select models that work with text-generation

app.py

@@ -13,9 +13,10 @@ if not HF_TOKEN:
 # Available models
 AVAILABLE_MODELS = [
     "HuggingFaceH4/zephyr-7b-beta",
-    "meta-llama/Llama-3.1-8B-Instruct",
-    "microsoft/Phi-3.5-mini-instruct",
-    "Qwen/QwQ-32B",
+    "NousResearch/Hermes-3-Llama-3.1-8B",
+    "mistralai/Mistral-Nemo-Base-2407",
+    "meta-llama/Llama-2-70b-hf",
+    "aaditya/Llama3-OpenBioLLM-8B",
 ]
 
 # Initialize inference client