
+
"layers.28.feed_forward.w1.scales": "2.safetensors",
|
| 742 |
+
"layers.28.feed_forward.w1.biases": "2.safetensors",
|
| 743 |
+
"layers.28.feed_forward.w2.weight": "2.safetensors",
|
| 744 |
+
"layers.28.feed_forward.w2.scales": "2.safetensors",
|
| 745 |
+
"layers.28.feed_forward.w2.biases": "2.safetensors",
|
| 746 |
+
"layers.28.feed_forward.w3.weight": "2.safetensors",
|
| 747 |
+
"layers.28.feed_forward.w3.scales": "2.safetensors",
|
| 748 |
+
"layers.28.feed_forward.w3.biases": "2.safetensors",
|
| 749 |
+
"layers.28.attention_norm1.weight": "2.safetensors",
|
| 750 |
+
"layers.28.ffn_norm1.weight": "2.safetensors",
|
| 751 |
+
"layers.28.attention_norm2.weight": "2.safetensors",
|
| 752 |
+
"layers.28.ffn_norm2.weight": "2.safetensors",
|
| 753 |
+
"layers.28.adaln_modulation.weight": "2.safetensors",
|
| 754 |
+
"layers.28.adaln_modulation.scales": "2.safetensors",
|
| 755 |
+
"layers.28.adaln_modulation.biases": "2.safetensors",
|
| 756 |
+
"layers.28.adaln_modulation.bias": "2.safetensors",
|
| 757 |
+
"layers.29.attention.qkv.weight": "2.safetensors",
|
| 758 |
+
"layers.29.attention.qkv.scales": "2.safetensors",
|
| 759 |
+
"layers.29.attention.qkv.biases": "2.safetensors",
|
| 760 |
+
"layers.29.attention.norm_q.weight": "2.safetensors",
|
| 761 |
+
"layers.29.attention.norm_k.weight": "2.safetensors",
|
| 762 |
+
"layers.29.attention.o.weight": "2.safetensors",
|
| 763 |
+
"layers.29.attention.o.scales": "2.safetensors",
|
| 764 |
+
"layers.29.attention.o.biases": "2.safetensors",
|
| 765 |
+
"layers.29.feed_forward.w1.weight": "2.safetensors",
|
| 766 |
+
"layers.29.feed_forward.w1.scales": "2.safetensors",
|
| 767 |
+
"layers.29.feed_forward.w1.biases": "2.safetensors",
|
| 768 |
+
"layers.29.feed_forward.w2.weight": "2.safetensors",
|
| 769 |
+
"layers.29.feed_forward.w2.scales": "2.safetensors",
|
| 770 |
+
"layers.29.feed_forward.w2.biases": "2.safetensors",
|
| 771 |
+
"layers.29.feed_forward.w3.weight": "2.safetensors",
|
| 772 |
+
"layers.29.feed_forward.w3.scales": "2.safetensors",
|
| 773 |
+
"layers.29.feed_forward.w3.biases": "2.safetensors",
|
| 774 |
+
"layers.29.attention_norm1.weight": "2.safetensors",
|
| 775 |
+
"layers.29.ffn_norm1.weight": "2.safetensors",
|
| 776 |
+
"layers.29.attention_norm2.weight": "2.safetensors",
|
| 777 |
+
"layers.29.ffn_norm2.weight": "2.safetensors",
|
| 778 |
+
"layers.29.adaln_modulation.weight": "2.safetensors",
|
| 779 |
+
"layers.29.adaln_modulation.scales": "2.safetensors",
|
| 780 |
+
"layers.29.adaln_modulation.biases": "2.safetensors",
|
| 781 |
+
"layers.29.adaln_modulation.bias": "2.safetensors",
|
| 782 |
+
"layers.30.attention.qkv.weight": "2.safetensors",
|
| 783 |
+
"layers.30.attention.qkv.scales": "2.safetensors",
|
| 784 |
+
"layers.30.attention.qkv.biases": "2.safetensors",
|
| 785 |
+
"layers.30.attention.norm_q.weight": "2.safetensors",
|
| 786 |
+
"layers.30.attention.norm_k.weight": "2.safetensors",
|
| 787 |
+
"layers.30.attention.o.weight": "2.safetensors",
|
| 788 |
+
"layers.30.attention.o.scales": "2.safetensors",
|
| 789 |
+
"layers.30.attention.o.biases": "2.safetensors",
|
| 790 |
+
"layers.30.feed_forward.w1.weight": "2.safetensors",
|
| 791 |
+
"layers.30.feed_forward.w1.scales": "2.safetensors",
|
| 792 |
+
"layers.30.feed_forward.w1.biases": "2.safetensors",
|
| 793 |
+
"layers.30.feed_forward.w2.weight": "2.safetensors",
|
| 794 |
+
"layers.30.feed_forward.w2.scales": "2.safetensors",
|
| 795 |
+
"layers.30.feed_forward.w2.biases": "2.safetensors",
|
| 796 |
+
"layers.30.feed_forward.w3.weight": "2.safetensors",
|
| 797 |
+
"layers.30.feed_forward.w3.scales": "2.safetensors",
|
| 798 |
+
"layers.30.feed_forward.w3.biases": "2.safetensors",
|
| 799 |
+
"layers.30.attention_norm1.weight": "2.safetensors",
|
| 800 |
+
"layers.30.ffn_norm1.weight": "2.safetensors",
|
| 801 |
+
"layers.30.attention_norm2.weight": "2.safetensors",
|
| 802 |
+
"layers.30.ffn_norm2.weight": "2.safetensors",
|
| 803 |
+
"layers.30.adaln_modulation.weight": "2.safetensors",
|
| 804 |
+
"layers.30.adaln_modulation.scales": "2.safetensors",
|
| 805 |
+
"layers.30.adaln_modulation.biases": "2.safetensors",
|
| 806 |
+
"layers.30.adaln_modulation.bias": "2.safetensors",
|
| 807 |
+
"layers.31.attention.qkv.weight": "2.safetensors",
|
| 808 |
+
"layers.31.attention.qkv.scales": "2.safetensors",
|
| 809 |
+
"layers.31.attention.qkv.biases": "2.safetensors",
|
| 810 |
+
"layers.31.attention.norm_q.weight": "2.safetensors",
|
| 811 |
+
"layers.31.attention.norm_k.weight": "2.safetensors",
|
| 812 |
+
"layers.31.attention.o.weight": "2.safetensors",
|
| 813 |
+
"layers.31.attention.o.scales": "2.safetensors",
|
| 814 |
+
"layers.31.attention.o.biases": "2.safetensors",
|
| 815 |
+
"layers.31.feed_forward.w1.weight": "2.safetensors",
|
| 816 |
+
"layers.31.feed_forward.w1.scales": "2.safetensors",
|
| 817 |
+
"layers.31.feed_forward.w1.biases": "2.safetensors",
|
| 818 |
+
"layers.31.feed_forward.w2.weight": "2.safetensors",
|
| 819 |
+
"layers.31.feed_forward.w2.scales": "2.safetensors",
|
| 820 |
+
"layers.31.feed_forward.w2.biases": "2.safetensors",
|
| 821 |
+
"layers.31.feed_forward.w3.weight": "2.safetensors",
|
| 822 |
+
"layers.31.feed_forward.w3.scales": "2.safetensors",
|
| 823 |
+
"layers.31.feed_forward.w3.biases": "2.safetensors",
|
| 824 |
+
"layers.31.attention_norm1.weight": "2.safetensors",
|
| 825 |
+
"layers.31.ffn_norm1.weight": "2.safetensors",
|
| 826 |
+
"layers.31.attention_norm2.weight": "2.safetensors",
|
| 827 |
+
"layers.31.ffn_norm2.weight": "2.safetensors",
|
| 828 |
+
"layers.31.adaln_modulation.weight": "2.safetensors",
|
| 829 |
+
"layers.31.adaln_modulation.scales": "2.safetensors",
|
| 830 |
+
"layers.31.adaln_modulation.biases": "2.safetensors",
|
| 831 |
+
"layers.31.adaln_modulation.bias": "2.safetensors",
|
| 832 |
+
"layers.32.attention.qkv.weight": "2.safetensors",
|
| 833 |
+
"layers.32.attention.qkv.scales": "2.safetensors",
|
| 834 |
+
"layers.32.attention.qkv.biases": "2.safetensors",
|
| 835 |
+
"layers.32.attention.norm_q.weight": "2.safetensors",
|
| 836 |
+
"layers.32.attention.norm_k.weight": "2.safetensors",
|
| 837 |
+
"layers.32.attention.o.weight": "2.safetensors",
|
| 838 |
+
"layers.32.attention.o.scales": "2.safetensors",
|
| 839 |
+
"layers.32.attention.o.biases": "2.safetensors",
|
| 840 |
+
"layers.32.feed_forward.w1.weight": "2.safetensors",
|
| 841 |
+
"layers.32.feed_forward.w1.scales": "2.safetensors",
|
| 842 |
+
"layers.32.feed_forward.w1.biases": "2.safetensors",
|
| 843 |
+
"layers.32.feed_forward.w2.weight": "2.safetensors",
|
| 844 |
+
"layers.32.feed_forward.w2.scales": "2.safetensors",
|
| 845 |
+
"layers.32.feed_forward.w2.biases": "2.safetensors",
|
| 846 |
+
"layers.32.feed_forward.w3.weight": "2.safetensors",
|
| 847 |
+
"layers.32.feed_forward.w3.scales": "2.safetensors",
|
| 848 |
+
"layers.32.feed_forward.w3.biases": "2.safetensors",
|
| 849 |
+
"layers.32.attention_norm1.weight": "2.safetensors",
|
| 850 |
+
"layers.32.ffn_norm1.weight": "2.safetensors",
|
| 851 |
+
"layers.32.attention_norm2.weight": "2.safetensors",
|
| 852 |
+
"layers.32.ffn_norm2.weight": "2.safetensors",
|
| 853 |
+
"layers.32.adaln_modulation.weight": "2.safetensors",
|
| 854 |
+
"layers.32.adaln_modulation.scales": "2.safetensors",
|
| 855 |
+
"layers.32.adaln_modulation.biases": "2.safetensors",
|
| 856 |
+
"layers.32.adaln_modulation.bias": "2.safetensors",
|
| 857 |
+
"layers.33.attention.qkv.weight": "2.safetensors",
|
| 858 |
+
"layers.33.attention.qkv.scales": "2.safetensors",
|
| 859 |
+
"layers.33.attention.qkv.biases": "2.safetensors",
|
| 860 |
+
"layers.33.attention.norm_q.weight": "2.safetensors",
|
| 861 |
+
"layers.33.attention.norm_k.weight": "2.safetensors",
|
| 862 |
+
"layers.33.attention.o.weight": "2.safetensors",
|
| 863 |
+
"layers.33.attention.o.scales": "2.safetensors",
|
| 864 |
+
"layers.33.attention.o.biases": "2.safetensors",
|
| 865 |
+
"layers.33.feed_forward.w1.weight": "2.safetensors",
|
| 866 |
+
"layers.33.feed_forward.w1.scales": "2.safetensors",
|
| 867 |
+
"layers.33.feed_forward.w1.biases": "2.safetensors",
|
| 868 |
+
"layers.33.feed_forward.w2.weight": "2.safetensors",
|
| 869 |
+
"layers.33.feed_forward.w2.scales": "2.safetensors",
|
| 870 |
+
"layers.33.feed_forward.w2.biases": "2.safetensors",
|
| 871 |
+
"layers.33.feed_forward.w3.weight": "2.safetensors",
|
| 872 |
+
"layers.33.feed_forward.w3.scales": "2.safetensors",
|
| 873 |
+
"layers.33.feed_forward.w3.biases": "2.safetensors",
|
| 874 |
+
"layers.33.attention_norm1.weight": "2.safetensors",
|
| 875 |
+
"layers.33.ffn_norm1.weight": "2.safetensors",
|
| 876 |
+
"layers.33.attention_norm2.weight": "2.safetensors",
|
| 877 |
+
"layers.33.ffn_norm2.weight": "2.safetensors",
|
| 878 |
+
"layers.33.adaln_modulation.weight": "2.safetensors",
|
| 879 |
+
"layers.33.adaln_modulation.scales": "2.safetensors",
|
| 880 |
+
"layers.33.adaln_modulation.biases": "2.safetensors",
|
| 881 |
+
"layers.33.adaln_modulation.bias": "2.safetensors",
|
| 882 |
+
"final_layer.linear.weight": "2.safetensors",
|
| 883 |
+
"final_layer.linear.scales": "2.safetensors",
|
| 884 |
+
"final_layer.linear.biases": "2.safetensors",
|
| 885 |
+
"final_layer.linear.bias": "2.safetensors",
|
| 886 |
+
"final_layer.adaln_modulation.weight": "2.safetensors",
|
| 887 |
+
"final_layer.adaln_modulation.scales": "2.safetensors",
|
| 888 |
+
"final_layer.adaln_modulation.biases": "2.safetensors",
|
| 889 |
+
"final_layer.adaln_modulation.bias": "2.safetensors"
|
| 890 |
}
|
| 891 |
}
|
unconditional_transformer/0.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:f0023804dbc53a0e4c5bb797fcda41b051d0640ea6d840115af5b95c159a2807
|
| 3 |
+
size 2144765248
|
unconditional_transformer/1.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 sha256:2634defc4b4cb0d0fcf1deaa47d998ca63f9156c588dfbe1c8d89e719eac7836
|
| 3 |
+
size 2145684605
|
unconditional_transformer/2.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 sha256:5b938492251bf636291afeb8c4ce67a6b0bb995b6989c5da2d2ee7fe0745d08c
|
| 3 |
+
size 931181187
|
unconditional_transformer/model.safetensors.index.json
CHANGED
|
@@ -1,678 +1,891 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"quantization_level": "4",
|
| 4 |
-
"mflux_version": "0.
