test

app.py

@@ -7,12 +7,6 @@ from vllm.config import DeviceConfig
 from vllm import LLM
 from sal.models.reward_models import RLHFFlow
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
 if not os.path.exists("search-and-learn"):
     subprocess.run(["git", "clone", "https://github.com/huggingface/search-and-learn"])
     subprocess.run(["pip", "install", "-e", "./search-and-learn[dev]"])
@@ -36,6 +30,12 @@ llm = LLM(
 )
 
 
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
 
 def respond(
     message,