Rename app (8).py to app.py

app (8).py → app.py

@@ -9,31 +9,20 @@ import torch
 import argparse
 from transformers import AutoModel, AutoTokenizer
 
-# README, How to run demo on different devices
-
 # For Nvidia GPUs.
 # python web_demo_2.5.py --device cuda
 
-# For Mac with MPS (Apple silicon or AMD GPUs).
-# PYTORCH_ENABLE_MPS_FALLBACK=1 python web_demo_2.5.py --device mps
-
 # Argparser
 parser = argparse.ArgumentParser(description='demo')
-parser.add_argument('--device', type=str, default='cuda', help='cuda or mps')
+parser.add_argument('--device', type=str, default='cuda')
 args = parser.parse_args()
 device = args.device
-assert device in ['cuda', 'mps']
+assert device in ['cuda']
 
 # Load model
 model_path = 'openbmb/MiniCPM-Llama3-V-2_5'
-if 'int4' in model_path:
-    if device == 'mps':
-        print('Error: running int4 model with bitsandbytes on Mac is not supported right now.')
-        exit()
-    model = AutoModel.from_pretrained(model_path, trust_remote_code=True)
-else:
-    model = AutoModel.from_pretrained(model_path, trust_remote_code=True).to(dtype=torch.float16)
-    model = model.to(device=device)
+model = AutoModel.from_pretrained(model_path, trust_remote_code=True).to(dtype=torch.float16)
+model = model.to(device=device)
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
 model.eval()
 
@@ -289,7 +278,6 @@ with gr.Blocks() as demo:
             )
             bt_pic.upload(lambda: None, None, chat_bot, queue=False).then(upload_img, inputs=[bt_pic,chat_bot,app_session], outputs=[chat_bot,app_session])
 
-# launch
-#demo.launch(share=False, debug=True, show_api=False, server_port=8080, server_name="0.0.0.0")
+
 demo.queue()
 demo.launch()