Update app.py

app.py

@@ -1,5 +1,3 @@
-#!/usr/bin/env python
-
 import os
 from collections.abc import Iterator
 from threading import Thread
@@ -22,7 +20,6 @@ CUSTOM_CSS = """
 # 2) Description: Add French greeting, plus any info
 #
 DESCRIPTION = """# Bonjour Dans le chat du consentement
-
 Mistral-7B Instruct Demo
 """
 
@@ -31,8 +28,6 @@ if not torch.cuda.is_available():
         "\n<p style='color:red;'>Running on CPU - This is likely too large to run effectively.</p>"
     )
 
-MAX_MAX_NEW_TOKENS = 2048
-DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 #
@@ -42,13 +37,15 @@ if torch.cuda.is_available():
     model_id = "mistralai/Mistral-7B-Instruct-v0.3"
     tokenizer = AutoTokenizer.from_pretrained(
         model_id, 
-        trust_remote_code=True  # Might be needed for custom code
+        trust_remote_code=True,  # Might be needed for custom code
+        use_auth_token=True
     )
     model = AutoModelForCausalLM.from_pretrained(
         model_id,
         torch_dtype=torch.float16,
         device_map="auto",
-        trust_remote_code=True
+        trust_remote_code=True,
+        use_auth_token=True
     )
 
 def generate(
@@ -101,49 +98,12 @@ def generate(
         yield "".join(outputs)
 
 #
-# 4) Build the Chat Interface with extra sliders
+# 4) Build the Chat Interface without additional inputs
 #
 demo = gr.ChatInterface(
     fn=generate,
     description=DESCRIPTION,
-    css=CUSTOM_CSS,  # Use our pastel gradient
-    additional_inputs=[
-        gr.Slider(
-            label="Max new tokens",
-            minimum=1,
-            maximum=MAX_MAX_NEW_TOKENS,
-            step=1,
-            value=DEFAULT_MAX_NEW_TOKENS,
-        ),
-        gr.Slider(
-            label="Temperature",
-            minimum=0.1,
-            maximum=4.0,
-            step=0.1,
-            value=0.6,
-        ),
-        gr.Slider(
-            label="Top-p (nucleus sampling)",
-            minimum=0.05,
-            maximum=1.0,
-            step=0.05,
-            value=0.9,
-        ),
-        gr.Slider(
-            label="Top-k",
-            minimum=1,
-            maximum=1000,
-            step=1,
-            value=50,
-        ),
-        gr.Slider(
-            label="Repetition penalty",
-            minimum=1.0,
-            maximum=2.0,
-            step=0.05,
-            value=1.2,
-        ),
-    ],
+    css=CUSTOM_CSS,
     stop_btn=None,
     examples=[
         ["Hello there! How are you doing?"],
@@ -156,4 +116,4 @@ demo = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch()
+    demo.queue(max_size=20).launch(share=True)