Update README.md

README.md

@@ -56,15 +56,21 @@ cae7b4ee8d1ad4e4402632bb0600cc17  ./tokenizer_config.json.ef7ef410b9b909949e96f1
 
 2. Decrypt the files using the scripts in https://github.com/LianjiaTech/BELLE/tree/main/models
 
-You can use the following command in Bash:
+You can use the following command in Bash, 
+Please replace "/path/to_encrypted" with the path where you stored your encrypted file, 
+replace "/path/to_original_llama_13B" with the path where you stored your original llama13B file, 
+and replace "/path/to_finetuned_model" with the path where you want to save your final trained model.:
+
 ```bash
-for f in "encrypted"/*; \
+mkdir /path/to_finetuned_model
+for f in "/path/to_encrypted"/*; \
     do if [ -f "$f" ]; then \
-       python3 decrypt.py "$f" "/path/to_original_llama_13B/consolidated.00.pth" "result/"; \
+       python3 decrypt.py "$f" "/path/to_original_llama_13B/consolidated.00.pth" "/path/to_finetuned_model/"; \
     fi; \
 done
 ```
 
+
 After executing the aforementioned command, you will obtain the following files.
 
 ```
@@ -113,7 +119,7 @@ After you decrypt the files, BELLE-LLAMA-13B-2M can be easily loaded with LlamaF
 from transformers import LlamaForCausalLM, AutoTokenizer
 import torch
 
-ckpt = './result/'
+ckpt = './path/to_finetuned_model/'
 device = torch.device('cuda')
 model = LlamaForCausalLM.from_pretrained(ckpt, device_map='auto', low_cpu_mem_usage=True)
 tokenizer = AutoTokenizer.from_pretrained(ckpt)