Update app.py

app.py

@@ -1,17 +1,16 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 import random
-from transformers import AutoTokenizer,AutoModelForCausalLM, BitsAndBytesConfig
+from transformers import AutoTokenizer,AutoModelForCausalLM
 from mySystemPrompt import SYSTEM_PROMPT
 
-bnb_config = BitsAndBytesConfig(load_in_8bit=True)
 
 # Model which is used
 checkpoint = "CohereForAI/c4ai-command-r-plus"
 # Inference client with the model (And HF-token if needed)
 client = InferenceClient(checkpoint)
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
-model = AutoModelForCausalLM.from_pretrained(checkpoint, quantization_config=bnb_config)
+model = AutoModelForCausalLM.from_pretrained(checkpoint)
 # Tokenizer chat template correction(Only works for mistral models)
 #chat_template = open("mistral-instruct.jinja").read()
 #chat_template = chat_template.replace('    ', '').replace('\n', '')