Update app.py

app.py

@@ -1,5 +1,10 @@
+import os
+os.environ["RWKV_JIT_ON"] = '1'
+os.environ["RWKV_CUDA_ON"] = '1' # if '1' then use CUDA kernel for seq mode (much faster)
+from modeling_rwkv import RWKV
+
+import gc
 import gradio as gr
-import os, gc
 import base64
 from io import BytesIO
 import torch
@@ -16,17 +21,13 @@ rwkv_remote_path = "rwkv1b5-vitl336p14-577token_mix665k_rwkv.pth"
 vision_remote_path = "rwkv1b5-vitl336p14-577token_mix665k_visual.pth"
 vision_tower_name = 'openai/clip-vit-large-patch14-336'
 
-os.environ["RWKV_JIT_ON"] = '1'
-os.environ["RWKV_CUDA_ON"] = '1' # if '1' then use CUDA kernel for seq mode (much faster)
-
-from modeling_vision import VisionEncoder, VisionEncoderConfig
-from modeling_rwkv import RWKV
 model_path = hf_hub_download(repo_id="howard-hou/visualrwkv-5", filename=rwkv_remote_path)
 model = RWKV(model=model_path, strategy='cuda fp16')
 from rwkv.utils import PIPELINE, PIPELINE_ARGS
 pipeline = PIPELINE(model, "rwkv_vocab_v20230424")
 
 ##########################################################################
+from modeling_vision import VisionEncoder, VisionEncoderConfig
 config = VisionEncoderConfig(n_embd=model.args.n_embd, 
                              vision_tower_name=vision_tower_name, 
                              grid_size=-1)