Update app.py

app.py

@@ -1,11 +1,8 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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("salmapm/llama2_salma")
-
+# Initialisez le client sans token
+client = InferenceClient(model="salmapm/llama2_salma")
 
 def respond(
     message,
@@ -27,21 +24,20 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+    try:
+        for message in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = message.choices[0].delta.content
+            response += token
+            yield response
+    except Exception as e:
+        yield f"An error occurred: {e}"
+
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +54,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()