chore: add .gitignore

util/utils.py

@@ -20,15 +20,7 @@ from matplotlib import pyplot as plt
 import easyocr
 from paddleocr import PaddleOCR
 reader = easyocr.Reader(['en'])
-paddle_ocr = PaddleOCR(
-    lang='en',  # other lang also available
-    use_angle_cls=False,
-    use_gpu=False,  # using cuda will conflict with pytorch in the same process
-    show_log=False,
-    max_batch_size=1024,
-    use_dilation=True,  # improves accuracy
-    det_db_score_mode='slow',  # improves accuracy
-    rec_batch_num=1024)
+paddle_ocr = PaddleOCR(lang='en')
 import time
 import base64
 
@@ -59,12 +51,12 @@ def get_caption_model_processor(model_name, model_name_or_path="Salesforce/blip2
             model_name_or_path, device_map=None, torch_dtype=torch.float16
         ).to(device)
     elif model_name == "florence2":
-        from transformers import AutoProcessor, AutoModelForCausalLM 
+        from transformers import AutoProcessor, AutoModelForCausalLM
         processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base", trust_remote_code=True)
         if device == 'cpu':
-            model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float32, trust_remote_code=True)
+            model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float32, trust_remote_code=True, attn_implementation="eager")
         else:
-            model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, trust_remote_code=True).to(device)
+            model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, trust_remote_code=True, attn_implementation="eager").to(device)
     return {'model': model.to(device), 'processor': processor}