Update README.md

README.md

@@ -3,32 +3,21 @@ license: mit
 datasets:
 - 3DGen/3DGen-Bench
 ---
+# 3DGen-Score
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+<!-- 
 **3DGen-Score** is an automatic evaluator fot 3D conditianl generation, which is trained on **3DGen-Bench**, a dataset of comparisons between two generated models on the same input. 
 The "clip-v1" version is finetued from "laion/CLIP-ViT-H-14-laion2B-s32B-b79K" in a "two-stage" style, and achieves an outstanding degree of human preference coherence.
-
-## Model Details
-
-### Model Description
+ -->
+**3DGen-Score** is an automatic evaluator for 3D conditianl generation, trained on a comparisons dataset.
 
 <!-- Provide a longer summary of what this model is. -->
+- **Paper:** 
 - **Training Data:** 3DGen/3DGen-Bench
 - **Pretrained Model:** laion/CLIP-ViT-H-14-laion2B-s32B-b79K
-- **Supported by:** Shanghai AI Lab
+- **Github Repository:** https://github.com/3DTopia/3DGen-Bench
 - **License:** MIT
 
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** https://github.com/3DTopia/3DGen-Bench
-- **Paper [optional]:** 
-- **Demo [optional]:** 
-
 ## Uses
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->