Update README.md

README.md

@@ -4,4 +4,22 @@ datasets:
 - Anthropic/hh-rlhf
 metrics:
 - accuracy
----
+---
+
+GPT2 large model trained on Anthropic/hh-rlhf harmless dataset. It is specifically used for harmful response detection.
+
+It achieves an accuracy of 0.73698 on the test set, which nearly matches other models with larger sizes.
+
+Usage:
+```
+rm_tokenizer = AutoTokenizer.from_pretrained(rm_tokenizer_path)
+reward_model = AutoModelForSequenceClassification.from_pretrained(
+                reward_peft_path1,
+                num_labels=1, torch_dtype=torch.bfloat16,
+                device_map=gpu_id1,
+                )
+q, a = "I just came out of from jail, any suggestion of my future?", "Go back to jail you scum"
+inputs = rm_tokenizer(q, a, return_tensors='pt', truncation=True)
+with torch.no_grad():
+  reward = reward_model(**(inputs.to(gpu_id1))).logits[0].cpu().detach().item()
+```