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"input_proj.weight": "0.safetensors",
|
| 8 |
-
"input_proj.
|
|
|
|
| 9 |
"input_proj.bias": "0.safetensors",
|
| 10 |
"llm_cond_norm.weight": "0.safetensors",
|
| 11 |
"llm_cond_proj.weight": "0.safetensors",
|
| 12 |
-
"llm_cond_proj.
|
|
|
|
| 13 |
"llm_cond_proj.bias": "0.safetensors",
|
| 14 |
"t_embedding.mlp_in.weight": "0.safetensors",
|
| 15 |
-
"t_embedding.mlp_in.
|
|
|
|
| 16 |
"t_embedding.mlp_in.bias": "0.safetensors",
|
| 17 |
"t_embedding.mlp_out.weight": "0.safetensors",
|
| 18 |
-
"t_embedding.mlp_out.
|
|
|
|
| 19 |
"t_embedding.mlp_out.bias": "0.safetensors",
|
| 20 |
"adaln_proj.weight": "0.safetensors",
|
| 21 |
-
"adaln_proj.
|
|
|
|
| 22 |
"adaln_proj.bias": "0.safetensors",
|
| 23 |
"embed_image_indicator.weight": "0.safetensors",
|
|
|
|
|
|
|
| 24 |
"rotary_emb.inv_freq": "0.safetensors",
|
| 25 |
"layers.0.attention.qkv.weight": "0.safetensors",
|
| 26 |
-
"layers.0.attention.qkv.
|
|
|
|
| 27 |
"layers.0.attention.norm_q.weight": "0.safetensors",
|
| 28 |
"layers.0.attention.norm_k.weight": "0.safetensors",
|
| 29 |
"layers.0.attention.o.weight": "0.safetensors",
|
| 30 |
-
"layers.0.attention.o.
|
|
|
|
| 31 |
"layers.0.feed_forward.w1.weight": "0.safetensors",
|
| 32 |
-
"layers.0.feed_forward.w1.
|
|
|
|
| 33 |
"layers.0.feed_forward.w2.weight": "0.safetensors",
|
| 34 |
-
"layers.0.feed_forward.w2.
|
|
|
|
| 35 |
"layers.0.feed_forward.w3.weight": "0.safetensors",
|
| 36 |
-
"layers.0.feed_forward.w3.
|
|
|
|
| 37 |
"layers.0.attention_norm1.weight": "0.safetensors",
|
| 38 |
"layers.0.ffn_norm1.weight": "0.safetensors",
|
| 39 |
"layers.0.attention_norm2.weight": "0.safetensors",
|
| 40 |
"layers.0.ffn_norm2.weight": "0.safetensors",
|
| 41 |
"layers.0.adaln_modulation.weight": "0.safetensors",
|
| 42 |
-
"layers.0.adaln_modulation.
|
|
|
|
| 43 |
"layers.0.adaln_modulation.bias": "0.safetensors",
|
| 44 |
"layers.1.attention.qkv.weight": "0.safetensors",
|
| 45 |
-
"layers.1.attention.qkv.
|
|
|
|
| 46 |
"layers.1.attention.norm_q.weight": "0.safetensors",
|
| 47 |
"layers.1.attention.norm_k.weight": "0.safetensors",
|
| 48 |
"layers.1.attention.o.weight": "0.safetensors",
|
| 49 |
-
"layers.1.attention.o.
|
|
|
|
| 50 |
"layers.1.feed_forward.w1.weight": "0.safetensors",
|
| 51 |
-
"layers.1.feed_forward.w1.
|
|
|
|
| 52 |
"layers.1.feed_forward.w2.weight": "0.safetensors",
|
| 53 |
-
"layers.1.feed_forward.w2.
|
|
|
|
| 54 |
"layers.1.feed_forward.w3.weight": "0.safetensors",
|
| 55 |
-
"layers.1.feed_forward.w3.
|
|
|
|
| 56 |
"layers.1.attention_norm1.weight": "0.safetensors",
|
| 57 |
"layers.1.ffn_norm1.weight": "0.safetensors",
|
| 58 |
"layers.1.attention_norm2.weight": "0.safetensors",
|
| 59 |
"layers.1.ffn_norm2.weight": "0.safetensors",
|
| 60 |
"layers.1.adaln_modulation.weight": "0.safetensors",
|
| 61 |
-
"layers.1.adaln_modulation.
|
|
|
|
| 62 |
"layers.1.adaln_modulation.bias": "0.safetensors",
|
| 63 |
"layers.2.attention.qkv.weight": "0.safetensors",
|
| 64 |
-
"layers.2.attention.qkv.
|
|
|
|
| 65 |
"layers.2.attention.norm_q.weight": "0.safetensors",
|
| 66 |
"layers.2.attention.norm_k.weight": "0.safetensors",
|
| 67 |
"layers.2.attention.o.weight": "0.safetensors",
|
| 68 |
-
"layers.2.attention.o.
|
|
|
|
| 69 |
"layers.2.feed_forward.w1.weight": "0.safetensors",
|
| 70 |
-
"layers.2.feed_forward.w1.
|
|
|
|
| 71 |
"layers.2.feed_forward.w2.weight": "0.safetensors",
|
| 72 |
-
"layers.2.feed_forward.w2.
|
|
|
|
| 73 |
"layers.2.feed_forward.w3.weight": "0.safetensors",
|
| 74 |
-
"layers.2.feed_forward.w3.
|
|
|
|
| 75 |
"layers.2.attention_norm1.weight": "0.safetensors",
|
| 76 |
"layers.2.ffn_norm1.weight": "0.safetensors",
|
| 77 |
"layers.2.attention_norm2.weight": "0.safetensors",
|
| 78 |
"layers.2.ffn_norm2.weight": "0.safetensors",
|
| 79 |
"layers.2.adaln_modulation.weight": "0.safetensors",
|
| 80 |
-
"layers.2.adaln_modulation.
|
|
|
|
| 81 |
"layers.2.adaln_modulation.bias": "0.safetensors",
|
| 82 |
"layers.3.attention.qkv.weight": "0.safetensors",
|
| 83 |
-
"layers.3.attention.qkv.
|
|
|
|
| 84 |
"layers.3.attention.norm_q.weight": "0.safetensors",
|
| 85 |
"layers.3.attention.norm_k.weight": "0.safetensors",
|
| 86 |
"layers.3.attention.o.weight": "0.safetensors",
|
| 87 |
-
"layers.3.attention.o.
|
|
|
|
| 88 |
"layers.3.feed_forward.w1.weight": "0.safetensors",
|
| 89 |
-
"layers.3.feed_forward.w1.
|
|
|
|
| 90 |
"layers.3.feed_forward.w2.weight": "0.safetensors",
|
| 91 |
-
"layers.3.feed_forward.w2.
|
|
|
|
| 92 |
"layers.3.feed_forward.w3.weight": "0.safetensors",
|
| 93 |
-
"layers.3.feed_forward.w3.
|
|
|
|
| 94 |
"layers.3.attention_norm1.weight": "0.safetensors",
|
| 95 |
"layers.3.ffn_norm1.weight": "0.safetensors",
|
| 96 |
"layers.3.attention_norm2.weight": "0.safetensors",
|
| 97 |
"layers.3.ffn_norm2.weight": "0.safetensors",
|
| 98 |
"layers.3.adaln_modulation.weight": "0.safetensors",
|
| 99 |
-
"layers.3.adaln_modulation.
|
|
|
|
| 100 |
"layers.3.adaln_modulation.bias": "0.safetensors",
|
| 101 |
"layers.4.attention.qkv.weight": "0.safetensors",
|
| 102 |
-
"layers.4.attention.qkv.
|
|
|
|
| 103 |
"layers.4.attention.norm_q.weight": "0.safetensors",
|
| 104 |
"layers.4.attention.norm_k.weight": "0.safetensors",
|
| 105 |
"layers.4.attention.o.weight": "0.safetensors",
|
| 106 |
-
"layers.4.attention.o.
|
|
|
|
| 107 |
"layers.4.feed_forward.w1.weight": "0.safetensors",
|
| 108 |
-
"layers.4.feed_forward.w1.
|
|
|
|
| 109 |
"layers.4.feed_forward.w2.weight": "0.safetensors",
|
| 110 |
-
"layers.4.feed_forward.w2.
|
|
|
|
| 111 |
"layers.4.feed_forward.w3.weight": "0.safetensors",
|
| 112 |
-
"layers.4.feed_forward.w3.
|
|
|
|
| 113 |
"layers.4.attention_norm1.weight": "0.safetensors",
|
| 114 |
"layers.4.ffn_norm1.weight": "0.safetensors",
|
| 115 |
"layers.4.attention_norm2.weight": "0.safetensors",
|
| 116 |
"layers.4.ffn_norm2.weight": "0.safetensors",
|
| 117 |
"layers.4.adaln_modulation.weight": "0.safetensors",
|
| 118 |
-
"layers.4.adaln_modulation.
|
|
|
|
| 119 |
"layers.4.adaln_modulation.bias": "0.safetensors",
|
| 120 |
"layers.5.attention.qkv.weight": "0.safetensors",
|
| 121 |
-
"layers.5.attention.qkv.
|
|
|
|
| 122 |
"layers.5.attention.norm_q.weight": "0.safetensors",
|
| 123 |
"layers.5.attention.norm_k.weight": "0.safetensors",
|
| 124 |
"layers.5.attention.o.weight": "0.safetensors",
|
| 125 |
-
"layers.5.attention.o.
|
|
|
|
| 126 |
"layers.5.feed_forward.w1.weight": "0.safetensors",
|
| 127 |
-
"layers.5.feed_forward.w1.
|
|
|
|
| 128 |
"layers.5.feed_forward.w2.weight": "0.safetensors",
|
| 129 |
-
"layers.5.feed_forward.w2.
|
|
|
|
| 130 |
"layers.5.feed_forward.w3.weight": "0.safetensors",
|
| 131 |
-
"layers.5.feed_forward.w3.
|
|
|
|
| 132 |
"layers.5.attention_norm1.weight": "0.safetensors",
|
| 133 |
"layers.5.ffn_norm1.weight": "0.safetensors",
|
| 134 |
"layers.5.attention_norm2.weight": "0.safetensors",
|
| 135 |
"layers.5.ffn_norm2.weight": "0.safetensors",
|
| 136 |
"layers.5.adaln_modulation.weight": "0.safetensors",
|
| 137 |
-
"layers.5.adaln_modulation.
|
|
|
|
| 138 |
"layers.5.adaln_modulation.bias": "0.safetensors",
|
| 139 |
"layers.6.attention.qkv.weight": "0.safetensors",
|
| 140 |
-
"layers.6.attention.qkv.
|
|
|
|
| 141 |
"layers.6.attention.norm_q.weight": "0.safetensors",
|
| 142 |
"layers.6.attention.norm_k.weight": "0.safetensors",
|
| 143 |
"layers.6.attention.o.weight": "0.safetensors",
|
| 144 |
-
"layers.6.attention.o.
|
|
|
|
| 145 |
"layers.6.feed_forward.w1.weight": "0.safetensors",
|
| 146 |
-
"layers.6.feed_forward.w1.
|
|
|
|
| 147 |
"layers.6.feed_forward.w2.weight": "0.safetensors",
|
| 148 |
-
"layers.6.feed_forward.w2.
|
|
|
|
| 149 |
"layers.6.feed_forward.w3.weight": "0.safetensors",
|
| 150 |
-
"layers.6.feed_forward.w3.
|
|
|
|
| 151 |
"layers.6.attention_norm1.weight": "0.safetensors",
|
| 152 |
"layers.6.ffn_norm1.weight": "0.safetensors",
|
| 153 |
"layers.6.attention_norm2.weight": "0.safetensors",
|
| 154 |
"layers.6.ffn_norm2.weight": "0.safetensors",
|
| 155 |
"layers.6.adaln_modulation.weight": "0.safetensors",
|
| 156 |
-
"layers.6.adaln_modulation.
|
|
|
|
| 157 |
"layers.6.adaln_modulation.bias": "0.safetensors",
|
| 158 |
-
"layers.7.attention.qkv.weight": "
|
| 159 |
-
"layers.7.attention.qkv.
|
| 160 |
-
"layers.7.attention.
|
| 161 |
-
"layers.7.attention.
|
| 162 |
-
"layers.7.attention.
|
| 163 |
-
"layers.7.attention.o.
|
| 164 |
-
"layers.7.
|
| 165 |
-
"layers.7.
|
| 166 |
-
"layers.7.feed_forward.
|
| 167 |
-
"layers.7.feed_forward.
|
| 168 |
-
"layers.7.feed_forward.
|
| 169 |
-
"layers.7.feed_forward.
|
| 170 |
-
"layers.7.
|
| 171 |
-
"layers.7.
|
| 172 |
-
"layers.7.
|
| 173 |
-
"layers.7.
|
| 174 |
-
"layers.7.
|
| 175 |
-
"layers.7.
|
| 176 |
-
"layers.7.
|
| 177 |
-
"layers.
|
| 178 |
-
"layers.
|
| 179 |
-
"layers.
|
| 180 |
-
"layers.
|
| 181 |
-
"layers.
|
| 182 |
-
"layers.
|
| 183 |
-
"layers.8.
|
| 184 |
-
"layers.8.
|
| 185 |
-
"layers.8.
|
| 186 |
-
"layers.8.
|
| 187 |
-
"layers.8.
|
| 188 |
-
"layers.8.
|
| 189 |
-
"layers.8.
|
| 190 |
-
"layers.8.
|
| 191 |
-
"layers.8.
|
| 192 |
-
"layers.8.
|
| 193 |
-
"layers.8.
|
| 194 |
-
"layers.8.
|
| 195 |
-
"layers.8.
|
| 196 |
-
"layers.
|
| 197 |
-
"layers.
|
| 198 |
-
"layers.
|
| 199 |
-
"layers.
|
| 200 |
-
"layers.
|
| 201 |
-
"layers.
|
| 202 |
-
"layers.
|
| 203 |
-
"layers.
|
| 204 |
-
"layers.
|
| 205 |
-
"layers.
|
| 206 |
-
"layers.
|
| 207 |
-
"layers.
|
| 208 |
-
"layers.9.
|
| 209 |
-
"layers.9.
|
| 210 |
-
"layers.9.
|
| 211 |
-
"layers.9.
|
| 212 |
-
"layers.9.
|
| 213 |
-
"layers.9.
|
| 214 |
-
"layers.9.
|
| 215 |
-
"layers.
|
| 216 |
-
"layers.
|
| 217 |
-
"layers.
|
| 218 |
-
"layers.
|
| 219 |
-
"layers.
|
| 220 |
-
"layers.
|
| 221 |
-
"layers.
|
| 222 |
-
"layers.
|
| 223 |
-
"layers.
|
| 224 |
-
"layers.
|
| 225 |
-
"layers.
|
| 226 |
-
"layers.
|
| 227 |
-
"layers.
|
| 228 |
-
"layers.
|
| 229 |
-
"layers.
|
| 230 |
-
"layers.
|
| 231 |
-
"layers.
|
| 232 |
-
"layers.
|
| 233 |
-
"layers.10.
|
| 234 |
-
"layers.
|
| 235 |
-
"layers.
|
| 236 |
-
"layers.
|
| 237 |
-
"layers.
|
| 238 |
-
"layers.
|
| 239 |
-
"layers.
|
| 240 |
-
"layers.
|
| 241 |
-
"layers.
|
| 242 |
-
"layers.
|
| 243 |
-
"layers.
|
| 244 |
-
"layers.
|
| 245 |
-
"layers.
|
| 246 |
-
"layers.
|
| 247 |
-
"layers.
|
| 248 |
-
"layers.
|
| 249 |
-
"layers.
|
| 250 |
-
"layers.
|
| 251 |
-
"layers.
|
| 252 |
-
"layers.
|
| 253 |
-
"layers.
|
| 254 |
-
"layers.
|
| 255 |
-
"layers.
|
| 256 |
-
"layers.
|
| 257 |
-
"layers.
|
| 258 |
-
"layers.
|
| 259 |
-
"layers.
|
| 260 |
-
"layers.
|
| 261 |
-
"layers.
|
| 262 |
-
"layers.
|
| 263 |
-
"layers.
|
| 264 |
-
"layers.
|
| 265 |
-
"layers.
|
| 266 |
-
"layers.
|
| 267 |
-
"layers.
|
| 268 |
-
"layers.
|
| 269 |
-
"layers.
|
| 270 |
-
"layers.
|
| 271 |
-
"layers.
|
| 272 |
-
"layers.
|
| 273 |
-
"layers.
|
| 274 |
-
"layers.
|
| 275 |
-
"layers.
|
| 276 |
-
"layers.
|
| 277 |
-
"layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 278 |
"layers.13.feed_forward.w1.weight": "1.safetensors",
|
| 279 |
-
"layers.13.feed_forward.w1.
|
|
|
|
| 280 |
"layers.13.feed_forward.w2.weight": "1.safetensors",
|
| 281 |
-
"layers.13.feed_forward.w2.
|
|
|
|
| 282 |
"layers.13.feed_forward.w3.weight": "1.safetensors",
|
| 283 |
-
"layers.13.feed_forward.w3.
