deve

app.py

@@ -246,19 +246,19 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
 # Define Gradio interface
 @spaces.GPU
 def predict(text):
+    
     config = AutoConfig.from_pretrained("shorecode/t5-efficient-tiny-nh8-summarizer")
     model = AutoModelForSeq2SeqLM.from_config(config)
     #initialize_weights(model)
     tokenizer = AutoTokenizer.from_pretrained('shorecode/t5-efficient-tiny-nh8-summarizer')
-    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
+    inputs = tokenizer(text, padding='max_lenght', max_length=512, truncation=True)
     outputs = model(inputs)
     predictions = outputs.logits.argmax(dim=-1)
     return predictions.item()
 
 
 @spaces.GPU(duration=120)
-#def run_train(dataset_name, hub_id, api_key, num_epochs, batch_size, lr, grad):
-def run_train(text):
+def run_train(dataset_name, hub_id, api_key, num_epochs, batch_size, lr, grad):
     def initialize_weights(model):
         for name, param in model.named_parameters():
             if 'encoder.block.0.layer.0.DenseReluDense.wi.weight' in name:  # Example layer