Upload config

config.json

@@ -1,58 +1,23 @@
 {
-  "abs_pos_patch_grid_size": null,
   "aum_pretrain": true,
-  "aum_pretrain_fstride": null,
   "aum_pretrain_path": "models/aum-base_audioset-vggsound.pth",
-  "aum_pretrain_tstride": null,
-  "bilinear_rope": false,
   "bimamba_type": "v1",
-  "channels": 1,
-  "depth": 24,
-  "device": null,
-  "drop_path_rate": 0,
-  "drop_rate": 0.0,
-  "dtype": null,
   "embed_dim": 768,
-  "final_pool_type": "mean",
-  "flexible_patch_sizes": null,
-  "flip_img_sequences_ratio": -1.0,
-  "ft_seq_len": null,
-  "fused_add_norm": true,
-  "if_abs_pos_embed": true,
-  "if_bidirectional": false,
-  "if_bimamba": false,
-  "if_cls_token": true,
-  "if_devide_out": true,
-  "if_rope": false,
-  "if_rope_residual": false,
-  "imagenet_load_double_cls_token": false,
-  "imagenet_load_middle_cls_token": true,
   "imagenet_pretrain": false,
-  "imagenet_pretrain_modelkey": "model",
   "imagenet_pretrain_path": null,
-  "init_layer_scale": null,
-  "initializer_cfg": null,
-  "norm_epsilon": 1e-05,
+  "model_type": "mamba",
   "num_classes": 309,
   "patch_size": [
     16,
     16
   ],
-  "pt_hw_seq_len": null,
-  "residual_in_fp32": true,
-  "rms_norm": true,
   "spectrogram_size": [
     128,
     1024
   ],
-  "ssm_cfg": null,
   "strides": [
     16,
     16
   ],
-  "transpose_token_sequence": false,
-  "use_PI_for_patch_embed": true,
-  "use_double_cls_token": false,
-  "use_end_cls_token": false,
-  "use_middle_cls_token": true
-}
+  "transformers_version": "4.35.2"
+}