Upload README.md

README.md

@@ -6,9 +6,9 @@
 
 ## Model Overview
 
-**CMRCLIP** encodes CMR images and clinical reports into a shared embedding space for retrieval, similarity scoring, and downstream tasks. It uses:
+**CMRCLIP** encodes CMR(Cardiac Magnetic Resonance) images and clinical reports into a shared embedding space for retrieval, similarity scoring, and downstream tasks. It uses:
 
-* A pretrained text encoder (`Bio+ClinicalBERT`)
+* A pretrained text encoder (`Bio_ClinicalBERT`)
 * A video encoder built on Vision Transformers (`SpaceTimeTransformer`)
 * A lightweight projection head to map both modalities into a common vector space
 
@@ -64,26 +64,21 @@ model.eval()
 
 ```json
 {
-  "arch": {
-      "type": "CMRCLIP",
-      "args": {
-          "video_params": {
-              "model": "SpaceTimeTransformer",
-              "arch_config": "base_patch16_224",
-              "num_frames": 64,
-              "pretrained": true,
-              "time_init": "zeros"
-          },
-          "text_params": {
-              "model": "emilyalsentzer/Bio_ClinicalBERT",
-              "pretrained": true,
-              "input": "text"
-          },
-          "projection": "minimal",
-          "projection_dim": 512,
-          "load_checkpoint": ""
-        }
-    }
+"video_params": {
+    "model": "SpaceTimeTransformer",
+    "arch_config": "base_patch16_224",
+    "num_frames": 64,
+    "pretrained": true,
+    "time_init": "zeros"
+},
+"text_params": {
+    "model": "emilyalsentzer/Bio_ClinicalBERT",
+    "pretrained": true,
+    "input": "text"
+},
+"projection": "minimal",
+"projection_dim": 512,
+"load_checkpoint": ""
 }
 
 ```