Update README.md

README.md

@@ -14,10 +14,10 @@ tags:
 
 We evaluated the xTrimoPGLM-MLM (xTMLM) and xTrimoPGLM(100B) models on two OOD test sets, one with sequence identity lower than 0.9 with the training set (<0.9 ID) and the other with sequence identity lower than 0.5 with the training set (<0.5 ID). Each OOD dataset comprises approximately 10,000 protein sequences. The perplexity results, compared against ESM2-3B and ESM2-15B, are as follows (lower is better):
 
-| Model               | ESM2(3B)| ESM2 (15B) | xTMLM (1B) | xTMLM (3B) | xTMLM (10B) | xT (100B) |
-|:--------------------|:----------:|:----------:|:----------:|:----------:|:--------------------:|:--------------------:|
-| < 0.9 ID           |   7.7   |   7.3    | 9.3    |    7.8    |      7.6    |            **6.7**         | 
-| < 0.5 ID            |  11.5 |  11.0  |  13.5 |   11.9  |   11.6   |         **10.8**          |
+| Model               | ESM2(3B)| ESM2 (15B) | xTMLM (1B) | xTMLM (3B) | xTMLM (10B) | xT (100B) | xT (100B)-INT4 |
+|:--------------------|:----------:|:----------:|:----------:|:----------:|:--------------------:|:--------------------:|:--------------------:|
+| < 0.9 ID           |   7.7   |   7.3    | 9.3    |    7.8    |      7.6    |            **6.7**         |  **6.8**         | 
+| < 0.5 ID            |  11.5 |  11.0  |  13.5 |   11.9  |   11.6   |         **10.7**          | **10.8**          |
 
 
 ## Downstream Protein Understanding Tasks Evaluation