Update app.py

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 import os
 import spaces
 from transformers import GemmaTokenizer, AutoModelForCausalLM
-from awq import AutoAWQForCausalLM
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 from threading import Thread
 
@@ -50,10 +49,10 @@ footer{display:none !important}
 """
 
 # Load the tokenizer and model
-model_name="collaiborateorg/Collaiborator-MEDLLM-Llama-3-8B-v2-AWQ-4Bit"
+model_name="collaiborateorg/Collaiborator-MEDLLM-Llama-3-8B-v2"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-#model = AutoModelForCausalLM.from_pretrained("collaiborateorg/Collaiborator-MEDLLM-Llama-3-8B-v1", device_map="auto")  # to("cuda:0") 
-model = AutoAWQForCausalLM.from_pretrained(model_name, device_map='auto')
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")  # to("cuda:0") 
+#model = AutoAWQForCausalLM.from_pretrained(model_name, device_map='auto')
 terminators = [
     tokenizer.eos_token_id,
     tokenizer.convert_tokens_to_ids("<|eot_id|>")