Update README.md

README.md

@@ -16,7 +16,7 @@ MOE the following models by mergekit:
 
 Works and generates coherent text. 
 
-code example
+gpu code example
 
 ```
 import torch
@@ -41,3 +41,30 @@ while len(prompt) > 0:
   print(tokenizer.decode(generation_output[0]))
   prompt = input("please input prompt:")
 ```
+
+CPU example
+
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+
+## v2 models
+model_path = "cloudyu/Mixtral_7Bx4_MOE_24B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype=torch.float32, device_map='cpu',local_files_only=False
+)
+print(model)
+prompt = input("please input prompt:")
+while len(prompt) > 0:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+
+  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:")
+
+```