Update: hf cache folder was manually provided

model.py

@@ -1,11 +1,15 @@
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+import os
+
+hf_cache_folder = './huggingface_cache/'
+os.makedirs(hf_cache_folder, exist_ok=True)
 
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
 model_id = "CohereForAI/c4ai-command-r-v01-4bit"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id).to(device)
+tokenizer = AutoTokenizer.from_pretrained(model_id, cache_dir=hf_cache_folder)
+model = AutoModelForCausalLM.from_pretrained(model_id, cache_dir=hf_cache_folder).to(device)
 ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>