Upload 2 files

text_encoder/config.json

@@ -1,30 +1,24 @@
 {
-  "_name_or_path": "CLIP-GmP-ViT-L-14/",
   "architectures": [
-    "CLIPModel"
+    "CLIPTextModel"
   ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 49406,
+  "dropout": 0.0,
+  "eos_token_id": 49407,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
   "initializer_factor": 1.0,
-  "logit_scale_init_value": 4.6052,
-  "model_type": "clip",
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
   "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": "4.44.2",
-  "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
-  }
+  "transformers_version": "4.51.3",
+  "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b820c4ef9a06ed7a5872b064405a69e26ebba5f524c92263b9bec1692a71bd7
-size 1710537716
+oid sha256:5887b2aab3464546970e06fa4af0766c29ee48135d3f4b8612042b1886177920
+size 492265168