Update app.py

app.py

@@ -3,7 +3,7 @@ from langchain.chains import LLMChain
 from langchain_core.prompts import PromptTemplate
 from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline,BitsAndBytesConfig
-quants = BitsAndBytesConfig(load_in_4bit=True)
+# quants = BitsAndBytesConfig(load_in_4bit=True)
 
 template = ''' You are an expert Blog generator , Given the Topic , the intended audience and the maximum number of words ,
     Write a blog on the given topic
@@ -40,8 +40,8 @@ def main():
 
     if st.sidebar.button("Generate Blog"):
         model_id = "mistralai/Mistral-7B-Instruct-v0.2"
-        tokenizer = AutoTokenizer.from_pretrained(model_id,quantization_config=quants)
-        model = AutoModelForCausalLM.from_pretrained(model_id,quantization_config=quants)
+        tokenizer = AutoTokenizer.from_pretrained(model_id)
+        model = AutoModelForCausalLM.from_pretrained(model_id)
         pipe = pipeline("text-generation", model=model, tokenizer=tokenizer,max_new_tokens=1000)
         hf = HuggingFacePipeline(pipeline=pipe)
         chain = LLMChain(llm=hf,prompt=prompt,verbose=True)