Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "CIDAS/clipseg-rd64-refined",
+  "architectures": [
+    "CLIPSegForImageSegmentation"
+  ],
+  "conditional_layer": 0,
+  "decoder_attention_dropout": 0.0,
+  "decoder_hidden_act": "quick_gelu",
+  "decoder_intermediate_size": 2048,
+  "decoder_num_attention_heads": 4,
+  "extract_layers": [
+    3,
+    6,
+    9
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clipseg",
+  "projection_dim": 512,
+  "reduce_dim": 64,
+  "text_config": {
+    "bos_token_id": 0,
+    "dropout": 0.0,
+    "eos_token_id": 2,
+    "model_type": "clipseg_text_model"
+  },
+  "transformers_version": "4.37.0.dev0",
+  "use_complex_transposed_convolution": true,
+  "vision_config": {
+    "dropout": 0.0,
+    "model_type": "clipseg_vision_model",
+    "patch_size": 16
+  }
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06bdfcae14e5e082a1d5b9f1b0ecdcda7e3ed6a27518e7153c30de73c31eaf7
+size 545418492

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da745cb0b9f3f8739148f58cc9a33756c76d1f1391f40e45474fd47695843f95
+size 138656948

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "processor_class": "CLIPSegProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 352,
+    "width": 352
+  }
+}

quantize_config.json

@@ -0,0 +1,43 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Pow",
+                "MatMul",
+                "Div",
+                "Shape",
+                "ConvTranspose",
+                "Flatten",
+                "Squeeze",
+                "Sigmoid",
+                "Mul",
+                "Unsqueeze",
+                "ReduceMean",
+                "Equal",
+                "Gemm",
+                "Sqrt",
+                "Expand",
+                "Transpose",
+                "ArgMax",
+                "Softmax",
+                "Range",
+                "Relu",
+                "Gather",
+                "Concat",
+                "Cast",
+                "Slice",
+                "Less",
+                "Constant",
+                "Conv",
+                "Add",
+                "ConstantOfShape",
+                "Reshape",
+                "Sub",
+                "Where"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "CLIPSegProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<|endoftext|>"
+}