Fix for llama delta path

The model 7 has only 1 subfolder, so relative path needs to be updated accordingly.
(Readme was probably copied and updated from model 6, which had an extra subfolder for the deltas.)

README.md

@@ -111,7 +111,7 @@ edd1a5897748864768b1fab645b31491  ./tokenizer_config.json
 7. Once you have LLaMA weights in the correct format, you can apply the XOR decoding:
 
 ```
-python xor_codec.py oasst-sft-7-llama-30b/ oasst-sft-7-llama-30b-xor/oasst-sft-7-llama-30b-xor/ llama30b_hf/
+python xor_codec.py oasst-sft-7-llama-30b/ oasst-sft-7-llama-30b-xor/ llama30b_hf/
 ```
 
 You should **expect to see one warning message** during execution: