Update README.md

README.md

@@ -84,7 +84,7 @@ sampling_params=SamplingParams(
     skip_special_tokens=True,
     temperature=0.0
 )
-# For the exact raspberry sample in the paper see
+# For the math sample 
 import re
 pattn=re.compile("\*\*Final Answer\*\*.*",re.S)
 
@@ -148,4 +148,19 @@ print("With budget forcing:")
 print(prompt + o[0].outputs[0].text)
 ```
 
+## If you want to combine lora weights into one model then use the following code
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained("jiangchengchengNLP/qwen2.5-distill-QWQ")
+base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-7B-Instruct",device_map='cpu',torch_dtype="bfloat16")
+model = PeftModel.from_pretrained(base_model, "jiangchengchengNLP/qwen2.5-distill-QWQ")
+mergemodel = model.merge_and_unload()
+mergemodel.save_pretrained("./merge_model")
+tokenizer.save_pretrained("./merge_model")
+print("model have merged!")
+```
+
+
 - PEFT 0.14.0