File size: 24,890 Bytes
d782d8d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 |
{
"metadata": {
"total_size": 374942912
},
"weight_map": {
"mask_decoder.iou_prediction_head.layers.0.bias": "model.safetensors",
"mask_decoder.iou_prediction_head.layers.0.weight": "model.safetensors",
"mask_decoder.iou_prediction_head.proj_in.bias": "model.safetensors",
"mask_decoder.iou_prediction_head.proj_in.weight": "model.safetensors",
"mask_decoder.iou_prediction_head.proj_out.bias": "model.safetensors",
"mask_decoder.iou_prediction_head.proj_out.weight": "model.safetensors",
"mask_decoder.iou_token.weight": "model.safetensors",
"mask_decoder.mask_tokens.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.0.layers.0.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.0.layers.0.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.0.proj_in.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.0.proj_in.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.0.proj_out.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.0.proj_out.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.1.layers.0.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.1.layers.0.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.1.proj_in.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.1.proj_in.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.1.proj_out.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.1.proj_out.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.2.layers.0.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.2.layers.0.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.2.proj_in.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.2.proj_in.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.2.proj_out.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.2.proj_out.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.3.layers.0.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.3.layers.0.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.3.proj_in.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.3.proj_in.weight": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.3.proj_out.bias": "model.safetensors",
"mask_decoder.output_hypernetworks_mlps.3.proj_out.weight": "model.safetensors",
"mask_decoder.transformer.final_attn_token_to_image.k_proj.bias": "model.safetensors",
"mask_decoder.transformer.final_attn_token_to_image.k_proj.weight": "model.safetensors",
"mask_decoder.transformer.final_attn_token_to_image.out_proj.bias": "model.safetensors",
"mask_decoder.transformer.final_attn_token_to_image.out_proj.weight": "model.safetensors",
"mask_decoder.transformer.final_attn_token_to_image.q_proj.bias": "model.safetensors",
"mask_decoder.transformer.final_attn_token_to_image.q_proj.weight": "model.safetensors",
"mask_decoder.transformer.final_attn_token_to_image.v_proj.bias": "model.safetensors",
"mask_decoder.transformer.final_attn_token_to_image.v_proj.weight": "model.safetensors",
"mask_decoder.transformer.layer_norm_final_attn.bias": "model.safetensors",
"mask_decoder.transformer.layer_norm_final_attn.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.layer_norm1.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.layer_norm1.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.layer_norm2.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.layer_norm2.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.layer_norm3.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.layer_norm3.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.layer_norm4.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.layer_norm4.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.mlp.lin1.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.mlp.lin1.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.mlp.lin2.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.mlp.lin2.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.self_attn.k_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.self_attn.k_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.self_attn.out_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.self_attn.out_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.self_attn.q_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.self_attn.q_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.0.self_attn.v_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.0.self_attn.v_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.layer_norm1.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.layer_norm1.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.layer_norm2.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.layer_norm2.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.layer_norm3.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.layer_norm3.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.layer_norm4.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.layer_norm4.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.mlp.lin1.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.mlp.lin1.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.mlp.lin2.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.mlp.lin2.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.self_attn.k_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.self_attn.k_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.self_attn.out_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.self_attn.out_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.self_attn.q_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.self_attn.q_proj.weight": "model.safetensors",
"mask_decoder.transformer.layers.1.self_attn.v_proj.bias": "model.safetensors",
"mask_decoder.transformer.layers.1.self_attn.v_proj.weight": "model.safetensors",
"mask_decoder.upscale_conv1.bias": "model.safetensors",
"mask_decoder.upscale_conv1.weight": "model.safetensors",
"mask_decoder.upscale_conv2.bias": "model.safetensors",
"mask_decoder.upscale_conv2.weight": "model.safetensors",
"mask_decoder.upscale_layer_norm.bias": "model.safetensors",
"mask_decoder.upscale_layer_norm.weight": "model.safetensors",
"prompt_encoder.mask_embed.conv1.bias": "model.safetensors",
"prompt_encoder.mask_embed.conv1.weight": "model.safetensors",
"prompt_encoder.mask_embed.conv2.bias": "model.safetensors",
"prompt_encoder.mask_embed.conv2.weight": "model.safetensors",
"prompt_encoder.mask_embed.conv3.bias": "model.safetensors",
"prompt_encoder.mask_embed.conv3.weight": "model.safetensors",
"prompt_encoder.mask_embed.layer_norm1.bias": "model.safetensors",
"prompt_encoder.mask_embed.layer_norm1.weight": "model.safetensors",
"prompt_encoder.mask_embed.layer_norm2.bias": "model.safetensors",
"prompt_encoder.mask_embed.layer_norm2.weight": "model.safetensors",
"prompt_encoder.no_mask_embed.weight": "model.safetensors",
"prompt_encoder.not_a_point_embed.weight": "model.safetensors",
"prompt_encoder.point_embed.0.weight": "model.safetensors",
"prompt_encoder.point_embed.1.weight": "model.safetensors",
"prompt_encoder.point_embed.2.weight": "model.safetensors",
"prompt_encoder.point_embed.3.weight": "model.safetensors",
"shared_image_embedding.positional_embedding": "model.safetensors",
"vision_encoder.layers.0.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.0.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.0.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.0.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.0.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.0.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.0.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.0.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.0.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.0.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.0.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.0.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.0.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.0.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.1.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.1.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.1.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.1.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.1.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.1.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.1.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.1.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.1.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.1.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.1.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.1.