Create README.md

README.md

@@ -0,0 +1,25 @@
+---
+datasets:
+- Anthropic/hh-rlhf
+language:
+- en
+tags:
+- rlhf
+model-index:
+  - name: deberta-v3-large-tasksource-rlhf-reward-model 
+    results:
+      - task:
+          type: text-classification
+          name: RLHF
+        dataset:
+          type: rlhf
+          name: Anthropic/hh-rlhf
+          split: validation
+        metrics:
+          - type: accuracy
+            value: 0,7516
+            verified: true
+---
+`deberta-v3-large-tasksource-nli` fine-tuned on Anthropic/hh-rlhf for 1 epoch with 1e-5 learning rate.
+
+Validation accuracy is currently the best publicly available reported: 75.16% (vs 69.25% for `OpenAssistant/reward-model-deberta-v3-large-v2`).