dev

app.py

@@ -1,6 +1,6 @@
 import spaces
 import gradio as gr
-from transformers import Trainer, TrainingArguments, AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import Trainer, TrainingArguments, AutoTokenizer, TFAutoModelForSeq2SeqLM
 from transformers import DataCollatorForSeq2Seq
 from datasets import load_dataset, concatenate_datasets, load_from_disk
 import traceback
@@ -19,7 +19,7 @@ lora_config = LoraConfig(
     lora_dropout=0.1,  # Dropout for LoRA layers
     bias="none"  # Bias handling
 )
-model = AutoModelForSeq2SeqLM.from_pretrained('google/t5-efficient-tiny', num_labels=2, force_download=True)
+model = TFAutoModelForSeq2SeqLM.from_pretrained('google/t5-efficient-tiny', num_labels=2, force_download=True)
 model = get_peft_model(model, lora_config)
 model.gradient_checkpointing_enable()
 model_save_path = '/data/lora_finetuned_model'  # Specify your desired save path
@@ -145,7 +145,7 @@ def predict(text):
 
 @spaces.GPU(duration=120)
 def run_train(dataset_name, hub_id, api_key, num_epochs, batch_size, lr, grad):
-    model = AutoModelForSeq2SeqLM.from_pretrained('/data/lora_finetuned_model', num_labels=2)
+    model = TFAutoModelForSeq2SeqLM.from_pretrained('/data/lora_finetuned_model', num_labels=2)
     result = fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size, lr, grad)
     return result
 # Create Gradio interface