Update README.md

README.md

@@ -25,6 +25,14 @@ from vllm import LLM, SamplingParams
 repo = snapshot_download(repo_id="Staticaliza/Reya-Human", allow_patterns=["*.json", "*.bin", "*.safetensors"])
 llm = LLM(model=repo, dtype="auto", tensor_parallel_size=torch.cuda.device_count(), enforce_eager=True, trust_remote_code=True)
 
+# ChatML is suggested
+input = """<|im_start|>system
+You are Reya.<|im_end|>
+<|im_start|>user
+Hi.<|im_end|>
+<|im_start|>assistant
+"""
+
 params = SamplingParams(
     max_tokens=256,
     temperature=1,