update cap

app.py

@@ -18,7 +18,7 @@ from PIL import Image
 from huggingface_hub import hf_hub_download, login
 
 from open_flamingo.src.factory import create_model_and_transforms
-from open_flamingo.chat.conversation import Chat, CONV_VISION
+from open_flamingo.chat.conversation import ChatBOT, CONV_VISION
 
 sys.path.append(str(Path(__file__).parent.parent.parent))
 TEMP_FILE_DIR = Path(__file__).parent / 'temp'
@@ -63,7 +63,7 @@ if "vision_encoder.logit_scale" in model_state_dict:
     del model_state_dict["vision_encoder.visual.ln_post.weight"]
     del model_state_dict["vision_encoder.visual.ln_post.bias"]
 flamingo.load_state_dict(model_state_dict, strict=True)
-chat = Chat(flamingo, image_processor, tokenizer, vis_embed_size,model_name)
+chat = ChatBOT(flamingo, image_processor, tokenizer, vis_embed_size,model_name)
 
 
 def get_outputs(

multimodal/open_flamingo/chat/__init__.py

@@ -0,0 +1,2 @@
+
+

multimodal/open_flamingo/chat/conversation.py

@@ -275,7 +275,7 @@ def preprocess_image(sample, image_processor):
     return image
 
 
-class Chat:
+class ChatBOT:
     def __init__(self, model, vis_processor, tokenizer, vis_embed_size,model_name):
         self.model = model
         self.vis_processor = vis_processor