Update README.md

README.md

@@ -46,7 +46,7 @@ model = AutoModelForCausalLM.from_pretrained('nicholascao/chatbloom-1b7-sft').ha
 inputs = tokenizer('<Human>: Hello <eoh> <Assistant>:', return_tensors='pt').to(torch.cuda.current_device())
 model.to(torch.cuda.current_device())
 
-output = model.generate(**inputs, max_length=768, do_sample=True, temperature=0.8, top_k=50, early_stopping=True, repetition_penalty=1.1)
+output = model.generate(**inputs, max_length=768, do_sample=True, temperature=0.8, top_k=50, early_stopping=True, repetition_penalty=1.05)
 output = tokenizer.decode(output[0], skip_special_tokens=True)
 print(output)
 ```