Update app.py

app.py

@@ -2,6 +2,9 @@ from huggingface_hub import InferenceClient
 import gradio as gr
 import torch
 
+client = InferenceClient(
+    "mistralai/Mixtral-8x7B-Instruct-v0.1"
+)
 
 def format_prompt(message, history):
   prompt = "<s>"
@@ -12,18 +15,8 @@ def format_prompt(message, history):
   return prompt
 
 def generate(
-    model_version, system_prompt, prompt, history, max_new_tokens, temperature, repetition_penalty, top_p, top_k, seed,
+    system_prompt, prompt, history, max_new_tokens, temperature, repetition_penalty, top_p, top_k, seed,
 ):
-    
-    if model_version == "1":
-        client = InferenceClient(
-            "mistralai/Mixtral-8x7B-v0.1"
-        )
-    else:
-        client = InferenceClient(
-            "mistralai/Mixtral-8x7B-Instruct-v0.1"
-        )
-
     temperature = float(temperature)
     if temperature < 1e-2:
         temperature = 1e-2
@@ -56,13 +49,6 @@ def generate(
 
 
 additional_inputs=[
-    gr.Dropdown(
-        ["1", "2"],
-        value="1",
-        interactive=True,
-        label="Mixtral 8x7b mModel Version",
-        info="Choose which Mixtral 8x7b model version to use in the chat"
-    ),
     gr.Textbox(
         label="System Prompt",
         interactive=True,
@@ -136,4 +122,4 @@ gr.ChatInterface(
     description="Chatbot Hugging Face space made by [Nick088](https://linktr.ee/Nick088) with costumizable options for model: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1<br>If you get an erorr, you putted a too much high Max_New_Tokens or your system prompt+prompt is too long, shorten up one of these",
     examples=examples,
     concurrency_limit=20,
-).launch(show_api=False)
+).launch(show_api=False, share=True)