| { |
| "architectures": [ |
| "LESSViTModel" |
| ], |
| "attention_radius": 640, |
| "attn_drop": 0.1, |
| "attn_type": "less", |
| "channel_dim": 24, |
| "channel_dropout": null, |
| "channel_embed_dims_per_head": 2, |
| "channel_mask_ratio": 0.0, |
| "decoder_channel_dim": 64, |
| "decoder_depth": 8, |
| "decoder_embed_dim": 512, |
| "decoder_num_heads": 16, |
| "decoder_out_chans": 1, |
| "decoder_rope_channel_split_dim": 256, |
| "decoder_rope_spatial_split_dim": 256, |
| "decoder_spatial_dim": 128, |
| "depth": 12, |
| "drop_path_rate": 0.1, |
| "drop_path_uniform": false, |
| "embed_dim": 768, |
| "fusion_init_scale": 1.0, |
| "init_values": 1.0, |
| "mask_ratio": 0.0, |
| "mlp_ratio": 4.0, |
| "model_type": "lessvit", |
| "norm_pix_loss": true, |
| "num_heads": 12, |
| "num_tokens": 1, |
| "patch_size": 16, |
| "pos_chan_embed_residual": true, |
| "pretrain": false, |
| "proj_drop": 0.1, |
| "qk_norm": false, |
| "qkv_bias": true, |
| "rank": 1, |
| "return_dict": true, |
| "rope_channel_split_dim": 384, |
| "rope_embed_base": 100.0, |
| "rope_spatial_split_dim": 384, |
| "spatial_dim": 384, |
| "torch_dtype": "float32", |
| "transformers_version": "4.53.3", |
| "use_perception_field_mask": true, |
| "use_rope_embed": true, |
| "auto_map": { |
| "AutoConfig": "modeling_lessvit.LESSViTConfig", |
| "AutoModel": "modeling_lessvit.LESSViTModel" |
| } |
| } |
|
|
