update

app.py

@@ -2,6 +2,32 @@ from utils import *
 import gradio as gr
 
 
+from transformers import PreTrainedModel, PreTrainedTokenizer, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModel
+
+def download_model():
+    # 下載並快取SentenceTransformer所需的模型和tokenizer
+    sentence_transformer_model = "sentence-transformers/all-MiniLM-L6-v2"
+    PreTrainedModel.from_pretrained(sentence_transformer_model)
+    PreTrainedTokenizer.from_pretrained(sentence_transformer_model)
+    
+    # 下載並快取AutoTokenizer所需的模型
+    biobart_model = "fuhsiao/BioBART-PMC-EXT-Section"
+    PreTrainedModel.from_pretrained(biobart_model)
+    AutoTokenizer.from_pretrained(biobart_model)
+    AutoModel.from_pretrained(biobart_model)
+    
+    # 下載並快取AutoModelForSeq2SeqLM所需的模型
+    bart_model = "fuhsiao/BART-PMC-EXT-Section"
+    PreTrainedModel.from_pretrained(bart_model)
+    AutoTokenizer.from_pretrained(bart_model)
+    AutoModelForSeq2SeqLM.from_pretrained(bart_model)
+    
+    return True
+
+
+
+
+
 def main(file, ext_threshold, article_type):
     
     if file is None or ext_threshold is None or article_type is None:
@@ -20,9 +46,9 @@ def main(file, ext_threshold, article_type):
 
     abstr_model_path = ''
     if article_type == 'non-specialized field':
-        abstr_model_path = 'model/BART-PMC-EXT-Section'
+        abstr_model_path = 'fuhsiao/BART-PMC-EXT-Section'
     elif article_type == 'biomedical field':
-        abstr_model_path = 'model/BioBART-PMC-EXT-Section'
+        abstr_model_path = 'fuhsiao/BioBART-PMC-EXT-Section'
         
     TOKENIZER, ABSTRMODEL = load_AbstrModel(abstr_model_path)
     abstr = abstractive_method(ext, tokenizer=TOKENIZER, model=ABSTRMODEL)
@@ -36,6 +62,9 @@ def main(file, ext_threshold, article_type):
 
 if __name__ == '__main__':
 
+    download_model()
+    
+
     # 定義Gradio介面
     iface = gr.Interface(
         fn=main,

utils/preprocess.py

@@ -143,7 +143,7 @@ def similarity(lst, ptm):
 def feature_extraction(title, section, sents): 
     lst = sent_lst(sents)
     tfisf = Tfisf(lst)
-    cosine = similarity(lst, "model/all-MiniLM-L6-v2")
+    cosine = similarity(lst, "sentence-transformers/all-MiniLM-L6-v2")
     
     # Number of sentences
     ns = len(sents)