Update app.py

app.py

@@ -8,10 +8,14 @@ from huggingface_hub import snapshot_download
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 
-# Load the model and processor
+# https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B
 # MODEL_PATH = "THUDM/cogvlm2-llama3-chat-19B"
+
+# https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B-int4
 MODEL_PATH = "THUDM/cogvlm2-llama3-chat-19B-int4"
 
+
+### DOWNLOAD ###
 os.environ['HF_HUB_ENABLE_HF_TRANSFER'] = '1'
 MODEL_PATH = snapshot_download(MODEL_PATH)
 move_cache()
@@ -19,10 +23,14 @@ move_cache()
 DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
 TORCH_TYPE = torch.bfloat16 if torch.cuda.is_available() and torch.cuda.get_device_capability()[0] >= 8 else torch.float16
 
+
+## MODEL ##
 tokenizer = AutoTokenizer.from_pretrained(
     MODEL_PATH,
     trust_remote_code=True
 )
+
+## TOKENIZER ##
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_PATH,
     torch_dtype=TORCH_TYPE,