back up

app.py

@@ -1,6 +1,5 @@
 import gradio as gr
 import torch
-import spaces
 from PIL import Image
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -19,7 +18,6 @@ seg_emb1 = model.encode_text(seg1, add_special_tokens=True)
 seg_emb2 = model.encode_text(seg2, add_special_tokens=False)
 
 
-@spaces.GPU(duration=60)
 def detailed_caption(img_path):
     subs = []
     image = Image.open(img_path).convert("RGB")

requirements.txt

@@ -4,13 +4,10 @@ tiktoken==0.5.1
 einops==0.7.0
 transformers_stream_generator==0.0.4
 scipy==1.11.3
-torch==2.1.2
-torchvision==0.16.2
+torchvision==0.15.2
 pillow==10.0.1
 matplotlib==3.8.0
-gradio==4.16.0
-gradio_client==0.8.1
+gradio==3.50.2
 sentencepiece
 urllib3==1.26.18
 timm==0.6.13
-spaces