Update README.md

README.md

@@ -36,7 +36,6 @@ In order to inference this model you will have to use Aphrodite or vLLM as llama
 
 1. Remove `"rope_scaling": {}` from `config.json`
 2. Change `"max_position_embeddings"` to `8192` in `config.json`
-3. Add `"add_bos_token": false` to `tokenizer_config.json`
 
 
 ## Credits