Update README.md

README.md

@@ -23,6 +23,8 @@ The model was trained for 200k steps on an Nvidia A30 GPU.
 
 It is very good at reasoning tasks (better than llama 3.1 8B Instruct on ANLI and FOLIO), long context reasoning, sentiment analysis and zero-shot classification with new labels. 
 
+The following table shows model test accuracy. It is the accuracy of the same single model with different classification heads, further gains can be obtained by fine-tuning on a single-task, e.g. SST, but it this checkpoint is very hard to beat for zero-shot classification, NLI generalization).
+
 | test_name                             |   test_accuracy |
 |:--------------------------------------|----------------:|
 | glue/mnli                             |            0.89 |