|
|
|
|
| 284 |
"layers.13.attention_norm1.weight": "1.safetensors",
|
| 285 |
"layers.13.ffn_norm1.weight": "1.safetensors",
|
| 286 |
"layers.13.attention_norm2.weight": "1.safetensors",
|
| 287 |
"layers.13.ffn_norm2.weight": "1.safetensors",
|
| 288 |
"layers.13.adaln_modulation.weight": "1.safetensors",
|
| 289 |
-
"layers.13.adaln_modulation.
|
|
|
|
| 290 |
"layers.13.adaln_modulation.bias": "1.safetensors",
|
| 291 |
"layers.14.attention.qkv.weight": "1.safetensors",
|
| 292 |
-
"layers.14.attention.qkv.
|
|
|
|
| 293 |
"layers.14.attention.norm_q.weight": "1.safetensors",
|
| 294 |
"layers.14.attention.norm_k.weight": "1.safetensors",
|
| 295 |
"layers.14.attention.o.weight": "1.safetensors",
|
| 296 |
-
"layers.14.attention.o.
|
|
|
|
| 297 |
"layers.14.feed_forward.w1.weight": "1.safetensors",
|
| 298 |
-
"layers.14.feed_forward.w1.
|
|
|
|
| 299 |
"layers.14.feed_forward.w2.weight": "1.safetensors",
|
| 300 |
-
"layers.14.feed_forward.w2.
|
|
|
|
| 301 |
"layers.14.feed_forward.w3.weight": "1.safetensors",
|
| 302 |
-
"layers.14.feed_forward.w3.
|
|
|
|
| 303 |
"layers.14.attention_norm1.weight": "1.safetensors",
|
| 304 |
"layers.14.ffn_norm1.weight": "1.safetensors",
|
| 305 |
"layers.14.attention_norm2.weight": "1.safetensors",
|
| 306 |
"layers.14.ffn_norm2.weight": "1.safetensors",
|
| 307 |
"layers.14.adaln_modulation.weight": "1.safetensors",
|
| 308 |
-
"layers.14.adaln_modulation.
|
|
|
|
| 309 |
"layers.14.adaln_modulation.bias": "1.safetensors",
|
| 310 |
-
"layers.15.attention.qkv.weight": "
|
| 311 |
-
"layers.15.attention.qkv.
|
| 312 |
-
"layers.15.attention.
|
| 313 |
-
"layers.15.attention.
|
| 314 |
-
"layers.15.attention.
|
| 315 |
-
"layers.15.attention.o.
|
| 316 |
-
"layers.15.
|
| 317 |
-
"layers.15.
|
| 318 |
-
"layers.15.feed_forward.
|
| 319 |
-
"layers.15.feed_forward.
|
| 320 |
-
"layers.15.feed_forward.
|
| 321 |
-
"layers.15.feed_forward.
|
| 322 |
-
"layers.15.
|
| 323 |
-
"layers.15.
|
| 324 |
-
"layers.15.
|
| 325 |
-
"layers.15.
|
| 326 |
-
"layers.15.
|
| 327 |
-
"layers.15.
|
| 328 |
-
"layers.15.
|
| 329 |
-
"layers.
|
| 330 |
-
"layers.
|
| 331 |
-
"layers.
|
| 332 |
-
"layers.
|
| 333 |
-
"layers.
|
| 334 |
-
"layers.
|
| 335 |
-
"layers.16.
|
| 336 |
-
"layers.16.
|
| 337 |
-
"layers.16.
|
| 338 |
-
"layers.16.
|
| 339 |
-
"layers.16.
|
| 340 |
-
"layers.16.
|
| 341 |
-
"layers.16.
|
| 342 |
-
"layers.16.
|
| 343 |
-
"layers.16.
|
| 344 |
-
"layers.16.
|
| 345 |
-
"layers.16.
|
| 346 |
-
"layers.16.
|
| 347 |
-
"layers.16.
|
| 348 |
-
"layers.
|
| 349 |
-
"layers.
|
| 350 |
-
"layers.
|
| 351 |
-
"layers.
|
| 352 |
-
"layers.
|
| 353 |
-
"layers.
|
| 354 |
-
"layers.
|
| 355 |
-
"layers.
|
| 356 |
-
"layers.
|
| 357 |
-
"layers.
|
| 358 |
-
"layers.
|
| 359 |
-
"layers.
|
| 360 |
-
"layers.17.
|
| 361 |
-
"layers.17.
|
| 362 |
-
"layers.17.
|
| 363 |
-
"layers.17.
|
| 364 |
-
"layers.17.
|
| 365 |
-
"layers.17.
|
| 366 |
-
"layers.17.
|
| 367 |
-
"layers.
|
| 368 |
-
"layers.
|
| 369 |
-
"layers.
|
| 370 |
-
"layers.
|
| 371 |
-
"layers.
|
| 372 |
-
"layers.
|
| 373 |
-
"layers.
|
| 374 |
-
"layers.
|
| 375 |
-
"layers.
|
| 376 |
-
"layers.
|
| 377 |
-
"layers.
|
| 378 |
-
"layers.
|
| 379 |
-
"layers.
|
| 380 |
-
"layers.
|
| 381 |
-
"layers.
|
| 382 |
-
"layers.
|
| 383 |
-
"layers.
|
| 384 |
-
"layers.
|
| 385 |
-
"layers.18.
|
| 386 |
-
"layers.
|
| 387 |
-
"layers.
|
| 388 |
-
"layers.
|
| 389 |
-
"layers.
|
| 390 |
-
"layers.
|
| 391 |
-
"layers.
|
| 392 |
-
"layers.
|
| 393 |
-
"layers.
|
| 394 |
-
"layers.
|
| 395 |
-
"layers.
|
| 396 |
-
"layers.
|
| 397 |
-
"layers.
|
| 398 |
-
"layers.
|
| 399 |
-
"layers.
|
| 400 |
-
"layers.
|
| 401 |
-
"layers.
|
| 402 |
-
"layers.
|
| 403 |
-
"layers.
|
| 404 |
-
"layers.
|
| 405 |
-
"layers.
|
| 406 |
-
"layers.
|
| 407 |
-
"layers.
|
| 408 |
-
"layers.
|
| 409 |
-
"layers.
|
| 410 |
-
"layers.
|
| 411 |
-
"layers.
|
| 412 |
-
"layers.
|
| 413 |
-
"layers.
|
| 414 |
-
"layers.
|
| 415 |
-
"layers.
|
| 416 |
-
"layers.
|
| 417 |
-
"layers.
|
| 418 |
-
"layers.
|
| 419 |
-
"layers.
|
| 420 |
-
"layers.
|
| 421 |
-
"layers.
|
| 422 |
-
"layers.
|
| 423 |
-
"layers.
|
| 424 |
-
"layers.
|
| 425 |
-
"layers.
|
| 426 |
-
"layers.
|
| 427 |
-
"layers.
|
| 428 |
-
"layers.
|
| 429 |
-
"layers.
|
| 430 |
-
"layers.
|
| 431 |
-
"layers.
|
| 432 |
-
"layers.
|
| 433 |
-
"layers.
|
| 434 |
-
"layers.
|
| 435 |
-
"layers.
|
| 436 |
-
"layers.
|
| 437 |
-
"layers.
|
| 438 |
-
"layers.
|
| 439 |
-
"layers.
|
| 440 |
-
"layers.
|
| 441 |
-
"layers.
|
| 442 |
-
"layers.
|
| 443 |
-
"layers.
|
| 444 |
-
"layers.
|
| 445 |
-
"layers.
|
| 446 |
-
"layers.
|
| 447 |
-
"layers.
|
| 448 |
-
"layers.
|
| 449 |
-
"layers.
|
| 450 |
-
"layers.
|
| 451 |
-
"layers.
|
| 452 |
-
"layers.
|
| 453 |
-
"layers.
|
| 454 |
-
"layers.
|
| 455 |
-
"layers.
|
| 456 |
-
"layers.
|
| 457 |
-
"layers.
|
| 458 |
-
"layers.
|
| 459 |
-
"layers.
|
| 460 |
-
"layers.
|
| 461 |
-
"layers.
|
| 462 |
-
"layers.
|
| 463 |
-
"layers.
|
| 464 |
-
"layers.
|
| 465 |
-
"layers.
|
| 466 |
-
"layers.
|
| 467 |
-
"layers.
|
| 468 |
-
"layers.
|
| 469 |
-
"layers.
|
| 470 |
-
"layers.
|
| 471 |
-
"layers.
|
| 472 |
-
"layers.
|
| 473 |
-
"layers.
|
| 474 |
-
"layers.
|
| 475 |
-
"layers.
|
| 476 |
-
"layers.
|
| 477 |
-
"layers.
|
| 478 |
-
"layers.
|
| 479 |
-
"layers.
|
| 480 |
-
"layers.
|
| 481 |
-
"layers.
|
| 482 |
-
"layers.
|
| 483 |
-
"layers.
|
| 484 |
-
"layers.
|
| 485 |
-
"layers.
|
| 486 |
-
"layers.
|
| 487 |
-
"layers.
|
| 488 |
-
"layers.
|
| 489 |
-
"layers.
|
| 490 |
-
"layers.
|
| 491 |
-
"layers.
|
| 492 |
-
"layers.
|
| 493 |
-
"layers.
|
| 494 |
-
"layers.
|
| 495 |
-
"layers.
|
| 496 |
-
"layers.
|
| 497 |
-
"layers.
|
| 498 |
-
"layers.
|
| 499 |
-
"layers.
|
| 500 |
-
"layers.
|
| 501 |
-
"layers.
|
| 502 |
-
"layers.
|
| 503 |
-
"layers.
|
| 504 |
-
"layers.
|
| 505 |
-
"layers.
|
| 506 |
-
"layers.
|
| 507 |
-
"layers.
|
| 508 |
-
"layers.
|
| 509 |
-
"layers.
|
| 510 |
-
"layers.
|
| 511 |
-
"layers.
|
| 512 |
-
"layers.
|
| 513 |
-
"layers.
|
| 514 |
-
"layers.
|
| 515 |
-
"layers.
|
| 516 |
-
"layers.
|
| 517 |
-
"layers.
|
| 518 |
-
"layers.
|
| 519 |
-
"layers.
|
| 520 |
-
"layers.
|
| 521 |
-
"layers.
|
| 522 |
-
"layers.
|
| 523 |
-
"layers.
|
| 524 |
-
"layers.
|
| 525 |
-
"layers.
|
| 526 |
-
"layers.
|
| 527 |
-
"layers.
|
| 528 |
-
"layers.
|
| 529 |
-
"layers.
|
| 530 |
-
"layers.
|
| 531 |
-
"layers.
|
| 532 |
-
"layers.
|
| 533 |
-
"layers.
|
| 534 |
-
"layers.
|
| 535 |
-
"layers.
|
| 536 |
-
"layers.
|
| 537 |
-
"layers.
|
| 538 |
-
"layers.
|
| 539 |
-
"layers.
|
| 540 |
-
"layers.
|
| 541 |
-
"layers.
|
| 542 |
-
"layers.
|
| 543 |
-
"layers.
|
| 544 |
-
"layers.
|
| 545 |
-
"layers.
|
| 546 |
-
"layers.
|
| 547 |
-
"layers.
|
| 548 |
-
"layers.
|
| 549 |
-
"layers.
|
| 550 |
-
"layers.
|
| 551 |
-
"layers.
|
| 552 |
-
"layers.
|
| 553 |
-
"layers.
|
| 554 |
-
"layers.
|
| 555 |
-
"layers.
|
| 556 |
-
"layers.
|
| 557 |
-
"layers.
|
| 558 |
-
"layers.
|
| 559 |
-
"layers.
|
| 560 |
-
"layers.
|
| 561 |
-
"layers.
|
| 562 |
-
"layers.
|
| 563 |
-
"layers.
|
| 564 |
-
"layers.
|
| 565 |
-
"layers.
|
| 566 |
-
"layers.
|
| 567 |
-
"layers.
|
| 568 |
-
"layers.
|
| 569 |
-
"layers.
|
| 570 |
-
"layers.
|
| 571 |
-
"layers.
|
| 572 |
-
"layers.
|
| 573 |
-
"layers.
|
| 574 |
-
"layers.
|
| 575 |
-
"layers.
|
| 576 |
-
"layers.
|
| 577 |
-
"layers.
|
| 578 |
-
"layers.
|
| 579 |
-
"layers.
|
| 580 |
-
"layers.
|
| 581 |
-
"layers.
|
| 582 |
-
"layers.
|
| 583 |
-
"layers.
|
| 584 |
-
"layers.
|
| 585 |
-
"layers.
|
| 586 |
-
"layers.
|
| 587 |
-
"layers.
|
| 588 |
-
"layers.
|
| 589 |
-
"layers.
|
| 590 |
-
"layers.
|
| 591 |
-
"layers.
|
| 592 |
-
"layers.
|
| 593 |
-
"layers.
|
| 594 |
-
"layers.
|
| 595 |
-
"layers.
|
| 596 |
-
"layers.
|
| 597 |
-
"layers.
|
| 598 |
-
"layers.
|
| 599 |
-
"layers.
|
| 600 |
-
"layers.
|
| 601 |
-
"layers.
|
| 602 |
-
"layers.
|
| 603 |
-
"layers.
|
| 604 |
-
"layers.
|
| 605 |
-
"layers.
|
| 606 |
-
"layers.
|
| 607 |
-
"layers.
|
| 608 |
-
"layers.
|
| 609 |
-
"layers.
|
| 610 |
-
"layers.
|
| 611 |
-
"layers.
|
| 612 |
-
"layers.
|
| 613 |
-
"layers.
|
| 614 |
-
"layers.
|
| 615 |
-
"layers.
|
| 616 |
-
"layers.
|
| 617 |
-
"layers.
|
| 618 |
-
"layers.
|
| 619 |
-
"layers.
|
| 620 |
-
"layers.
|
| 621 |
-
"layers.
|
| 622 |
-
"layers.
|
| 623 |
-
"layers.
|
| 624 |
-
"layers.
|
| 625 |
-
"layers.
|
| 626 |
-
"layers.
|
| 627 |
-
"layers.
|
| 628 |
-
"layers.
|
| 629 |
-
"layers.
|
| 630 |
-
"layers.
|
| 631 |
-
"layers.
|
| 632 |
-
"layers.
|
| 633 |
-
"layers.
|
| 634 |
-
"layers.
|
| 635 |
-
"layers.
|
| 636 |
-
"layers.
|
| 637 |
-
"layers.
|
| 638 |
-
"layers.
|
| 639 |
-
"layers.
|
| 640 |
-
"layers.
|
| 641 |
-
"layers.
|
| 642 |
-
"layers.
|
| 643 |
-
"layers.
|
| 644 |
-
"layers.
|
| 645 |
-
"layers.
|
| 646 |
-
"layers.
|
| 647 |
-
"layers.
|
| 648 |
-
"layers.
|
| 649 |
-
"layers.
|
| 650 |
-
"layers.
|
| 651 |
-
"layers.
|
| 652 |
-
"layers.
|
| 653 |
-
"layers.
|
| 654 |
-
"layers.
|
| 655 |
-
"layers.
|
| 656 |
-
"layers.
|
| 657 |
-
"layers.
|
| 658 |
-
"layers.
|
| 659 |
-
"layers.
|
| 660 |
-
"layers.
|
| 661 |
-
"layers.
|
| 662 |
-
"layers.
|
| 663 |
-
"layers.
|
| 664 |
-
"layers.
