Update app.py

app.py

@@ -3,23 +3,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # Load your fine-tuned model and tokenizer
 model_name = "dextersud/sudbits_llama_pharma_clincal_model"
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
-
-
-quant_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=compute_dtype,
-    bnb_4bit_use_double_quant=False,
-    )
-
-model = AutoModelForCausalLM.from_pretrained(
-model_name,  # Load from the checkpoint directory
-quantization_config=quant_config,
-device_map="auto", 
-)
-model.config.use_cache = False
-model.config.pretraining_tp = 1
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 def respond(
     message,