Update app.py

app.py

@@ -1,12 +1,14 @@
 import os 
-os.system("pip install --upgrade torch transformers sentencepiece scipy cpm_kernels accelerate bitsandbytes")
+os.system("pip install --upgrade torch transformers sentencepiece scipy cpm_kernels accelerate bitsandbytes loguru")
 
 
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
+logger.debug("load")
 model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
+logger.debug("done load")
 # tokenizer = AutoTokenizer.from_pretrained("openchat/openchat_v2_w")
 # model = AutoModelForCausalLM.from_pretrained("openchat/openchat_v2_w", load_in_8bit_fp32_cpu_offload=True, load_in_8bit=True)
 model.half()