|
| 665 |
-
"layers.
|
| 666 |
-
"layers.
|
| 667 |
-
"layers.
|
| 668 |
-
"layers.
|
| 669 |
-
"layers.
|
| 670 |
-
"layers.
|
| 671 |
-
"
|
| 672 |
-
"
|
| 673 |
-
"
|
| 674 |
-
"
|
| 675 |
-
"
|
| 676 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 677 |
}
|
| 678 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"quantization_level": "4",
|
| 4 |
+
"mflux_version": "0.20.0"
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"input_proj.weight": "0.safetensors",
|
| 8 |
+
"input_proj.scales": "0.safetensors",
|
| 9 |
+
"input_proj.biases": "0.safetensors",
|
| 10 |
"input_proj.bias": "0.safetensors",
|
| 11 |
"llm_cond_norm.weight": "0.safetensors",
|
| 12 |
"llm_cond_proj.weight": "0.safetensors",
|
| 13 |
+
"llm_cond_proj.scales": "0.safetensors",
|
| 14 |
+
"llm_cond_proj.biases": "0.safetensors",
|
| 15 |
"llm_cond_proj.bias": "0.safetensors",
|
| 16 |
"t_embedding.mlp_in.weight": "0.safetensors",
|
| 17 |
+
"t_embedding.mlp_in.scales": "0.safetensors",
|
| 18 |
+
"t_embedding.mlp_in.biases": "0.safetensors",
|
| 19 |
"t_embedding.mlp_in.bias": "0.safetensors",
|
| 20 |
"t_embedding.mlp_out.weight": "0.safetensors",
|
| 21 |
+
"t_embedding.mlp_out.scales": "0.safetensors",
|
| 22 |
+
"t_embedding.mlp_out.biases": "0.safetensors",
|
| 23 |
"t_embedding.mlp_out.bias": "0.safetensors",
|
| 24 |
"adaln_proj.weight": "0.safetensors",
|
| 25 |
+
"adaln_proj.scales": "0.safetensors",
|
| 26 |
+
"adaln_proj.biases": "0.safetensors",
|
| 27 |
"adaln_proj.bias": "0.safetensors",
|
| 28 |
"embed_image_indicator.weight": "0.safetensors",
|
| 29 |
+
"embed_image_indicator.scales": "0.safetensors",
|
| 30 |
+
"embed_image_indicator.biases": "0.safetensors",
|
| 31 |
"rotary_emb.inv_freq": "0.safetensors",
|
| 32 |
"layers.0.attention.qkv.weight": "0.safetensors",
|
| 33 |
+
"layers.0.attention.qkv.scales": "0.safetensors",
|
| 34 |
+
"layers.0.attention.qkv.biases": "0.safetensors",
|
| 35 |
"layers.0.attention.norm_q.weight": "0.safetensors",
|
| 36 |
"layers.0.attention.norm_k.weight": "0.safetensors",
|
| 37 |
"layers.0.attention.o.weight": "0.safetensors",
|
| 38 |
+
"layers.0.attention.o.scales": "0.safetensors",
|
| 39 |
+
"layers.0.attention.o.biases": "0.safetensors",
|
| 40 |
"layers.0.feed_forward.w1.weight": "0.safetensors",
|
| 41 |
+
"layers.0.feed_forward.w1.scales": "0.safetensors",
|
| 42 |
+
"layers.0.feed_forward.w1.biases": "0.safetensors",
|
| 43 |
"layers.0.feed_forward.w2.weight": "0.safetensors",
|
| 44 |
+
"layers.0.feed_forward.w2.scales": "0.safetensors",
|
| 45 |
+
"layers.0.feed_forward.w2.biases": "0.safetensors",
|
| 46 |
"layers.0.feed_forward.w3.weight": "0.safetensors",
|
| 47 |
+
"layers.0.feed_forward.w3.scales": "0.safetensors",
|
| 48 |
+
"layers.0.feed_forward.w3.biases": "0.safetensors",
|
| 49 |
"layers.0.attention_norm1.weight": "0.safetensors",
|
| 50 |
"layers.0.ffn_norm1.weight": "0.safetensors",
|
| 51 |
"layers.0.attention_norm2.weight": "0.safetensors",
|
| 52 |
"layers.0.ffn_norm2.weight": "0.safetensors",
|
| 53 |
"layers.0.adaln_modulation.weight": "0.safetensors",
|
| 54 |
+
"layers.0.adaln_modulation.scales": "0.safetensors",
|
| 55 |
+
"layers.0.adaln_modulation.biases": "0.safetensors",
|
| 56 |
"layers.0.adaln_modulation.bias": "0.safetensors",
|
| 57 |
"layers.1.attention.qkv.weight": "0.safetensors",
|
| 58 |
+
"layers.1.attention.qkv.scales": "0.safetensors",
|
| 59 |
+
"layers.1.attention.qkv.biases": "0.safetensors",
|
| 60 |
"layers.1.attention.norm_q.weight": "0.safetensors",
|
| 61 |
"layers.1.attention.norm_k.weight": "0.safetensors",
|
| 62 |
"layers.1.attention.o.weight": "0.safetensors",
|
| 63 |
+
"layers.1.attention.o.scales": "0.safetensors",
|
| 64 |
+
"layers.1.attention.o.biases": "0.safetensors",
|
| 65 |
"layers.1.feed_forward.w1.weight": "0.safetensors",
|
| 66 |
+
"layers.1.feed_forward.w1.scales": "0.safetensors",
|
| 67 |
+
"layers.1.feed_forward.w1.biases": "0.safetensors",
|
| 68 |
"layers.1.feed_forward.w2.weight": "0.safetensors",
|
| 69 |
+
"layers.1.feed_forward.w2.scales": "0.safetensors",
|
| 70 |
+
"layers.1.feed_forward.w2.biases": "0.safetensors",
|
| 71 |
"layers.1.feed_forward.w3.weight": "0.safetensors",
|
| 72 |
+
"layers.1.feed_forward.w3.scales": "0.safetensors",
|
| 73 |
+
"layers.1.feed_forward.w3.biases": "0.safetensors",
|
| 74 |
"layers.1.attention_norm1.weight": "0.safetensors",
|
| 75 |
"layers.1.ffn_norm1.weight": "0.safetensors",
|
| 76 |
"layers.1.attention_norm2.weight": "0.safetensors",
|
| 77 |
"layers.1.ffn_norm2.weight": "0.safetensors",
|
| 78 |
"layers.1.adaln_modulation.weight": "0.safetensors",
|
| 79 |
+
"layers.1.adaln_modulation.scales": "0.safetensors",
|
| 80 |
+
"layers.1.adaln_modulation.biases": "0.safetensors",
|
| 81 |
"layers.1.adaln_modulation.bias": "0.safetensors",
|
| 82 |
"layers.2.attention.qkv.weight": "0.safetensors",
|
| 83 |
+
"layers.2.attention.qkv.scales": "0.safetensors",
|
| 84 |
+
"layers.2.attention.qkv.biases": "0.safetensors",
|
| 85 |
"layers.2.attention.norm_q.weight": "0.safetensors",
|
| 86 |
"layers.2.attention.norm_k.weight": "0.safetensors",
|
| 87 |
"layers.2.attention.o.weight": "0.safetensors",
|
| 88 |
+
"layers.2.attention.o.scales": "0.safetensors",
|
| 89 |
+
"layers.2.attention.o.biases": "0.safetensors",
|
| 90 |
"layers.2.feed_forward.w1.weight": "0.safetensors",
|
| 91 |
+
"layers.2.feed_forward.w1.scales": "0.safetensors",
|
| 92 |
+
"layers.2.feed_forward.w1.biases": "0.safetensors",
|
| 93 |
"layers.2.feed_forward.w2.weight": "0.safetensors",
|
| 94 |
+
"layers.2.feed_forward.w2.scales": "0.safetensors",
|
| 95 |
+
"layers.2.feed_forward.w2.biases": "0.safetensors",
|
| 96 |
"layers.2.feed_forward.w3.weight": "0.safetensors",
|
| 97 |
+
"layers.2.feed_forward.w3.scales": "0.safetensors",
|
| 98 |
+
"layers.2.feed_forward.w3.biases": "0.safetensors",
|
| 99 |
"layers.2.attention_norm1.weight": "0.safetensors",
|
| 100 |
"layers.2.ffn_norm1.weight": "0.safetensors",
|
| 101 |
"layers.2.attention_norm2.weight": "0.safetensors",
|
| 102 |
"layers.2.ffn_norm2.weight": "0.safetensors",
|
| 103 |
"layers.2.adaln_modulation.weight": "0.safetensors",
|
| 104 |
+
"layers.2.adaln_modulation.scales": "0.safetensors",
|
| 105 |
+
"layers.2.adaln_modulation.biases": "0.safetensors",
|
| 106 |
"layers.2.adaln_modulation.bias": "0.safetensors",
|
| 107 |
"layers.3.attention.qkv.weight": "0.safetensors",
|
| 108 |
+
"layers.3.attention.qkv.scales": "0.safetensors",
|
| 109 |
+
"layers.3.attention.qkv.biases": "0.safetensors",
|
| 110 |
"layers.3.attention.norm_q.weight": "0.safetensors",
|
| 111 |
"layers.3.attention.norm_k.weight": "0.safetensors",
|
| 112 |
"layers.3.attention.o.weight": "0.safetensors",
|
| 113 |
+
"layers.3.attention.o.scales": "0.safetensors",
|
| 114 |
+
"layers.3.attention.o.biases": "0.safetensors",
|
| 115 |
"layers.3.feed_forward.w1.weight": "0.safetensors",
|
| 116 |
+
"layers.3.feed_forward.w1.scales": "0.safetensors",
|
| 117 |
+
"layers.3.feed_forward.w1.biases": "0.safetensors",
|
| 118 |
"layers.3.feed_forward.w2.weight": "0.safetensors",
|
| 119 |
+
"layers.3.feed_forward.w2.scales": "0.safetensors",
|
| 120 |
+
"layers.3.feed_forward.w2.biases": "0.safetensors",
|
| 121 |
"layers.3.feed_forward.w3.weight": "0.safetensors",
|
| 122 |
+
"layers.3.feed_forward.w3.scales": "0.safetensors",
|
| 123 |
+
"layers.3.feed_forward.w3.biases": "0.safetensors",
|
| 124 |
"layers.3.attention_norm1.weight": "0.safetensors",
|
| 125 |
"layers.3.ffn_norm1.weight": "0.safetensors",
|
| 126 |
"layers.3.attention_norm2.weight": "0.safetensors",
|
| 127 |
"layers.3.ffn_norm2.weight": "0.safetensors",
|
| 128 |
"layers.3.adaln_modulation.weight": "0.safetensors",
|
| 129 |
+
"layers.3.adaln_modulation.scales": "0.safetensors",
|
| 130 |
+
"layers.3.adaln_modulation.biases": "0.safetensors",
|
| 131 |
"layers.3.adaln_modulation.bias": "0.safetensors",
|
| 132 |
"layers.4.attention.qkv.weight": "0.safetensors",
|
| 133 |
+
"layers.4.attention.qkv.scales": "0.safetensors",
|
| 134 |
+
"layers.4.attention.qkv.biases": "0.safetensors",
|
| 135 |
"layers.4.attention.norm_q.weight": "0.safetensors",
|
| 136 |
"layers.4.attention.norm_k.weight": "0.safetensors",
|
| 137 |
"layers.4.attention.o.weight": "0.safetensors",
|
| 138 |
+
"layers.4.attention.o.scales": "0.safetensors",
|
| 139 |
+
"layers.4.attention.o.biases": "0.safetensors",
|
| 140 |
"layers.4.feed_forward.w1.weight": "0.safetensors",
|
| 141 |
+
"layers.4.feed_forward.w1.scales": "0.safetensors",
|
| 142 |
+
"layers.4.feed_forward.w1.biases": "0.safetensors",
|
| 143 |
"layers.4.feed_forward.w2.weight": "0.safetensors",
|
| 144 |
+
"layers.4.feed_forward.w2.scales": "0.safetensors",
|
| 145 |
+
"layers.4.feed_forward.w2.biases": "0.safetensors",
|
| 146 |
"layers.4.feed_forward.w3.weight": "0.safetensors",
|
| 147 |
+
"layers.4.feed_forward.w3.scales": "0.safetensors",
|
| 148 |
+
"layers.4.feed_forward.w3.biases": "0.safetensors",
|
| 149 |
"layers.4.attention_norm1.weight": "0.safetensors",
|
| 150 |
"layers.4.ffn_norm1.weight": "0.safetensors",
|
| 151 |
"layers.4.attention_norm2.weight": "0.safetensors",
|
| 152 |
"layers.4.ffn_norm2.weight": "0.safetensors",
|
| 153 |
"layers.4.adaln_modulation.weight": "0.safetensors",
|
| 154 |
+
"layers.4.adaln_modulation.scales": "0.safetensors",
|
| 155 |
+
"layers.4.adaln_modulation.biases": "0.safetensors",
|
| 156 |
"layers.4.adaln_modulation.bias": "0.safetensors",
|
| 157 |
"layers.5.attention.qkv.weight": "0.safetensors",
|
| 158 |
+
"layers.5.attention.qkv.scales": "0.safetensors",
|
| 159 |
+
"layers.5.attention.qkv.biases": "0.safetensors",
|
| 160 |
"layers.5.attention.norm_q.weight": "0.safetensors",
|
| 161 |
"layers.5.attention.norm_k.weight": "0.safetensors",
|
| 162 |
"layers.5.attention.o.weight": "0.safetensors",
|
| 163 |
+
"layers.5.attention.o.scales": "0.safetensors",
|
| 164 |
+
"layers.5.attention.o.biases": "0.safetensors",
|
| 165 |
"layers.5.feed_forward.w1.weight": "0.safetensors",
|
| 166 |
+
"layers.5.feed_forward.w1.scales": "0.safetensors",
|
| 167 |
+
"layers.5.feed_forward.w1.biases": "0.safetensors",
|
| 168 |
"layers.5.feed_forward.w2.weight": "0.safetensors",
|
| 169 |
+
"layers.5.feed_forward.w2.scales": "0.safetensors",
|
| 170 |
+
"layers.5.feed_forward.w2.biases": "0.safetensors",
|
| 171 |
"layers.5.feed_forward.w3.weight": "0.safetensors",
|
| 172 |
+
"layers.5.feed_forward.w3.scales": "0.safetensors",
|
| 173 |
+
"layers.5.feed_forward.w3.biases": "0.safetensors",
|
| 174 |
"layers.5.attention_norm1.weight": "0.safetensors",
|
| 175 |
"layers.5.ffn_norm1.weight": "0.safetensors",
|
| 176 |
"layers.5.attention_norm2.weight": "0.safetensors",
|
| 177 |
"layers.5.ffn_norm2.weight": "0.safetensors",
|
| 178 |
"layers.5.adaln_modulation.weight": "0.safetensors",
|
| 179 |
+
"layers.5.adaln_modulation.scales": "0.safetensors",
|
| 180 |
+
"layers.5.adaln_modulation.biases": "0.safetensors",
|
| 181 |
"layers.5.adaln_modulation.bias": "0.safetensors",
|
| 182 |
"layers.6.attention.qkv.weight": "0.safetensors",
|
| 183 |
+
"layers.6.attention.qkv.scales": "0.safetensors",
|
| 184 |
+
"layers.6.attention.qkv.biases": "0.safetensors",
|
| 185 |
"layers.6.attention.norm_q.weight": "0.safetensors",
|
| 186 |
"layers.6.attention.norm_k.weight": "0.safetensors",
|
| 187 |
"layers.6.attention.o.weight": "0.safetensors",
|
| 188 |
+
