Update app.py

app.py

@@ -251,14 +251,12 @@ def process_audio_from_video(video_path):
 
 
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Load Mistral 7B
-model_name = "mistralai/Mistral-7B-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
-
+tokenizer = AutoTokenizer.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.1-GPTQ")
+model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.1-GPTQ")
 
 
 def transcribe_and_predict_video(video, chat_history=[]):