Update app.py

app.py

@@ -14,12 +14,9 @@ def generate_prompts(user_input):
         input_variables=["Question"],
         template=f"Just list 10 quetion prompts for {user_input} and don't put number before each of the prompts."
     )
-    llm = CTransformers(
-        model="llama-2-7b-chat.ggmlv3.q8_0.bin",
-        model_type="llama",
-        max_new_tokens=512,
-        temperature=0.5
-    )
+    config = {'max_new_tokens': 512, 'temperature': 0.7, 'context_length': 512}
+    llm = CTransformers(model="TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
+                        config=config)
     hub_chain = LLMChain(prompt = prompt_template, llm = llm)
     input_data = {"Question": user_input}
 
@@ -36,10 +33,9 @@ def answer_question(prompt):
         input_variables=["Question"],
         template=f"give one answer for {prompt} and do not consider the number behind it."
     )
-    config = {'max_new_tokens': 2048, 'temperature': 0.7, 'context_length': 4096}
+    config = {'max_new_tokens': 512, 'temperature': 0.7, 'context_length': 512}
     llm = CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML",
-                        config=config,
-                        threads=os.cpu_count())
+                        config=config)
     hub_chain = LLMChain(prompt = prompt_template, llm = llm)
     input_data = {"Question": prompt}
     generated_answer = hub_chain.run(input_data)