Update README.md

README.md

@@ -296,4 +296,4 @@ datasets:
 deberta-v3-base with context length of 1280 fine-tuned on tasksource for 150k steps. I oversampled long NLI tasks (ConTRoL, doc-nli).
 Training data include helpsteer v1/v2, logical reasoning tasks (FOLIO, FOL-nli, LogicNLI...), OASST, hh/rlhf, linguistics oriented NLI tasks, tasksource-dpo, fact verification tasks.
 
-This model is suitable for long context NLI or and as a backbone for RLHF fine-tuning.
+This model is suitable for long context NLI or and as a backbone for reward models or classifiers fine-tuning.