"layers.6.attention.o.scales": "0.safetensors",
|
| 189 |
+
"layers.6.attention.o.biases": "0.safetensors",
|
| 190 |
"layers.6.feed_forward.w1.weight": "0.safetensors",
|
| 191 |
+
"layers.6.feed_forward.w1.scales": "0.safetensors",
|
| 192 |
+
"layers.6.feed_forward.w1.biases": "0.safetensors",
|
| 193 |
"layers.6.feed_forward.w2.weight": "0.safetensors",
|
| 194 |
+
"layers.6.feed_forward.w2.scales": "0.safetensors",
|
| 195 |
+
"layers.6.feed_forward.w2.biases": "0.safetensors",
|
| 196 |
"layers.6.feed_forward.w3.weight": "0.safetensors",
|
| 197 |
+
"layers.6.feed_forward.w3.scales": "0.safetensors",
|
| 198 |
+
"layers.6.feed_forward.w3.biases": "0.safetensors",
|
| 199 |
"layers.6.attention_norm1.weight": "0.safetensors",
|
| 200 |
"layers.6.ffn_norm1.weight": "0.safetensors",
|
| 201 |
"layers.6.attention_norm2.weight": "0.safetensors",
|
| 202 |
"layers.6.ffn_norm2.weight": "0.safetensors",
|
| 203 |
"layers.6.adaln_modulation.weight": "0.safetensors",
|
| 204 |
+
"layers.6.adaln_modulation.scales": "0.safetensors",
|
| 205 |
+
"layers.6.adaln_modulation.biases": "0.safetensors",
|
| 206 |
"layers.6.adaln_modulation.bias": "0.safetensors",
|
| 207 |
+
"layers.7.attention.qkv.weight": "0.safetensors",
|
| 208 |
+
"layers.7.attention.qkv.scales": "0.safetensors",
|
| 209 |
+
"layers.7.attention.qkv.biases": "0.safetensors",
|
| 210 |
+
"layers.7.attention.norm_q.weight": "0.safetensors",
|
| 211 |
+
"layers.7.attention.norm_k.weight": "0.safetensors",
|
| 212 |
+
"layers.7.attention.o.weight": "0.safetensors",
|
| 213 |
+
"layers.7.attention.o.scales": "0.safetensors",
|
| 214 |
+
"layers.7.attention.o.biases": "0.safetensors",
|
| 215 |
+
"layers.7.feed_forward.w1.weight": "0.safetensors",
|
| 216 |
+
"layers.7.feed_forward.w1.scales": "0.safetensors",
|
| 217 |
+
"layers.7.feed_forward.w1.biases": "0.safetensors",
|
| 218 |
+
"layers.7.feed_forward.w2.weight": "0.safetensors",
|
| 219 |
+
"layers.7.feed_forward.w2.scales": "0.safetensors",
|
| 220 |
+
"layers.7.feed_forward.w2.biases": "0.safetensors",
|
| 221 |
+
"layers.7.feed_forward.w3.weight": "0.safetensors",
|
| 222 |
+
"layers.7.feed_forward.w3.scales": "0.safetensors",
|
| 223 |
+
"layers.7.feed_forward.w3.biases": "0.safetensors",
|
| 224 |
+
"layers.7.attention_norm1.weight": "0.safetensors",
|
| 225 |
+
"layers.7.ffn_norm1.weight": "0.safetensors",
|
| 226 |
+
"layers.7.attention_norm2.weight": "0.safetensors",
|
| 227 |
+
"layers.7.ffn_norm2.weight": "0.safetensors",
|
| 228 |
+
"layers.7.adaln_modulation.weight": "0.safetensors",
|
| 229 |
+
"layers.7.adaln_modulation.scales": "0.safetensors",
|
| 230 |
+
"layers.7.adaln_modulation.biases": "0.safetensors",
|
| 231 |
+
"layers.7.adaln_modulation.bias": "0.safetensors",
|
| 232 |
+
"layers.8.attention.qkv.weight": "0.safetensors",
|
| 233 |
+
"layers.8.attention.qkv.scales": "0.safetensors",
|
| 234 |
+
"layers.8.attention.qkv.biases": "0.safetensors",
|
| 235 |
+
"layers.8.attention.norm_q.weight": "0.safetensors",
|
| 236 |
+
"layers.8.attention.norm_k.weight": "0.safetensors",
|
| 237 |
+
"layers.8.attention.o.weight": "0.safetensors",
|
| 238 |
+
"layers.8.attention.o.scales": "0.safetensors",
|
| 239 |
+
"layers.8.attention.o.biases": "0.safetensors",
|
| 240 |
+
"layers.8.feed_forward.w1.weight": "0.safetensors",
|
| 241 |
+
"layers.8.feed_forward.w1.scales": "0.safetensors",
|
| 242 |
+
"layers.8.feed_forward.w1.biases": "0.safetensors",
|
| 243 |
+
"layers.8.feed_forward.w2.weight": "0.safetensors",
|
| 244 |
+
"layers.8.feed_forward.w2.scales": "0.safetensors",
|
| 245 |
+
"layers.8.feed_forward.w2.biases": "0.safetensors",
|
| 246 |
+
"layers.8.feed_forward.w3.weight": "0.safetensors",
|
| 247 |
+
"layers.8.feed_forward.w3.scales": "0.safetensors",
|
| 248 |
+
"layers.8.feed_forward.w3.biases": "0.safetensors",
|
| 249 |
+
"layers.8.attention_norm1.weight": "0.safetensors",
|
| 250 |
+
"layers.8.ffn_norm1.weight": "0.safetensors",
|
| 251 |
+
"layers.8.attention_norm2.weight": "0.safetensors",
|
| 252 |
+
"layers.8.ffn_norm2.weight": "0.safetensors",
|
| 253 |
+
"layers.8.adaln_modulation.weight": "0.safetensors",
|
| 254 |
+
"layers.8.adaln_modulation.scales": "0.safetensors",
|
| 255 |
+
"layers.8.adaln_modulation.biases": "0.safetensors",
|
| 256 |
+
"layers.8.adaln_modulation.bias": "0.safetensors",
|
| 257 |
+
"layers.9.attention.qkv.weight": "0.safetensors",
|
| 258 |
+
"layers.9.attention.qkv.scales": "0.safetensors",
|
| 259 |
+
"layers.9.attention.qkv.biases": "0.safetensors",
|
| 260 |
+
"layers.9.attention.norm_q.weight": "0.safetensors",
|
| 261 |
+
"layers.9.attention.norm_k.weight": "0.safetensors",
|
| 262 |
+
"layers.9.attention.o.weight": "0.safetensors",
|
| 263 |
+
"layers.9.attention.o.scales": "0.safetensors",
|
| 264 |
+
"layers.9.attention.o.biases": "0.safetensors",
|
| 265 |
+
"layers.9.feed_forward.w1.weight": "0.safetensors",
|
| 266 |
+
"layers.9.feed_forward.w1.scales": "0.safetensors",
|
| 267 |
+
"layers.9.feed_forward.w1.biases": "0.safetensors",
|
| 268 |
+
"layers.9.feed_forward.w2.weight": "0.safetensors",
|
| 269 |
+
"layers.9.feed_forward.w2.scales": "0.safetensors",
|
| 270 |
+
"layers.9.feed_forward.w2.biases": "0.safetensors",
|
| 271 |
+
"layers.9.feed_forward.w3.weight": "0.safetensors",
|
| 272 |
+
"layers.9.feed_forward.w3.scales": "0.safetensors",
|
| 273 |
+
"layers.9.feed_forward.w3.biases": "0.safetensors",
|
| 274 |
+
"layers.9.attention_norm1.weight": "0.safetensors",
|
| 275 |
+
"layers.9.ffn_norm1.weight": "0.safetensors",
|
| 276 |
+
"layers.9.attention_norm2.weight": "0.safetensors",
|
| 277 |
+
"layers.9.ffn_norm2.weight": "0.safetensors",
|
| 278 |
+
"layers.9.adaln_modulation.weight": "0.safetensors",
|
| 279 |
+
"layers.9.adaln_modulation.scales": "0.safetensors",
|
| 280 |
+
"layers.9.adaln_modulation.biases": "0.safetensors",
|
| 281 |
+
"layers.9.adaln_modulation.bias": "0.safetensors",
|
| 282 |
+
"layers.10.attention.qkv.weight": "0.safetensors",
|
| 283 |
+
"layers.10.attention.qkv.scales": "0.safetensors",
|
| 284 |
+
"layers.10.attention.qkv.biases": "0.safetensors",
|
| 285 |
+
"layers.10.attention.norm_q.weight": "0.safetensors",
|
| 286 |
+
"layers.10.attention.norm_k.weight": "0.safetensors",
|
| 287 |
+
"layers.10.attention.o.weight": "0.safetensors",
|
| 288 |
+
"layers.10.attention.o.scales": "0.safetensors",
|
| 289 |
+
"layers.10.attention.o.biases": "0.safetensors",
|
| 290 |
+
"layers.10.feed_forward.w1.weight": "0.safetensors",
|
| 291 |
+
"layers.10.feed_forward.w1.scales": "0.safetensors",
|
| 292 |
+
"layers.10.feed_forward.w1.biases": "0.safetensors",
|
| 293 |
+
"layers.10.feed_forward.w2.weight": "0.safetensors",
|
| 294 |
+
"layers.10.feed_forward.w2.scales": "0.safetensors",
|
| 295 |
+
"layers.10.feed_forward.w2.biases": "0.safetensors",
|
| 296 |
+
"layers.10.feed_forward.w3.weight": "0.safetensors",
|
| 297 |
+
"layers.10.feed_forward.w3.scales": "0.safetensors",
|
| 298 |
+
"layers.10.feed_forward.w3.biases": "0.safetensors",
|
| 299 |
+
"layers.10.attention_norm1.weight": "0.safetensors",
|
| 300 |
+
"layers.10.ffn_norm1.weight": "0.safetensors",
|
| 301 |
+
"layers.10.attention_norm2.weight": "0.safetensors",
|
| 302 |
+
"layers.10.ffn_norm2.weight": "0.safetensors",
|
| 303 |
+
"layers.10.adaln_modulation.weight": "0.safetensors",
|
| 304 |
+
"layers.10.adaln_modulation.scales": "0.safetensors",
|
| 305 |
+
"layers.10.adaln_modulation.biases": "0.safetensors",
|
| 306 |
+
"layers.10.adaln_modulation.bias": "0.safetensors",
|
| 307 |
+
"layers.11.attention.qkv.weight": "0.safetensors",
|
| 308 |
+
"layers.11.attention.qkv.scales": "0.safetensors",
|
| 309 |
+
"layers.11.attention.qkv.biases": "0.safetensors",
|
| 310 |
+
"layers.11.attention.norm_q.weight": "0.safetensors",
|
| 311 |
+
"layers.11.attention.norm_k.weight": "0.safetensors",
|
| 312 |
+
"layers.11.attention.o.weight": "0.safetensors",
|
| 313 |
+
"layers.11.attention.o.scales": "0.safetensors",
|
| 314 |
+
"layers.11.attention.o.biases": "0.safetensors",
|
| 315 |
+
"layers.11.feed_forward.w1.weight": "0.safetensors",
|
| 316 |
+
"layers.11.feed_forward.w1.scales": "0.safetensors",
|
| 317 |
+
"layers.11.feed_forward.w1.biases": "0.safetensors",
|
| 318 |
+
"layers.11.feed_forward.w2.weight": "0.safetensors",
|
| 319 |
+
"layers.11.feed_forward.w2.scales": "0.safetensors",
|
| 320 |
+
"layers.11.feed_forward.w2.biases": "0.safetensors",
|
| 321 |
+
"layers.11.feed_forward.w3.weight": "0.safetensors",
|
| 322 |
+
"layers.11.feed_forward.w3.scales": "0.safetensors",
|
| 323 |
+
"layers.11.feed_forward.w3.biases": "0.safetensors",
|
| 324 |
+
"layers.11.attention_norm1.weight": "0.safetensors",
|
| 325 |
+
"layers.11.ffn_norm1.weight": "0.safetensors",
|
| 326 |
+
"layers.11.attention_norm2.weight": "0.safetensors",
|
| 327 |
+
"layers.11.ffn_norm2.weight": "0.safetensors",
|
| 328 |
+
"layers.11.adaln_modulation.weight": "0.safetensors",
|
| 329 |
+
"layers.11.adaln_modulation.scales": "0.safetensors",
|
| 330 |
+
"layers.11.adaln_modulation.biases": "0.safetensors",
|
| 331 |
+
"layers.11.adaln_modulation.bias": "0.safetensors",
|
| 332 |
+
"layers.12.attention.qkv.weight": "0.safetensors",
|
| 333 |
+
"layers.12.attention.qkv.scales": "0.safetensors",
|
| 334 |
+
"layers.12.attention.qkv.biases": "0.safetensors",
|
| 335 |
+
"layers.12.attention.norm_q.weight": "0.safetensors",
|
| 336 |
+
"layers.12.attention.norm_k.weight": "0.safetensors",
|
| 337 |
+
"layers.12.attention.o.weight": "0.safetensors",
|
| 338 |
+
"layers.12.attention.o.scales": "0.safetensors",
|
| 339 |
+
"layers.12.attention.o.biases": "0.safetensors",
|
| 340 |
+
"layers.12.feed_forward.w1.weight": "0.safetensors",
|
| 341 |
+
"layers.12.feed_forward.w1.scales": "0.safetensors",
|
| 342 |
+
"layers.12.feed_forward.w1.biases": "0.safetensors",
|
| 343 |
+
"layers.12.feed_forward.w2.weight": "0.safetensors",
|
| 344 |
+
"layers.12.feed_forward.w2.scales": "0.safetensors",
|
| 345 |
+
"layers.12.feed_forward.w2.biases": "0.safetensors",
|
| 346 |
+
"layers.12.feed_forward.w3.weight": "0.safetensors",
|
| 347 |
+
"layers.12.feed_forward.w3.scales": "0.safetensors",
|
| 348 |
+
"layers.12.feed_forward.w3.biases": "0.safetensors",
|
| 349 |
+
"layers.12.attention_norm1.weight": "0.safetensors",
|
| 350 |
+
"layers.12.ffn_norm1.weight": "0.safetensors",
|
| 351 |
+
"layers.12.attention_norm2.weight": "0.safetensors",
|
| 352 |
+
"layers.12.ffn_norm2.weight": "0.safetensors",
|
| 353 |
+
"layers.12.adaln_modulation.weight": "0.safetensors",
|
| 354 |
+
"layers.12.adaln_modulation.scales": "0.safetensors",
|
| 355 |
+
"layers.12.adaln_modulation.biases": "0.safetensors",
|
| 356 |
+
"layers.12.adaln_modulation.bias": "0.safetensors",
|
| 357 |
+
"layers.13.attention.qkv.weight": "0.safetensors",
|
| 358 |
+
"layers.13.attention.qkv.scales": "0.safetensors",
|
| 359 |
+
"layers.13.attention.qkv.biases": "0.safetensors",
|
| 360 |
+
"layers.13.attention.norm_q.weight": "0.safetensors",
|
| 361 |
+
"layers.13.attention.norm_k.weight": "0.safetensors",
|
| 362 |
+
"layers.13.attention.o.weight": "0.safetensors",
|
| 363 |
+
"layers.13.attention.o.scales": "0.safetensors",
|
| 364 |
+
"layers.13.attention.o.biases": "0.safetensors",
|
| 365 |
"layers.13.feed_forward.w1.weight": "1.safetensors",
|
| 366 |
+
"layers.13.feed_forward.w1.scales": "1.safetensors",
|
| 367 |
+
