Move some stuff from server.py to modules

modules/models.py

@@ -7,9 +7,12 @@ from pathlib import Path
 import modules.shared as shared
 import numpy as np
 import torch
+import transformers
 from transformers import AutoModelForCausalLM
 from transformers import AutoTokenizer
 
+transformers.logging.set_verbosity_error()
+
 local_rank = None
 
 if shared.args.flexgen: