Delete image_encoder

Remove outdated image_encoder (update image_encoder from CLIPVisionModel to CLIPVisionModelWithProjection)

image_encoder/config.json

@@ -1,23 +0,0 @@
-{
-  "_name_or_path": "openai/clip-vit-base-patch32",
-  "architectures": [
-    "CLIPVisionModel"
-  ],
-  "attention_dropout": 0.0,
-  "dropout": 0.0,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 768,
-  "image_size": 224,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "model_type": "clip_vision_model",
-  "num_attention_heads": 12,
-  "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 32,
-  "projection_dim": 512,
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.1"
-}

image_encoder/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:97d6b9a07cd0d2448ee68a8d60d8c46aa827c32284088cc6536639d70332af54
-size 349890221