Update app.py

app.py

@@ -12,17 +12,6 @@ quantization_config = QuantoConfig(
 model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", quantization_config=quantization_config, device_map="auto", token=access_token)
 tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
 
-# Load the tokenizer and model
-#model_id = "mistralai/Mixtral-8x7B-v0.1"
-#tokenizer = AutoTokenizer.from_pretrained(model_id, token=access_token)
-#model = AutoModelForCausalLM.from_pretrained(model_id, token=access_token, load_in_4bit=True)
-#model = AutoModelForCausalLM.from_pretrained(model_id, token=access_token)
-# Initialize the quantizer
-#quantizer = bnb.GemmQuantizer(act_bits=8, weight_bits=8)
-
-# Quantize the model
-#model = quantizer(model)
-
 # Function to generate text using the model
 def generate_text(prompt):
     text = prompt