update

app.py

@@ -1,15 +1,7 @@
 from huggingface_hub import InferenceClient
-import gradio as gr
-
-css = '''
-.gradio-container{max-width: 1000px !important}
-h1{text-align:center}
-footer {
-    visibility: hidden
-}
-'''
 
 client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
+
 def format_prompt(message, history, system_prompt=None):
     prompt = "<s>"
     for user_prompt, bot_response in history:
@@ -19,7 +11,7 @@ def format_prompt(message, history, system_prompt=None):
         prompt += f"[SYS] {system_prompt} [/SYS]"
     prompt += f"[INST] {message} [/INST]"
     return prompt
-#Generate
+
 def generate(
     prompt, history, system_prompt=None, temperature=0.2, max_new_tokens=1024, top_p=0.95, repetition_penalty=1.0,
 ):
@@ -44,15 +36,16 @@ def generate(
 
     for response in stream:
         output += response.token.text
-        yield output
+        print(output, end='', flush=True)
     return output
 
-
-demo = gr.ChatInterface(
-    fn=generate,
-    css=css,
-    title="",
-    theme="bethecloud/storj_theme"
-)
-
-demo.queue().launch(show_api=False)
+if __name__ == "__main__":
+    history = []
+    system_prompt = None
+    while True:
+        user_input = input("You: ")
+        if user_input.lower() in ["exit", "quit"]:
+            break
+        response = generate(user_input, history, system_prompt)
+        history.append((user_input, response))
+        print(f"\nBot: {response}\n")