SAE-informed fine-tune

SAE (Sparse Autoencoder) informed adversarial training, goal: lower "text obsession" (typographic attack vulnerability; tendency to read text in images and misclassify) in CLIP ViT-L/14.

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "CLIP-SAE-ViT-L-14/",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 4.6052,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12,
+    "projection_dim": 768
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:820afa79f4ba17399e740b4b5630ab74bc3a196e471d7321123efa8356b62f79
+size 1710537716

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+    "unk_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "bos_token": {
+        "content": "<|startoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "eos_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "pad_token": "<|endoftext|>",
+    "add_prefix_space": false,
+    "errors": "replace",
+    "do_lower_case": true,
+    "name_or_path": "zer0int/CLIP-GmP-ViT-L-14",
+    "model_max_length": 77,
+    "special_tokens_map_file": "./special_tokens_map.json",
+    "tokenizer_class": "CLIPTokenizer"
+}