Update README.md

README.md

@@ -12,10 +12,10 @@ tags:
 
 We evaluated the xTrimoPGLM-CLM (xTCLM) 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 ProGen2-xlarge (6.4B), are as follows (lower is better):
 
-| Model               | ProGen2-xlarge (6.4B) | xTCLM (1B) | xTCLM (3B) | xTCLM (7B) | xT (100B) | xT (100B)-INT4 |
-|:--------------------|:----------:|:----------:|:----------:|:--------------------:|:--------------------:|:--------------------:|
-| < 0.9 ID            |   9.7     | 9.8    |    9.3    |      8.9    |            **8.7**         |      **8.9**         | 
-| < 0.5 ID            |   14.3    |  14.0  |    13.7  |    13.5   |         **13.3**          |   **13.5**          |
+| Model               | ProGen2-xlarge (6.4B) | xTCLM (1B) | xTCLM (3B) | xTCLM (7B) |  xT (100B)-INT4 |
+|:--------------------|:----------:|:----------:|:----------:|:--------------------:|:--------------------:|
+| < 0.9 ID            |   9.7     | 9.8    |    9.3    |      8.9    |                **8.9**         | 
+| < 0.5 ID            |   14.3    |  14.0  |    13.7  |    13.5           |   **13.5**          |
 
 
 ## How to use