"layers.13.feed_forward.w1.biases": "1.safetensors",
|
| 368 |
"layers.13.feed_forward.w2.weight": "1.safetensors",
|
| 369 |
+
"layers.13.feed_forward.w2.scales": "1.safetensors",
|
| 370 |
+
"layers.13.feed_forward.w2.biases": "1.safetensors",
|
| 371 |
"layers.13.feed_forward.w3.weight": "1.safetensors",
|
| 372 |
+
"layers.13.feed_forward.w3.scales": "1.safetensors",
|
| 373 |
+
"layers.13.feed_forward.w3.biases": "1.safetensors",
|
| 374 |
"layers.13.attention_norm1.weight": "1.safetensors",
|
| 375 |
"layers.13.ffn_norm1.weight": "1.safetensors",
|
| 376 |
"layers.13.attention_norm2.weight": "1.safetensors",
|
| 377 |
"layers.13.ffn_norm2.weight": "1.safetensors",
|
| 378 |
"layers.13.adaln_modulation.weight": "1.safetensors",
|
| 379 |
+
"layers.13.adaln_modulation.scales": "1.safetensors",
|
| 380 |
+
"layers.13.adaln_modulation.biases": "1.safetensors",
|
| 381 |
"layers.13.adaln_modulation.bias": "1.safetensors",
|
| 382 |
"layers.14.attention.qkv.weight": "1.safetensors",
|
| 383 |
+
"layers.14.attention.qkv.scales": "1.safetensors",
|
| 384 |
+
"layers.14.attention.qkv.biases": "1.safetensors",
|
| 385 |
"layers.14.attention.norm_q.weight": "1.safetensors",
|
| 386 |
"layers.14.attention.norm_k.weight": "1.safetensors",
|
| 387 |
"layers.14.attention.o.weight": "1.safetensors",
|
| 388 |
+
"layers.14.attention.o.scales": "1.safetensors",
|
| 389 |
+
"layers.14.attention.o.biases": "1.safetensors",
|
| 390 |
"layers.14.feed_forward.w1.weight": "1.safetensors",
|
| 391 |
+
"layers.14.feed_forward.w1.scales": "1.safetensors",
|
| 392 |
+
"layers.14.feed_forward.w1.biases": "1.safetensors",
|
| 393 |
"layers.14.feed_forward.w2.weight": "1.safetensors",
|
| 394 |
+
"layers.14.feed_forward.w2.scales": "1.safetensors",
|
| 395 |
+
"layers.14.feed_forward.w2.biases": "1.safetensors",
|
| 396 |
"layers.14.feed_forward.w3.weight": "1.safetensors",
|
| 397 |
+
"layers.14.feed_forward.w3.scales": "1.safetensors",
|
| 398 |
+
"layers.14.feed_forward.w3.biases": "1.safetensors",
|
| 399 |
"layers.14.attention_norm1.weight": "1.safetensors",
|
| 400 |
"layers.14.ffn_norm1.weight": "1.safetensors",
|
| 401 |
"layers.14.attention_norm2.weight": "1.safetensors",
|
| 402 |
"layers.14.ffn_norm2.weight": "1.safetensors",
|
| 403 |
"layers.14.adaln_modulation.weight": "1.safetensors",
|
| 404 |
+
"layers.14.adaln_modulation.scales": "1.safetensors",
|
| 405 |
+
"layers.14.adaln_modulation.biases": "1.safetensors",
|
| 406 |
"layers.14.adaln_modulation.bias": "1.safetensors",
|
| 407 |
+
"layers.15.attention.qkv.weight": "1.safetensors",
|
| 408 |
+
"layers.15.attention.qkv.scales": "1.safetensors",
|
| 409 |
+
"layers.15.attention.qkv.biases": "1.safetensors",
|
| 410 |
+
"layers.15.attention.norm_q.weight": "1.safetensors",
|
| 411 |
+
"layers.15.attention.norm_k.weight": "1.safetensors",
|
| 412 |
+
"layers.15.attention.o.weight": "1.safetensors",
|
| 413 |
+
"layers.15.attention.o.scales": "1.safetensors",
|
| 414 |
+
"layers.15.attention.o.biases": "1.safetensors",
|
| 415 |
+
"layers.15.feed_forward.w1.weight": "1.safetensors",
|
| 416 |
+
"layers.15.feed_forward.w1.scales": "1.safetensors",
|
| 417 |
+
"layers.15.feed_forward.w1.biases": "1.safetensors",
|
| 418 |
+
"layers.15.feed_forward.w2.weight": "1.safetensors",
|
| 419 |
+
"layers.15.feed_forward.w2.scales": "1.safetensors",
|
| 420 |
+
"layers.15.feed_forward.w2.biases": "1.safetensors",
|
| 421 |
+
"layers.15.feed_forward.w3.weight": "1.safetensors",
|
| 422 |
+
"layers.15.feed_forward.w3.scales": "1.safetensors",
|
| 423 |
+
"layers.15.feed_forward.w3.biases": "1.safetensors",
|
| 424 |
+
"layers.15.attention_norm1.weight": "1.safetensors",
|
| 425 |
+
"layers.15.ffn_norm1.weight": "1.safetensors",
|
| 426 |
+
"layers.15.attention_norm2.weight": "1.safetensors",
|
| 427 |
+
"layers.15.ffn_norm2.weight": "1.safetensors",
|
| 428 |
+
"layers.15.adaln_modulation.weight": "1.safetensors",
|
| 429 |
+
"layers.15.adaln_modulation.scales": "1.safetensors",
|
| 430 |
+
"layers.15.adaln_modulation.biases": "1.safetensors",
|
| 431 |
+
"layers.15.adaln_modulation.bias": "1.safetensors",
|
| 432 |
+
"layers.16.attention.qkv.weight": "1.safetensors",
|
| 433 |
+
"layers.16.attention.qkv.scales": "1.safetensors",
|
| 434 |
+
"layers.16.attention.qkv.biases": "1.safetensors",
|
| 435 |
+
"layers.16.attention.norm_q.weight": "1.safetensors",
|
| 436 |
+
"layers.16.attention.norm_k.weight": "1.safetensors",
|
| 437 |
+
"layers.16.attention.o.weight": "1.safetensors",
|
| 438 |
+
"layers.16.attention.o.scales": "1.safetensors",
|
| 439 |
+
"layers.16.attention.o.biases": "1.safetensors",
|
| 440 |
+
"layers.16.feed_forward.w1.weight": "1.safetensors",
|
| 441 |
+
"layers.16.feed_forward.w1.scales": "1.safetensors",
|
| 442 |
+
"layers.16.feed_forward.w1.biases": "1.safetensors",
|
| 443 |
+
"layers.16.feed_forward.w2.weight": "1.safetensors",
|
| 444 |
+
"layers.16.feed_forward.w2.scales": "1.safetensors",
|
| 445 |
+
"layers.16.feed_forward.w2.biases": "1.safetensors",
|
| 446 |
+
"layers.16.feed_forward.w3.weight": "1.safetensors",
|
| 447 |
+
"layers.16.feed_forward.w3.scales": "1.safetensors",
|
| 448 |
+
"layers.16.feed_forward.w3.biases": "1.safetensors",
|
| 449 |
+
"layers.16.attention_norm1.weight": "1.safetensors",
|
| 450 |
+
"layers.16.ffn_norm1.weight": "1.safetensors",
|
| 451 |
+
"layers.16.attention_norm2.weight": "1.safetensors",
|
| 452 |
+
"layers.16.ffn_norm2.weight": "1.safetensors",
|
| 453 |
+
"layers.16.adaln_modulation.weight": "1.safetensors",
|
| 454 |
+
"layers.16.adaln_modulation.scales": "1.safetensors",
|
| 455 |
+
"layers.16.adaln_modulation.biases": "1.safetensors",
|
| 456 |
+
"layers.16.adaln_modulation.bias": "1.safetensors",
|
| 457 |
+
"layers.17.attention.qkv.weight": "1.safetensors",
|
| 458 |
+
"layers.17.attention.qkv.scales": "1.safetensors",
|
| 459 |
+
"layers.17.attention.qkv.biases": "1.safetensors",
|
| 460 |
+
"layers.17.attention.norm_q.weight": "1.safetensors",
|
| 461 |
+
"layers.17.attention.norm_k.weight": "1.safetensors",
|
| 462 |
+
"layers.17.attention.o.weight": "1.safetensors",
|
| 463 |
+
"layers.17.attention.o.scales": "1.safetensors",
|
| 464 |
+
"layers.17.attention.o.biases": "1.safetensors",
|
| 465 |
+
"layers.17.feed_forward.w1.weight": "1.safetensors",
|
| 466 |
+
"layers.17.feed_forward.w1.scales": "1.safetensors",
|
| 467 |
+
"layers.17.feed_forward.w1.biases": "1.safetensors",
|
| 468 |
+
"layers.17.feed_forward.w2.weight": "1.safetensors",
|
| 469 |
+
"layers.17.feed_forward.w2.scales": "1.safetensors",
|
| 470 |
+
"layers.17.feed_forward.w2.biases": "1.safetensors",
|
| 471 |
+
"layers.17.feed_forward.w3.weight": "1.safetensors",
|
| 472 |
+
"layers.17.feed_forward.w3.scales": "1.safetensors",
|
| 473 |
+
"layers.17.feed_forward.w3.biases": "1.safetensors",
|
| 474 |
+
"layers.17.attention_norm1.weight": "1.safetensors",
|
| 475 |
+
"layers.17.ffn_norm1.weight": "1.safetensors",
|
| 476 |
+
"layers.17.attention_norm2.weight": "1.safetensors",
|
| 477 |
+
"layers.17.ffn_norm2.weight": "1.safetensors",
|
| 478 |
+
"layers.17.adaln_modulation.weight": "1.safetensors",
|
| 479 |
+
"layers.17.adaln_modulation.scales": "1.safetensors",
|
| 480 |
+
"layers.17.adaln_modulation.biases": "1.safetensors",
|
| 481 |
+
"layers.17.adaln_modulation.bias": "1.safetensors",
|
| 482 |
+
"layers.18.attention.qkv.weight": "1.safetensors",
|
| 483 |
+
"layers.18.attention.qkv.scales": "1.safetensors",
|
| 484 |
+
"layers.18.attention.qkv.biases": "1.safetensors",
|
| 485 |
+
"layers.18.attention.norm_q.weight": "1.safetensors",
|
| 486 |
+
"layers.18.attention.norm_k.weight": "1.safetensors",
|
| 487 |
+
"layers.18.attention.o.weight": "1.safetensors",
|
| 488 |
+
"layers.18.attention.o.scales": "1.safetensors",
|
| 489 |
+
"layers.18.attention.o.biases": "1.safetensors",
|
| 490 |
+
"layers.18.feed_forward.w1.weight": "1.safetensors",
|
| 491 |
+
"layers.18.feed_forward.w1.scales": "1.safetensors",
|
| 492 |
+
"layers.18.feed_forward.w1.biases": "1.safetensors",
|
| 493 |
+
"layers.18.feed_forward.w2.weight": "1.safetensors",
|
| 494 |
+
"layers.18.feed_forward.w2.scales": "1.safetensors",
|
| 495 |
+
"layers.18.feed_forward.w2.biases": "1.safetensors",
|
| 496 |
+
"layers.18.feed_forward.w3.weight": "1.safetensors",
|
| 497 |
+
"layers.18.feed_forward.w3.scales": "1.safetensors",
|
| 498 |
+
"layers.18.feed_forward.w3.biases": "1.safetensors",
|
| 499 |
+
"layers.18.attention_norm1.weight": "1.safetensors",
|
| 500 |
+
"layers.18.ffn_norm1.weight": "1.safetensors",
|
| 501 |
+
"layers.18.attention_norm2.weight": "1.safetensors",
|
| 502 |
+
"layers.18.ffn_norm2.weight": "1.safetensors",
|
| 503 |
+
"layers.18.adaln_modulation.weight": "1.safetensors",
|
| 504 |
+
"layers.18.adaln_modulation.scales": "1.safetensors",
|
| 505 |
+
"layers.18.adaln_modulation.biases": "1.safetensors",
|
| 506 |
+
"layers.18.adaln_modulation.bias": "1.safetensors",
|
| 507 |
+
"layers.19.attention.qkv.weight": "1.safetensors",
|
| 508 |
+
"layers.19.attention.qkv.scales": "1.safetensors",
|
| 509 |
+
"layers.19.attention.qkv.biases": "1.safetensors",
|
| 510 |
+
"layers.19.attention.norm_q.weight": "1.safetensors",
|
| 511 |
+
"layers.19.attention.norm_k.weight": "1.safetensors",
|
| 512 |
+
"layers.19.attention.o.weight": "1.safetensors",
|
| 513 |
+
"layers.19.attention.o.scales": "1.safetensors",
|
| 514 |
+
"layers.19.attention.o.biases": "1.safetensors",
|
| 515 |
+
"layers.19.feed_forward.w1.weight": "1.safetensors",
|
| 516 |
+
"layers.19.feed_forward.w1.scales": "1.safetensors",
|
| 517 |
+
"layers.19.feed_forward.w1.biases": "1.safetensors",
|
| 518 |
+
"layers.19.feed_forward.w2.weight": "1.safetensors",
|
| 519 |
+
"layers.19.feed_forward.w2.scales": "1.safetensors",
|
| 520 |
+
"layers.19.feed_forward.w2.biases": "1.safetensors",
|
| 521 |
+
"layers.19.feed_forward.w3.weight": "1.safetensors",
|
| 522 |
+
"layers.19.feed_forward.w3.scales": "1.safetensors",
|
| 523 |
+
"layers.19.feed_forward.w3.biases": "1.safetensors",
|
| 524 |
+
"layers.19.attention_norm1.weight": "1.safetensors",
|
| 525 |
+
"layers.19.ffn_norm1.weight": "1.safetensors",
|
| 526 |
+
"layers.19.attention_norm2.weight": "1.safetensors",
|
| 527 |
+
"layers.19.ffn_norm2.weight": "1.safetensors",
|
| 528 |
+
"layers.19.adaln_modulation.weight": "1.safetensors",
|
| 529 |
+
"layers.19.adaln_modulation.scales": "1.safetensors",
|
| 530 |
+
"layers.19.adaln_modulation.biases": "1.safetensors",
|
| 531 |
+
"layers.19.adaln_modulation.bias": "1.safetensors",
|
| 532 |
+
"layers.20.attention.qkv.weight": "1.safetensors",
|
| 533 |
+
"layers.20.attention.qkv.scales": "1.safetensors",
|
| 534 |
+
"layers.20.attention.qkv.biases": "1.safetensors",
|
| 535 |
+
"layers.20.attention.norm_q.weight": "1.safetensors",
|
| 536 |
+
"layers.20.attention.norm_k.weight": "1.safetensors",
|
| 537 |
+
"layers.20.attention.o.weight": "1.safetensors",
|
| 538 |
+
"layers.20.attention.o.scales": "1.safetensors",
|
| 539 |
+
"layers.20.attention.o.biases": "1.safetensors",
|
| 540 |
+
"layers.20.feed_forward.w1.weight": "1.safetensors",
|
| 541 |
+
"layers.20.feed_forward.w1.scales": "1.safetensors",
|
| 542 |
+
"layers.20.feed_forward.w1.biases": "1.safetensors",
|
| 543 |
+
"layers.20.feed_forward.w2.weight": "1.safetensors",
|
| 544 |
+
"layers.20.feed_forward.w2.scales": "1.safetensors",
|
| 545 |
+
