Update README.md

README.md

@@ -5,28 +5,3 @@
 * Metrics improved by DPO 
 ![Metrsc improment](dpo-metrics.jpg)
 
-gpu code example
-
-```
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import math
-
-## v2 models
-model_path = "cloudyu/Pluto_24B_DPO_200"
-
-tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
-model = AutoModelForCausalLM.from_pretrained(
-    model_path, torch_dtype=torch.bfloat16, device_map='auto',local_files_only=False, load_in_4bit=True
-)
-print(model)
-prompt = input("please input prompt:")
-while len(prompt) > 0:
-  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
-
-  generation_output = model.generate(
-    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
-  )
-  print(tokenizer.decode(generation_output[0]))
-  prompt = input("please input prompt:")
-```