Upload model

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "/datasets/work/hb-mlaifsp-mm/work/checkpoints/uniformer_base_tl_384",
+  "architectures": [
+    "UniFormerModel"
+  ],
+  "attn_drop_rate": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_uniformer.UniFormerWithProjectionHeadConfig",
+    "AutoModel": "modelling_uniformer.UniFormerModel"
+  },
+  "conv_stem": false,
+  "depth": [
+    5,
+    8,
+    20,
+    7
+  ],
+  "drop_path_rate": 0.3,
+  "drop_rate": 0.0,
+  "embed_dim": [
+    64,
+    128,
+    320,
+    512
+  ],
+  "head_dim": 64,
+  "image_size": 384,
+  "in_chans": 3,
+  "layer_norm_eps": 1e-06,
+  "mlp_ratio": 4,
+  "model_type": "uniformer",
+  "num_classes": 1000,
+  "patch_size": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "projection_size": null,
+  "qk_scale": null,
+  "qkv_bias": true,
+  "representation_size": null,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3"
+}

modelling_uniformer.py

@@ -6,7 +6,6 @@ from typing import Optional, Tuple, Union
 import torch
 import torch.nn as nn
 from timm.models.layers import DropPath, to_2tuple, trunc_normal_
-from transformers import ViTConfig
 from transformers.modeling_outputs import ModelOutput
 from transformers.modeling_utils import PreTrainedModel
 from transformers.utils import logging