Upload 3 files

src/clip_model/config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 512,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "dropout": 0.0,
+    "eos_token_id": 2,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 512,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "projection_dim": 512,
+    "torch_dtype": "float32",
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "vision_config": {
+    "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"
+  }
+}

src/clip_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab491c99ba210d84fca9111cdfddc6a8e3afa7712b7fd17662f522c3a90d7ab2
+size 605156676

src/clip_model/train_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0f1b58a97c40b7735729e17bc5ea205c7de1446b37f2bdd1dddbfbd6aed08b
+size 152875675