Update app.py

app.py

@@ -87,7 +87,8 @@ MODEL_NAME_IMAGE = "gpt-4-vision-preview"
 #verfügbare Modelle anzeigen lassen
 #HuggingFace Reop ID--------------------------------
 #repo_id = "meta-llama/Llama-2-13b-chat-hf"   
-repo_id = "HuggingFaceH4/zephyr-7b-alpha"   #das Modell ist echt gut!!! Vom MIT
+#repo_id = "HuggingFaceH4/zephyr-7b-alpha"   #das Modell ist echt gut!!! Vom MIT
+repo_id = "google/gemma-7b"
 #repo_id = "TheBloke/Yi-34B-Chat-GGUF"
 #repo_id = "meta-llama/Llama-2-70b-chat-hf"    
 #repo_id = "tiiuae/falcon-40b"  
@@ -443,8 +444,8 @@ def generate_text (prompt, chatbot, history, rag_option, model_option, openai_ap
             #oder an Hugging Face --------------------------
             print("HF Anfrage.......................")
             model_kwargs={"temperature": 0.5, "max_length": 512, "num_return_sequences": 1, "top_k": top_k, "top_p": top_p, "repetition_penalty": repetition_penalty}
-            #llm = HuggingFaceHub(repo_id=repo_id, model_kwargs=model_kwargs) 
-            llm = HuggingFaceHub(model=MODEL_NAME_HF, model_kwargs={"temperature": 0.5, "max_length": 128}) 
+            llm = HuggingFaceHub(repo_id=repo_id, model_kwargs=model_kwargs) 
+            #llm = HuggingFaceHub(model=MODEL_NAME_HF, model_kwargs={"temperature": 0.5, "max_length": 128}) 
             #llm = HuggingFaceHub(url_??? = "https://wdgsjd6zf201mufn.us-east-1.aws.endpoints.huggingface.cloud", model_kwargs={"temperature": 0.5, "max_length": 64}) 
             #llm = HuggingFaceTextGenInference( inference_server_url="http://localhost:8010/", max_new_tokens=max_new_tokens,top_k=10,top_p=top_p,typical_p=0.95,temperature=temperature,repetition_penalty=repetition_penalty,)
             print("HF")