diff --git a/README.md b/README.md
index 58232c1c..0fa7a538 100644
--- a/README.md
+++ b/README.md
@@ -59,7 +59,7 @@ Text Generation Inference (TGI) is a toolkit for deploying and serving Large Lan
 For a detailed starting guide, please see the [Quick Tour](https://huggingface.co/docs/text-generation-inference/quicktour). The easiest way of getting started is using the official Docker container:
 
 ```shell
-model=tiiuae/falcon-7b-instruct
+model=HuggingFaceH4/zephyr-7b-beta
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
 docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.1.1 --model-id $model
diff --git a/server/text_generation_server/utils/peft.py b/server/text_generation_server/utils/peft.py
index e37447dc..d37e8940 100644
--- a/server/text_generation_server/utils/peft.py
+++ b/server/text_generation_server/utils/peft.py
@@ -38,7 +38,7 @@ def download_and_unload_peft(model_id, revision, trust_remote_code):
     os.makedirs(model_id, exist_ok=True)
     cache_dir = model_id
     logger.info(f"Saving the newly created merged model to {cache_dir}")
-    tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+    tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=trust_remote_code)
     model.save_pretrained(cache_dir, safe_serialization=True)
     model.config.save_pretrained(cache_dir)
     tokenizer.save_pretrained(cache_dir)