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.1.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.1.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.10.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.10.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.10.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.10.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.10.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.10.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.10.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.10.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.10.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.10.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.10.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.10.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.10.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.10.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.11.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.11.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.11.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.11.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.11.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.11.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.11.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.11.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.11.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.11.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.11.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.11.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.11.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.11.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.2.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.2.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.2.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.2.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.2.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.2.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.2.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.2.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.2.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.2.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.2.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.2.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.2.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.2.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.3.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.3.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.3.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.3.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.3.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.3.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.3.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.3.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.3.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.3.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.3.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.3.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.3.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.3.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.4.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.4.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.4.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.4.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.4.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.4.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.4.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.4.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.4.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.4.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.4.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.4.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.4.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.4.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.5.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.5.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.5.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.5.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.5.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.5.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.5.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.5.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.5.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.5.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.5.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.5.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.5.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.5.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.6.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.6.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.6.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.6.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.6.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.6.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.6.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.6.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.6.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.6.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.6.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.6.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.6.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.6.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.7.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.7.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.7.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.7.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.7.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.7.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.7.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.7.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.7.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.7.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.7.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.7.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.7.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.7.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.8.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.8.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.8.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.8.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.8.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.8.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.8.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.8.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.8.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.8.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.8.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.8.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.8.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.8.mlp.lin2.weight": "model.safetensors",
"vision_encoder.layers.9.attn.proj.bias": "model.safetensors",
"vision_encoder.layers.9.attn.proj.weight": "model.safetensors",
"vision_encoder.layers.9.attn.qkv.bias": "model.safetensors",
"vision_encoder.layers.9.attn.qkv.weight": "model.safetensors",
"vision_encoder.layers.9.attn.rel_pos_h": "model.safetensors",
"vision_encoder.layers.9.attn.rel_pos_w": "model.safetensors",
"vision_encoder.layers.9.layer_norm1.bias": "model.safetensors",
"vision_encoder.layers.9.layer_norm1.weight": "model.safetensors",
"vision_encoder.layers.9.layer_norm2.bias": "model.safetensors",
"vision_encoder.layers.9.layer_norm2.weight": "model.safetensors",
"vision_encoder.layers.9.mlp.lin1.bias": "model.safetensors",
"vision_encoder.layers.9.mlp.lin1.weight": "model.safetensors",
"vision_encoder.layers.9.mlp.lin2.bias": "model.safetensors",
"vision_encoder.layers.9.mlp.lin2.weight": "model.safetensors",
"vision_encoder.neck.conv1.weight": "model.safetensors",
"vision_encoder.neck.conv2.weight": "model.safetensors",
"vision_encoder.neck.layer_norm1.bias": "model.safetensors",
"vision_encoder.neck.layer_norm1.weight": "model.safetensors",
"vision_encoder.neck.layer_norm2.bias": "model.safetensors",
"vision_encoder.neck.layer_norm2.weight": "model.safetensors",
"vision_encoder.patch_embed.projection.bias": "model.safetensors",
"vision_encoder.patch_embed.projection.weight": "model.safetensors",
"vision_encoder.pos_embed": "model.safetensors"
}
} |