Update app.py

app.py

@@ -1,6 +1,8 @@
 import gradio as gr
 from langchain import PromptTemplate, LLMChain, HuggingFaceHub
 from langchain.llms import CTransformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
 
 def generate_prompts(user_input):
     prompt_template = PromptTemplate(
@@ -9,9 +11,12 @@ def generate_prompts(user_input):
     )
     config = {'max_new_tokens': 2048, 'temperature': 0.7, 'context_length': 4096}
 
-    llm = HuggingFaceHub(repo_id="TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
-                       model_kwargs={"temperature": 0, "max_length":200})
-    
+    model_name = "TheBloke/Mistral-7B-Instruct-v0.1-GGUF"
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+    llm = CTransformers(model, tokenizer)
+
     hub_chain = LLMChain(prompt = prompt_template, llm = llm)
     input_data = {"Question": user_input}