.

config.json

@@ -0,0 +1 @@
+{"model_type": "clipseg", "text_config": {"vocab_size": 100, "hidden_size": 1, "intermediate_size": 1, "num_hidden_layers": 1, "num_attention_heads": 1, "max_position_embeddings": 77, "hidden_act": "quick_gelu", "layer_norm_eps": 1e-05, "attention_dropout": 0.0, "initializer_range": 0.02, "initializer_factor": 1.0, "pad_token_id": 1, "bos_token_id": 49406, "eos_token_id": 49407}, "vision_config": {"hidden_size": 1, "intermediate_size": 1, "num_hidden_layers": 1, "num_attention_heads": 1, "num_channels": 3, "image_size": 224, "patch_size": 32, "hidden_act": "quick_gelu", "layer_norm_eps": 1e-05, "attention_dropout": 0.0, "initializer_range": 0.02, "initializer_factor": 1.0}, "projection_dim": 1, "logit_scale_init_value": 2.6592, "extract_layers": [0], "reduce_dim": 1, "decoder_num_attention_heads": 1, "decoder_attention_dropout": 0.0, "decoder_hidden_act": "quick_gelu", "decoder_intermediate_size": 1, "conditional_layer": 0, "use_complex_transposed_convolution": false}

merges.txt

@@ -0,0 +1 @@
+#version: 0.2

preprocessor_config.json

@@ -0,0 +1 @@
+{"do_resize": true, "size": {"height": 224, "width": 224}, "do_rescale": true, "rescale_factor": 0.00392156862745098, "do_normalize": true, "image_mean": [0.48145466, 0.4578275, 0.40821073], "image_std": [0.26862954, 0.26130258, 0.27577711]}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6d4327f5b33c43398a5b7a8303e94ea29ca754ff778f0f4d3bc34895fdd318
+size 1297

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+    "add_prefix_space": false,
+    "bos_token": {
+        "__type": "AddedToken",
+        "content": "<|startoftext|>",
+        "lstrip": false,
+        "normalized": true,
+        "rstrip": false,
+        "single_word": false
+    },
+    "do_lower_case": true,
+    "eos_token": {
+        "__type": "AddedToken",
+        "content": "<|endoftext|>",
+        "lstrip": false,
+        "normalized": true,
+        "rstrip": false,
+        "single_word": false
+    },
+    "errors": "replace",
+    "model_max_length": 77,
+    "name_or_path": "openai/clip-vit-base-patch32",
+    "pad_token": "<|endoftext|>",
+    "processor_class": "CLIPSegProcessor",
+    "special_tokens_map_file": "/Users/nielsrogge/.cache/huggingface/hub/models--openai--clip-vit-base-patch32/snapshots/e6a30b603a447e251fdaca1c3056b2a16cdfebeb/special_tokens_map.json",
+    "tokenizer_class": "CLIPTokenizer",
+    "unk_token": {
+        "__type": "AddedToken",
+        "content": "<|endoftext|>",
+        "lstrip": false,
+        "normalized": true,
+        "rstrip": false,
+        "single_word": false
+    }
+}

vocab.json

@@ -0,0 +1 @@
+{"<|startoftext|>": 49406, "<|endoftext|>": 49407, "<|pad|>": 1}