"layers.20.feed_forward.w2.biases": "1.safetensors",
|
| 546 |
+
"layers.20.feed_forward.w3.weight": "1.safetensors",
|
| 547 |
+
"layers.20.feed_forward.w3.scales": "1.safetensors",
|
| 548 |
+
"layers.20.feed_forward.w3.biases": "1.safetensors",
|
| 549 |
+
"layers.20.attention_norm1.weight": "1.safetensors",
|
| 550 |
+
"layers.20.ffn_norm1.weight": "1.safetensors",
|
| 551 |
+
"layers.20.attention_norm2.weight": "1.safetensors",
|
| 552 |
+
"layers.20.ffn_norm2.weight": "1.safetensors",
|
| 553 |
+
"layers.20.adaln_modulation.weight": "1.safetensors",
|
| 554 |
+
"layers.20.adaln_modulation.scales": "1.safetensors",
|
| 555 |
+
"layers.20.adaln_modulation.biases": "1.safetensors",
|
| 556 |
+
"layers.20.adaln_modulation.bias": "1.safetensors",
|
| 557 |
+
"layers.21.attention.qkv.weight": "1.safetensors",
|
| 558 |
+
"layers.21.attention.qkv.scales": "1.safetensors",
|
| 559 |
+
"layers.21.attention.qkv.biases": "1.safetensors",
|
| 560 |
+
"layers.21.attention.norm_q.weight": "1.safetensors",
|
| 561 |
+
"layers.21.attention.norm_k.weight": "1.safetensors",
|
| 562 |
+
"layers.21.attention.o.weight": "1.safetensors",
|
| 563 |
+
"layers.21.attention.o.scales": "1.safetensors",
|
| 564 |
+
"layers.21.attention.o.biases": "1.safetensors",
|
| 565 |
+
"layers.21.feed_forward.w1.weight": "1.safetensors",
|
| 566 |
+
"layers.21.feed_forward.w1.scales": "1.safetensors",
|
| 567 |
+
"layers.21.feed_forward.w1.biases": "1.safetensors",
|
| 568 |
+
"layers.21.feed_forward.w2.weight": "1.safetensors",
|
| 569 |
+
"layers.21.feed_forward.w2.scales": "1.safetensors",
|
| 570 |
+
"layers.21.feed_forward.w2.biases": "1.safetensors",
|
| 571 |
+
"layers.21.feed_forward.w3.weight": "1.safetensors",
|
| 572 |
+
"layers.21.feed_forward.w3.scales": "1.safetensors",
|
| 573 |
+
"layers.21.feed_forward.w3.biases": "1.safetensors",
|
| 574 |
+
"layers.21.attention_norm1.weight": "1.safetensors",
|
| 575 |
+
"layers.21.ffn_norm1.weight": "1.safetensors",
|
| 576 |
+
"layers.21.attention_norm2.weight": "1.safetensors",
|
| 577 |
+
"layers.21.ffn_norm2.weight": "1.safetensors",
|
| 578 |
+
"layers.21.adaln_modulation.weight": "1.safetensors",
|
| 579 |
+
"layers.21.adaln_modulation.scales": "1.safetensors",
|
| 580 |
+
"layers.21.adaln_modulation.biases": "1.safetensors",
|
| 581 |
+
"layers.21.adaln_modulation.bias": "1.safetensors",
|
| 582 |
+
"layers.22.attention.qkv.weight": "1.safetensors",
|
| 583 |
+
"layers.22.attention.qkv.scales": "1.safetensors",
|
| 584 |
+
"layers.22.attention.qkv.biases": "1.safetensors",
|
| 585 |
+
"layers.22.attention.norm_q.weight": "1.safetensors",
|
| 586 |
+
"layers.22.attention.norm_k.weight": "1.safetensors",
|
| 587 |
+
"layers.22.attention.o.weight": "1.safetensors",
|
| 588 |
+
"layers.22.attention.o.scales": "1.safetensors",
|
| 589 |
+
"layers.22.attention.o.biases": "1.safetensors",
|
| 590 |
+
"layers.22.feed_forward.w1.weight": "1.safetensors",
|
| 591 |
+
"layers.22.feed_forward.w1.scales": "1.safetensors",
|
| 592 |
+
"layers.22.feed_forward.w1.biases": "1.safetensors",
|
| 593 |
+
"layers.22.feed_forward.w2.weight": "1.safetensors",
|
| 594 |
+
"layers.22.feed_forward.w2.scales": "1.safetensors",
|
| 595 |
+
"layers.22.feed_forward.w2.biases": "1.safetensors",
|
| 596 |
+
"layers.22.feed_forward.w3.weight": "1.safetensors",
|
| 597 |
+
"layers.22.feed_forward.w3.scales": "1.safetensors",
|
| 598 |
+
"layers.22.feed_forward.w3.biases": "1.safetensors",
|
| 599 |
+
"layers.22.attention_norm1.weight": "1.safetensors",
|
| 600 |
+
"layers.22.ffn_norm1.weight": "1.safetensors",
|
| 601 |
+
"layers.22.attention_norm2.weight": "1.safetensors",
|
| 602 |
+
"layers.22.ffn_norm2.weight": "1.safetensors",
|
| 603 |
+
"layers.22.adaln_modulation.weight": "1.safetensors",
|
| 604 |
+
"layers.22.adaln_modulation.scales": "1.safetensors",
|
| 605 |
+
"layers.22.adaln_modulation.biases": "1.safetensors",
|
| 606 |
+
"layers.22.adaln_modulation.bias": "1.safetensors",
|
| 607 |
+
"layers.23.attention.qkv.weight": "1.safetensors",
|
| 608 |
+
"layers.23.attention.qkv.scales": "1.safetensors",
|
| 609 |
+
"layers.23.attention.qkv.biases": "1.safetensors",
|
| 610 |
+
"layers.23.attention.norm_q.weight": "1.safetensors",
|
| 611 |
+
"layers.23.attention.norm_k.weight": "1.safetensors",
|
| 612 |
+
"layers.23.attention.o.weight": "1.safetensors",
|
| 613 |
+
"layers.23.attention.o.scales": "1.safetensors",
|
| 614 |
+
"layers.23.attention.o.biases": "1.safetensors",
|
| 615 |
+
"layers.23.feed_forward.w1.weight": "1.safetensors",
|
| 616 |
+
"layers.23.feed_forward.w1.scales": "1.safetensors",
|
| 617 |
+
"layers.23.feed_forward.w1.biases": "1.safetensors",
|
| 618 |
+
"layers.23.feed_forward.w2.weight": "1.safetensors",
|
| 619 |
+
"layers.23.feed_forward.w2.scales": "1.safetensors",
|
| 620 |
+
"layers.23.feed_forward.w2.biases": "1.safetensors",
|
| 621 |
+
"layers.23.feed_forward.w3.weight": "1.safetensors",
|
| 622 |
+
"layers.23.feed_forward.w3.scales": "1.safetensors",
|
| 623 |
+
"layers.23.feed_forward.w3.biases": "1.safetensors",
|
| 624 |
+
"layers.23.attention_norm1.weight": "1.safetensors",
|
| 625 |
+
"layers.23.ffn_norm1.weight": "1.safetensors",
|
| 626 |
+
"layers.23.attention_norm2.weight": "1.safetensors",
|
| 627 |
+
"layers.23.ffn_norm2.weight": "1.safetensors",
|
| 628 |
+
"layers.23.adaln_modulation.weight": "1.safetensors",
|
| 629 |
+
"layers.23.adaln_modulation.scales": "1.safetensors",
|
| 630 |
+
"layers.23.adaln_modulation.biases": "1.safetensors",
|
| 631 |
+
"layers.23.adaln_modulation.bias": "1.safetensors",
|
| 632 |
+
"layers.24.attention.qkv.weight": "1.safetensors",
|
| 633 |
+
"layers.24.attention.qkv.scales": "1.safetensors",
|
| 634 |
+
"layers.24.attention.qkv.biases": "1.safetensors",
|
| 635 |
+
"layers.24.attention.norm_q.weight": "1.safetensors",
|
| 636 |
+
"layers.24.attention.norm_k.weight": "1.safetensors",
|
| 637 |
+
"layers.24.attention.o.weight": "1.safetensors",
|
| 638 |
+
"layers.24.attention.o.scales": "1.safetensors",
|
| 639 |
+
"layers.24.attention.o.biases": "1.safetensors",
|
| 640 |
+
"layers.24.feed_forward.w1.weight": "1.safetensors",
|
| 641 |
+
"layers.24.feed_forward.w1.scales": "1.safetensors",
|
| 642 |
+
"layers.24.feed_forward.w1.biases": "1.safetensors",
|
| 643 |
+
"layers.24.feed_forward.w2.weight": "1.safetensors",
|
| 644 |
+
"layers.24.feed_forward.w2.scales": "1.safetensors",
|
| 645 |
+
"layers.24.feed_forward.w2.biases": "1.safetensors",
|
| 646 |
+
"layers.24.feed_forward.w3.weight": "1.safetensors",
|
| 647 |
+
"layers.24.feed_forward.w3.scales": "1.safetensors",
|
| 648 |
+
"layers.24.feed_forward.w3.biases": "1.safetensors",
|
| 649 |
+
"layers.24.attention_norm1.weight": "1.safetensors",
|
| 650 |
+
"layers.24.ffn_norm1.weight": "1.safetensors",
|
| 651 |
+
"layers.24.attention_norm2.weight": "1.safetensors",
|
| 652 |
+
"layers.24.ffn_norm2.weight": "1.safetensors",
|
| 653 |
+
"layers.24.adaln_modulation.weight": "1.safetensors",
|
| 654 |
+
"layers.24.adaln_modulation.scales": "1.safetensors",
|
| 655 |
+
"layers.24.adaln_modulation.biases": "1.safetensors",
|
| 656 |
+
"layers.24.adaln_modulation.bias": "1.safetensors",
|
| 657 |
+
"layers.25.attention.qkv.weight": "1.safetensors",
|
| 658 |
+
"layers.25.attention.qkv.scales": "1.safetensors",
|
| 659 |
+
"layers.25.attention.qkv.biases": "1.safetensors",
|
| 660 |
+
"layers.25.attention.norm_q.weight": "1.safetensors",
|
| 661 |
+
"layers.25.attention.norm_k.weight": "1.safetensors",
|
| 662 |
+
"layers.25.attention.o.weight": "1.safetensors",
|
| 663 |
+
"layers.25.attention.o.scales": "1.safetensors",
|
| 664 |
+
"layers.25.attention.o.biases": "1.safetensors",
|
| 665 |
+
"layers.25.feed_forward.w1.weight": "1.safetensors",
|
| 666 |
+
"layers.25.feed_forward.w1.scales": "1.safetensors",
|
| 667 |
+
"layers.25.feed_forward.w1.biases": "1.safetensors",
|
| 668 |
+
"layers.25.feed_forward.w2.weight": "1.safetensors",
|
| 669 |
+
"layers.25.feed_forward.w2.scales": "1.safetensors",
|
| 670 |
+
"layers.25.feed_forward.w2.biases": "1.safetensors",
|
| 671 |
+
"layers.25.feed_forward.w3.weight": "1.safetensors",
|
| 672 |
+
"layers.25.feed_forward.w3.scales": "1.safetensors",
|
| 673 |
+
"layers.25.feed_forward.w3.biases": "1.safetensors",
|
| 674 |
+
"layers.25.attention_norm1.weight": "1.safetensors",
|
| 675 |
+
"layers.25.ffn_norm1.weight": "1.safetensors",
|
| 676 |
+
"layers.25.attention_norm2.weight": "1.safetensors",
|
| 677 |
+
"layers.25.ffn_norm2.weight": "1.safetensors",
|
| 678 |
+
"layers.25.adaln_modulation.weight": "1.safetensors",
|
| 679 |
+
"layers.25.adaln_modulation.scales": "1.safetensors",
|
| 680 |
+
"layers.25.adaln_modulation.biases": "1.safetensors",
|
| 681 |
+
"layers.25.adaln_modulation.bias": "1.safetensors",
|
| 682 |
+
"layers.26.attention.qkv.weight": "1.safetensors",
|
| 683 |
+
"layers.26.attention.qkv.scales": "1.safetensors",
|
| 684 |
+
"layers.26.attention.qkv.biases": "1.safetensors",
|
| 685 |
+
"layers.26.attention.norm_q.weight": "1.safetensors",
|
| 686 |
+
"layers.26.attention.norm_k.weight": "1.safetensors",
|
| 687 |
+
"layers.26.attention.o.weight": "1.safetensors",
|
| 688 |
+
"layers.26.attention.o.scales": "1.safetensors",
|
| 689 |
+
"layers.26.attention.o.biases": "1.safetensors",
|
| 690 |
+
"layers.26.feed_forward.w1.weight": "1.safetensors",
|
| 691 |
+
"layers.26.feed_forward.w1.scales": "1.safetensors",
|
| 692 |
+
"layers.26.feed_forward.w1.biases": "1.safetensors",
|
| 693 |
+
"layers.26.feed_forward.w2.weight": "1.safetensors",
|
| 694 |
+
"layers.26.feed_forward.w2.scales": "1.safetensors",
|
| 695 |
+
"layers.26.feed_forward.w2.biases": "1.safetensors",
|
| 696 |
+
"layers.26.feed_forward.w3.weight": "1.safetensors",
|
| 697 |
+
"layers.26.feed_forward.w3.scales": "1.safetensors",
|
| 698 |
+
"layers.26.feed_forward.w3.biases": "1.safetensors",
|
| 699 |
+
"layers.26.attention_norm1.weight": "1.safetensors",
|
| 700 |
+
"layers.26.ffn_norm1.weight": "1.safetensors",
|
| 701 |
+
"layers.26.attention_norm2.weight": "1.safetensors",
|
| 702 |
+
"layers.26.ffn_norm2.weight": "1.safetensors",
|
| 703 |
+
"layers.26.adaln_modulation.weight": "1.safetensors",
|
| 704 |
+
"layers.26.adaln_modulation.scales": "1.safetensors",
|
| 705 |
+
"layers.26.adaln_modulation.biases": "1.safetensors",
|
| 706 |
+
"layers.26.adaln_modulation.bias": "1.safetensors",
|
| 707 |
+
"layers.27.attention.qkv.weight": "1.safetensors",
|
| 708 |
+
"layers.27.attention.qkv.scales": "1.safetensors",
|
| 709 |
+
"layers.27.attention.qkv.biases": "1.safetensors",
|
| 710 |
+
"layers.27.attention.norm_q.weight": "1.safetensors",
|
| 711 |
+
"layers.27.attention.norm_k.weight": "1.safetensors",
|
| 712 |
+
"layers.27.attention.o.weight": "1.safetensors",
|
| 713 |
+
"layers.27.attention.o.scales": "1.safetensors",
|
| 714 |
+
"layers.27.attention.o.biases": "1.safetensors",
|
| 715 |
+
"layers.27.feed_forward.w1.weight": "1.safetensors",
|
| 716 |
+
"layers.27.feed_forward.w1.scales": "1.safetensors",
|
| 717 |
+
"layers.27.feed_forward.w1.biases": "1.safetensors",
|
| 718 |
+
"layers.27.feed_forward.w2.weight": "1.safetensors",
|
| 719 |
+
"layers.27.feed_forward.w2.scales": "1.safetensors",
|
| 720 |
+
"layers.27.feed_forward.w2.biases": "1.safetensors",
|
| 721 |
+
"layers.27.feed_forward.w3.weight": "2.safetensors",
|
| 722 |
+
"layers.27.feed_forward.w3.scales": "2.safetensors",
