Update app.py

app.py

@@ -9,8 +9,8 @@ import chromadb
 from datasets import load_dataset
 # from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
-from gpt4all import GPT4All
-from pathlib import Path
+from transformers import AutoTokenizer, MistralForCausalLM
+
 
 
 # Function to clear the cache
@@ -86,10 +86,9 @@ vector_store.populate_vectors(dataset=None)
 # load model orca-mini general purpose model
 # tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
 # model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
-model_name = 'Meta-Llama-3-8B-Instruct.Q4_0.gguf' # .gguf represents quantized model
-model_path = "gpt4all"
-# add path to download load the model locally, download once and load for subsequent inference
-model = GPT4All(model_name=model_name, model_path=model_path,device="cuda")
+
+model = MistralForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
 
 # Define the chatbot response function
 def chatbot_response(user_input):