Load model from hub

Prediction.py

@@ -66,19 +66,6 @@ def predict_single(sentence, tokenizer, model, device, max_token_len=128):
     y_inten = [round(i, 8) for i in y_inten]
     return y_inten
 
-def model_factory(local_path, device):
-  manager = {}
-  for model_path in glob.glob(f"{local_path}/*"):
-    base_name = os.path.basename(model_path)
-    model_name = os.path.splitext(base_name)[0]
-    tokenizer = BertTokenizer.from_pretrained(model_path)
-    model = BertForSequenceClassification.from_pretrained(model_path)
-    model = model.to(device)
-    manager[model_name] = {
-       "model": model,
-       "tokenizer": tokenizer
-    }
-  return manager
 
 
 if __name__ == "__main__":
@@ -87,9 +74,10 @@ if __name__ == "__main__":
   Data = Data[:20]
   device = torch.device('cpu')
 
-  manager = model_factory("./models", device)
-  for model_name, dct in manager.items():
-    model, tokenizer = dct['model'], dct['tokenizer']
-    fk_doc_result = predict_csv(Data,"content", tokenizer, model, device)
-    single_response = predict_single("Games of the imagination teach us actions have consequences in a realm that can be reset.", tokenizer, model, device)
-    fk_doc_result.to_csv(f"output/prediction_{model_name}.csv")
+  # Load model directly
+  tokenizer = BertTokenizer.from_pretrained("Oliver12315/Brand_Tone_of_Voice")
+  model = BertForSequenceClassification.from_pretrained("Oliver12315/Brand_Tone_of_Voice")
+  model = model.to(device)
+  fk_doc_result = predict_csv(Data,"content", tokenizer, model, device)
+  single_response = predict_single("Games of the imagination teach us actions have consequences in a realm that can be reset.", tokenizer, model, device)
+  fk_doc_result.to_csv(f"output/prediction_Brand_Tone_of_Voice.csv")

app.py

@@ -20,13 +20,12 @@ else:
         ]
 
 device = torch.device('cpu')
-manager = model_factory("./models", device)
+tokenizer = BertTokenizer.from_pretrained("Oliver12315/Brand_Tone_of_Voice")
+model = BertForSequenceClassification.from_pretrained("Oliver12315/Brand_Tone_of_Voice")
+model = model.to(device)
 
 
 def single_sentence(sentence):
-    model_name = 'All_Data'
-    dct = manager[model_name]
-    model, tokenizer = dct['model'], dct['tokenizer']
     predictions = predict_single(sentence, tokenizer, model, device)
     predictions.sort(reverse=True)
     return list(zip(LABEL_COLUMNS, predictions))
@@ -38,18 +37,15 @@ def csv_process(csv_file, attr="content"):
     data = data.reset_index()
     os.makedirs('output', exist_ok=True)
     outputs = []
-    model_name = 'All_Data'
-    dct = manager[model_name]
-    model, tokenizer = dct['model'], dct['tokenizer']
     predictions = predict_csv(data, attr, tokenizer, model, device)
-    output_path = f"output/prediction_{model_name}_{formatted_time}.csv"
+    output_path = f"output/prediction_Brand_Tone_of_Voice_{formatted_time}.csv"
     predictions.to_csv(output_path)
     outputs.append(output_path)
     return outputs
 
 
 my_theme = gr.Theme.from_hub("JohnSmith9982/small_and_pretty")
-with gr.Blocks(theme=my_theme, title='Murphy') as demo:
+with gr.Blocks(theme=my_theme, title='Brand_Tone_of_Voice_demo') as demo:
     gr.HTML(
         """
         <div style="display: flex; justify-content: center; align-items: center; text-align: center;">
@@ -60,7 +56,7 @@ with gr.Blocks(theme=my_theme, title='Murphy') as demo:
             <h5 style="margin: 0;">If you like our project, please give us a star ✨ on Github for the latest update.</h5>
             <div style="display: flex; justify-content: center; align-items: center; text-align: center;>
                 <a href="https://arxiv.org/abs/xx.xx"><img src="https://img.shields.io/badge/Arxiv-xx.xx-red"></a>
-                <a href='https://huggingface.co/spaces/cheesexuebao/murphy'><img src='https://img.shields.io/badge/Project_Page-Murphy/xxBert' alt='Project Page'></a>
+                <a href='https://huggingface.co/spaces/Oliver12315/Brand_Tone_of_Voice_demo'><img src='https://img.shields.io/badge/Project_Page-Oliver12315/Brand_Tone_of_Voice_demo' alt='Project Page'></a>
                 <a href='https://github.com'><img src='https://img.shields.io/badge/Github-Code-blue'></a>
             </div>
         </div>

models/All_Data/config.json

@@ -1,39 +0,0 @@
-{
-  "_name_or_path": "bert-base-uncased",
-  "architectures": [
-    "BertForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "Assertive Tone",
-    "1": "Conversational Tone",
-    "2": "Emotional Tone",
-    "3": "Informative Tone",
-    "4": "None"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "Assertive Tone": 0,
-    "Conversational Tone": 1,
-    "Emotional Tone": 2,
-    "Informative Tone": 3,
-    "None": 4
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "transformers_version": "4.36.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
-}

models/All_Data/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:593dc3210abcc95df5a0f63580ce571df2b60c39cc4f1d7122e371c9f37c4c64
-size 438024366

tmp.py

@@ -1,5 +0,0 @@
-import pandas as pd
-
-pd.read_csv('output/example.csv')
-pd.inde
-...