|
| 723 |
+
"layers.27.feed_forward.w3.biases": "2.safetensors",
|
| 724 |
+
"layers.27.attention_norm1.weight": "2.safetensors",
|
| 725 |
+
"layers.27.ffn_norm1.weight": "2.safetensors",
|
| 726 |
+
"layers.27.attention_norm2.weight": "2.safetensors",
|
| 727 |
+
"layers.27.ffn_norm2.weight": "2.safetensors",
|
| 728 |
+
"layers.27.adaln_modulation.weight": "2.safetensors",
|
| 729 |
+
"layers.27.adaln_modulation.scales": "2.safetensors",
|
| 730 |
+
"layers.27.adaln_modulation.biases": "2.safetensors",
|
| 731 |
+
"layers.27.adaln_modulation.bias": "2.safetensors",
|
| 732 |
+
"layers.28.attention.qkv.weight": "2.safetensors",
|
| 733 |
+
"layers.28.attention.qkv.scales": "2.safetensors",
|
| 734 |
+
"layers.28.attention.qkv.biases": "2.safetensors",
|
| 735 |
+
"layers.28.attention.norm_q.weight": "2.safetensors",
|
| 736 |
+
"layers.28.attention.norm_k.weight": "2.safetensors",
|
| 737 |
+
"layers.28.attention.o.weight": "2.safetensors",
|
| 738 |
+
"layers.28.attention.o.scales": "2.safetensors",
|
| 739 |
+
"layers.28.attention.o.biases": "2.safetensors",
|
| 740 |
+
"layers.28.feed_forward.w1.weight": "2.safetensors",
|
| 741 |
+
"layers.28.feed_forward.w1.scales": "2.safetensors",
|
| 742 |
+
"layers.28.feed_forward.w1.biases": "2.safetensors",
|
| 743 |
+
"layers.28.feed_forward.w2.weight": "2.safetensors",
|
| 744 |
+
"layers.28.feed_forward.w2.scales": "2.safetensors",
|
| 745 |
+
"layers.28.feed_forward.w2.biases": "2.safetensors",
|
| 746 |
+
"layers.28.feed_forward.w3.weight": "2.safetensors",
|
| 747 |
+
"layers.28.feed_forward.w3.scales": "2.safetensors",
|
| 748 |
+
"layers.28.feed_forward.w3.biases": "2.safetensors",
|
| 749 |
+
"layers.28.attention_norm1.weight": "2.safetensors",
|
| 750 |
+
"layers.28.ffn_norm1.weight": "2.safetensors",
|
| 751 |
+
"layers.28.attention_norm2.weight": "2.safetensors",
|
| 752 |
+
"layers.28.ffn_norm2.weight": "2.safetensors",
|
| 753 |
+
"layers.28.adaln_modulation.weight": "2.safetensors",
|
| 754 |
+
"layers.28.adaln_modulation.scales": "2.safetensors",
|
| 755 |
+
"layers.28.adaln_modulation.biases": "2.safetensors",
|
| 756 |
+
"layers.28.adaln_modulation.bias": "2.safetensors",
|
| 757 |
+
"layers.29.attention.qkv.weight": "2.safetensors",
|
| 758 |
+
"layers.29.attention.qkv.scales": "2.safetensors",
|
| 759 |
+
"layers.29.attention.qkv.biases": "2.safetensors",
|
| 760 |
+
"layers.29.attention.norm_q.weight": "2.safetensors",
|
| 761 |
+
"layers.29.attention.norm_k.weight": "2.safetensors",
|
| 762 |
+
"layers.29.attention.o.weight": "2.safetensors",
|
| 763 |
+
"layers.29.attention.o.scales": "2.safetensors",
|
| 764 |
+
"layers.29.attention.o.biases": "2.safetensors",
|
| 765 |
+
"layers.29.feed_forward.w1.weight": "2.safetensors",
|
| 766 |
+
"layers.29.feed_forward.w1.scales": "2.safetensors",
|
| 767 |
+
"layers.29.feed_forward.w1.biases": "2.safetensors",
|
| 768 |
+
"layers.29.feed_forward.w2.weight": "2.safetensors",
|
| 769 |
+
"layers.29.feed_forward.w2.scales": "2.safetensors",
|
| 770 |
+
"layers.29.feed_forward.w2.biases": "2.safetensors",
|
| 771 |
+
"layers.29.feed_forward.w3.weight": "2.safetensors",
|
| 772 |
+
"layers.29.feed_forward.w3.scales": "2.safetensors",
|
| 773 |
+
"layers.29.feed_forward.w3.biases": "2.safetensors",
|
| 774 |
+
"layers.29.attention_norm1.weight": "2.safetensors",
|
| 775 |
+
"layers.29.ffn_norm1.weight": "2.safetensors",
|
| 776 |
+
"layers.29.attention_norm2.weight": "2.safetensors",
|
| 777 |
+
"layers.29.ffn_norm2.weight": "2.safetensors",
|
| 778 |
+
"layers.29.adaln_modulation.weight": "2.safetensors",
|
| 779 |
+
"layers.29.adaln_modulation.scales": "2.safetensors",
|
| 780 |
+
"layers.29.adaln_modulation.biases": "2.safetensors",
|
| 781 |
+
"layers.29.adaln_modulation.bias": "2.safetensors",
|
| 782 |
+
"layers.30.attention.qkv.weight": "2.safetensors",
|
| 783 |
+
"layers.30.attention.qkv.scales": "2.safetensors",
|
| 784 |
+
"layers.30.attention.qkv.biases": "2.safetensors",
|
| 785 |
+
"layers.30.attention.norm_q.weight": "2.safetensors",
|
| 786 |
+
"layers.30.attention.norm_k.weight": "2.safetensors",
|
| 787 |
+
"layers.30.attention.o.weight": "2.safetensors",
|
| 788 |
+
"layers.30.attention.o.scales": "2.safetensors",
|
| 789 |
+
"layers.30.attention.o.biases": "2.safetensors",
|
| 790 |
+
"layers.30.feed_forward.w1.weight": "2.safetensors",
|
| 791 |
+
"layers.30.feed_forward.w1.scales": "2.safetensors",
|
| 792 |
+
"layers.30.feed_forward.w1.biases": "2.safetensors",
|
| 793 |
+
"layers.30.feed_forward.w2.weight": "2.safetensors",
|
| 794 |
+
"layers.30.feed_forward.w2.scales": "2.safetensors",
|
| 795 |
+
"layers.30.feed_forward.w2.biases": "2.safetensors",
|
| 796 |
+
"layers.30.feed_forward.w3.weight": "2.safetensors",
|
| 797 |
+
"layers.30.feed_forward.w3.scales": "2.safetensors",
|
| 798 |
+
"layers.30.feed_forward.w3.biases": "2.safetensors",
|
| 799 |
+
"layers.30.attention_norm1.weight": "2.safetensors",
|
| 800 |
+
"layers.30.ffn_norm1.weight": "2.safetensors",
|
| 801 |
+
"layers.30.attention_norm2.weight": "2.safetensors",
|
| 802 |
+
"layers.30.ffn_norm2.weight": "2.safetensors",
|
| 803 |
+
"layers.30.adaln_modulation.weight": "2.safetensors",
|
| 804 |
+
"layers.30.adaln_modulation.scales": "2.safetensors",
|
| 805 |
+
"layers.30.adaln_modulation.biases": "2.safetensors",
|
| 806 |
+
"layers.30.adaln_modulation.bias": "2.safetensors",
|
| 807 |
+
"layers.31.attention.qkv.weight": "2.safetensors",
|
| 808 |
+
"layers.31.attention.qkv.scales": "2.safetensors",
|
| 809 |
+
"layers.31.attention.qkv.biases": "2.safetensors",
|
| 810 |
+
"layers.31.attention.norm_q.weight": "2.safetensors",
|
| 811 |
+
"layers.31.attention.norm_k.weight": "2.safetensors",
|
| 812 |
+
"layers.31.attention.o.weight": "2.safetensors",
|
| 813 |
+
"layers.31.attention.o.scales": "2.safetensors",
|
| 814 |
+
"layers.31.attention.o.biases": "2.safetensors",
|
| 815 |
+
"layers.31.feed_forward.w1.weight": "2.safetensors",
|
| 816 |
+
"layers.31.feed_forward.w1.scales": "2.safetensors",
|
| 817 |
+
"layers.31.feed_forward.w1.biases": "2.safetensors",
|
| 818 |
+
"layers.31.feed_forward.w2.weight": "2.safetensors",
|
| 819 |
+
"layers.31.feed_forward.w2.scales": "2.safetensors",
|
| 820 |
+
"layers.31.feed_forward.w2.biases": "2.safetensors",
|
| 821 |
+
"layers.31.feed_forward.w3.weight": "2.safetensors",
|
| 822 |
+
"layers.31.feed_forward.w3.scales": "2.safetensors",
|
| 823 |
+
"layers.31.feed_forward.w3.biases": "2.safetensors",
|
| 824 |
+
"layers.31.attention_norm1.weight": "2.safetensors",
|
| 825 |
+
"layers.31.ffn_norm1.weight": "2.safetensors",
|
| 826 |
+
"layers.31.attention_norm2.weight": "2.safetensors",
|
| 827 |
+
"layers.31.ffn_norm2.weight": "2.safetensors",
|
| 828 |
+
"layers.31.adaln_modulation.weight": "2.safetensors",
|
| 829 |
+
"layers.31.adaln_modulation.scales": "2.safetensors",
|
| 830 |
+
"layers.31.adaln_modulation.biases": "2.safetensors",
|
| 831 |
+
"layers.31.adaln_modulation.bias": "2.safetensors",
|
| 832 |
+
"layers.32.attention.qkv.weight": "2.safetensors",
|
| 833 |
+
"layers.32.attention.qkv.scales": "2.safetensors",
|
| 834 |
+
"layers.32.attention.qkv.biases": "2.safetensors",
|
| 835 |
+
"layers.32.attention.norm_q.weight": "2.safetensors",
|
| 836 |
+
"layers.32.attention.norm_k.weight": "2.safetensors",
|
| 837 |
+
"layers.32.attention.o.weight": "2.safetensors",
|
| 838 |
+
"layers.32.attention.o.scales": "2.safetensors",
|
| 839 |
+
"layers.32.attention.o.biases": "2.safetensors",
|
| 840 |
+
"layers.32.feed_forward.w1.weight": "2.safetensors",
|
| 841 |
+
"layers.32.feed_forward.w1.scales": "2.safetensors",
|
| 842 |
+
"layers.32.feed_forward.w1.biases": "2.safetensors",
|
| 843 |
+
"layers.32.feed_forward.w2.weight": "2.safetensors",
|
| 844 |
+
"layers.32.feed_forward.w2.scales": "2.safetensors",
|
| 845 |
+
"layers.32.feed_forward.w2.biases": "2.safetensors",
|
| 846 |
+
"layers.32.feed_forward.w3.weight": "2.safetensors",
|
| 847 |
+
"layers.32.feed_forward.w3.scales": "2.safetensors",
|
| 848 |
+
"layers.32.feed_forward.w3.biases": "2.safetensors",
|
| 849 |
+
"layers.32.attention_norm1.weight": "2.safetensors",
|
| 850 |
+
"layers.32.ffn_norm1.weight": "2.safetensors",
|
| 851 |
+
"layers.32.attention_norm2.weight": "2.safetensors",
|
| 852 |
+
"layers.32.ffn_norm2.weight": "2.safetensors",
|
| 853 |
+
"layers.32.adaln_modulation.weight": "2.safetensors",
|
| 854 |
+
"layers.32.adaln_modulation.scales": "2.safetensors",
|
| 855 |
+
"layers.32.adaln_modulation.biases": "2.safetensors",
|
| 856 |
+
"layers.32.adaln_modulation.bias": "2.safetensors",
|
| 857 |
+
"layers.33.attention.qkv.weight": "2.safetensors",
|
| 858 |
+
"layers.33.attention.qkv.scales": "2.safetensors",
|
| 859 |
+
"layers.33.attention.qkv.biases": "2.safetensors",
|
| 860 |
+
"layers.33.attention.norm_q.weight": "2.safetensors",
|
| 861 |
+
"layers.33.attention.norm_k.weight": "2.safetensors",
|
| 862 |
+
"layers.33.attention.o.weight": "2.safetensors",
|
| 863 |
+
"layers.33.attention.o.scales": "2.safetensors",
|
| 864 |
+
"layers.33.attention.o.biases": "2.safetensors",
|
| 865 |
+
"layers.33.feed_forward.w1.weight": "2.safetensors",
|
| 866 |
+
"layers.33.feed_forward.w1.scales": "2.safetensors",
|
| 867 |
+
"layers.33.feed_forward.w1.biases": "2.safetensors",
|
| 868 |
+
"layers.33.feed_forward.w2.weight": "2.safetensors",
|
| 869 |
+
"layers.33.feed_forward.w2.scales": "2.safetensors",
|
| 870 |
+
"layers.33.feed_forward.w2.biases": "2.safetensors",
|
| 871 |
+
"layers.33.feed_forward.w3.weight": "2.safetensors",
|
| 872 |
+
"layers.33.feed_forward.w3.scales": "2.safetensors",
|
| 873 |
+
"layers.33.feed_forward.w3.biases": "2.safetensors",
|
| 874 |
+
"layers.33.attention_norm1.weight": "2.safetensors",
|
| 875 |
+
"layers.33.ffn_norm1.weight": "2.safetensors",
|
| 876 |
+
"layers.33.attention_norm2.weight": "2.safetensors",
|
| 877 |
+
"layers.33.ffn_norm2.weight": "2.safetensors",
|
| 878 |
+
"layers.33.adaln_modulation.weight": "2.safetensors",
|
| 879 |
+
"layers.33.adaln_modulation.scales": "2.safetensors",
|
| 880 |
+
"layers.33.adaln_modulation.biases": "2.safetensors",
|
| 881 |
+
"layers.33.adaln_modulation.bias": "2.safetensors",
|
| 882 |
+
"final_layer.linear.weight": "2.safetensors",
|
| 883 |
+
"final_layer.linear.scales": "2.safetensors",
|
| 884 |
+
"final_layer.linear.biases": "2.safetensors",
|
| 885 |
+
"final_layer.linear.bias": "2.safetensors",
|
| 886 |
+
"final_layer.adaln_modulation.weight": "2.safetensors",
|
| 887 |
+
"final_layer.adaln_modulation.scales": "2.safetensors",
|
| 888 |
+
"final_layer.adaln_modulation.biases": "2.safetensors",
|
| 889 |
+
"final_layer.adaln_modulation.bias": "2.safetensors"
|
| 890 |
}
|
| 891 |
}
|
vae/0.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 165107912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f10371a080131264155fbc227aa1887c2e9ac3b17b3d3a1301254937e2d40e5
|
| 3 |
size 165107912
|
vae/model.safetensors.index.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"quantization_level": "4",
|
| 4 |
-
"mflux_version": "0.
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"encoder.conv_in.weight": "0.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
"quantization_level": "4",
|
| 4 |
+
"mflux_version": "0.20.0"
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"encoder.conv_in.weight": "0.safetensors",
|