Update app.py

app.py

@@ -1,12 +1,7 @@
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-MODEL_ID = "rinna/bilingual-gpt-neox-4b-instruction-ppo"
-model = AutoModelForCausalLM.from_pretrained(
-    MODEL_ID,
-    load_in_8bit=True,
-    device_map="auto"
-)
+MODEL_ID = "rinna/bilingual-gpt-neox-4b-instruction-ppo"model = AutoModelForCausalLM.from_pretrained("model_name", device_map="cpu")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, use_fast=False)
 
 device = model.device