Update README.md

README.md

@@ -101,19 +101,14 @@ The XVERSE-13B-256K model can be loaded for chat using the following code:
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from transformers.generation.utils import GenerationConfig
-model_path = "xverse/XVERSE-13B-256K"
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
-model.generation_config = GenerationConfig.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B-256K")
+model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B-256K", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
 model = model.eval()
-history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
-response = model.chat(tokenizer, history)
-print(response)
-history.append({"role": "assistant", "content": response})
-history.append({"role": "user", "content": "他任职了多少年"})
-response = model.chat(tokenizer, history)
-print(response)
+inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
+inputs = inputs.cuda()
+generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
+print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))
+
 ```
 
 更多细节，包括对话 demo 、模型微调及量化等，请参考我们的[Github](https://github.com/xverse-ai/XVERSE-13B)。