Upload 2 files

merge.sh

@@ -0,0 +1,13 @@
+# beam_size=1
+# output_size=1
+# input_dir=/data3/HuangKai/Dataset/TRANSFER_dataset/template_sec
+max_input_size=2048
+model_name=CodeLlama-70b-hf
+output_dir=/mnt/share/huangk/Dataset/Transfer_dataset/RQ2/result_CodeLlama-70B/model_set_pr_2048_LORA
+
+# mkdir -p $output_dir
+
+python merge_peft_adapters.py \
+        --base_model_name_or_path codellama/$model_name \
+        --peft_model_path $output_dir/Epoch_1/  \
+        --push_to_hub \

merge_peft_adapters.py

@@ -0,0 +1,46 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+import os
+import argparse
+
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--base_model_name_or_path", type=str, default="bigcode/large-model")
+    parser.add_argument("--peft_model_path", type=str, default="/")
+    parser.add_argument("--push_to_hub", action="store_true", default=True)
+
+    return parser.parse_args()
+
+def main():
+    args = get_args()
+    
+    base_model = AutoModelForCausalLM.from_pretrained(
+        args.base_model_name_or_path,
+        return_dict=True,
+        # torch_dtype=torch.float16 
+    )
+     
+
+    model = PeftModel.from_pretrained(base_model, args.peft_model_path)
+    model = model.merge_and_unload()
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    tokenizer = AutoTokenizer.from_pretrained(args.base_model_name_or_path)
+
+    # if args.push_to_hub:
+    #     print(f"Saving to hub ...")
+    #     model.push_to_hub(f"{args.base_model_name_or_path}-merged", use_temp_dir=False, private=True)
+    #     tokenizer.push_to_hub(f"{args.base_model_name_or_path}-merged", use_temp_dir=False, private=True)
+    # else:
+    #     model.save_pretrained(f"{args.base_model_name_or_path}-merged")
+    #     tokenizer.save_pretrained(f"{args.base_model_name_or_path}-merged")
+    #     print(f"Model saved to {args.base_model_name_or_path}-merged")
+
+    model.save_pretrained(f"{args.peft_model_path}-merged")
+    tokenizer.save_pretrained(f"{args.peft_model_path}-merged")
+    print(f"Model saved to {args.peft_model_path}-merged")
+    
+if __name__ == "__main__" :
+    main()