get it running again

app.py

@@ -1,15 +1,24 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
+
+# Setze deinen Hugging Face API-Token hier
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+print("HF_TOKEN:", HF_TOKEN)
 
 """
 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")
+client = InferenceClient(
+    "Qwen/Qwen2.5-72B-Instruct",
+    token=HF_TOKEN # Token from Environment Variable or passed directly
+)
 
 
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history: list,
     system_message,
     max_tokens,
     temperature,
@@ -17,11 +26,21 @@ def respond(
 ):
     messages = [{"role": "system", "content": system_message}]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Unterstütze altes Tuple-Format und neues Message-Format
+    if history:
+        first = history[0]
+        if isinstance(first, (list, tuple)):
+            for user_msg, assistant_msg in history:
+                if user_msg:
+                    messages.append({"role": "user", "content": user_msg})
+                if assistant_msg:
+                    messages.append({"role": "assistant", "content": assistant_msg})
+        elif isinstance(first, dict):
+            for item in history:
+                role = item.get("role")
+                content = item.get("content")
+                if role and content:
+                    messages.append({"role": role, "content": content})
 
     messages.append({"role": "user", "content": message})
 
@@ -34,9 +53,10 @@ def respond(
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
+        if message and message.choices and message.choices[0].delta and message.choices[0].delta.content:
+            token = message.choices[0].delta.content
+            response += str(token)
+        
         yield response