Update app.py

app.py

@@ -1 +1,64 @@
-!pip install transformers datasets accelerate torch sentencepiece
+import torch
+import json
+import os
+from transformers import T5Tokenizer, T5ForConditionalGeneration, Trainer, TrainingArguments, DataCollatorForSeq2Seq
+from datasets import Dataset
+
+# ✅ 1. Ielādē treniņa datus
+with open("train.json", "r", encoding="utf-8") as f:
+    train_data = json.load(f)
+
+# ✅ 2. Pārveido datus Hugging Face formātā
+dataset = Dataset.from_list([{"input_text": d["question"], "target_text": d["answer"]} for d in train_data])
+
+# ✅ 3. Izvēlies modeli (piemēram, `mT5-small` vai `facebook/opt-1.3b`)
+model_name = "google/mt5-small"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+tokenizer = T5Tokenizer.from_pretrained(model_name)
+model = T5ForConditionalGeneration.from_pretrained(model_name).to(device)
+
+# ✅ 4. Sagatavo datus treniņam
+def preprocess_data(examples):
+    model_inputs = tokenizer(examples["input_text"], max_length=128, truncation=True)
+    labels = tokenizer(examples["target_text"], max_length=128, truncation=True)
+    model_inputs["labels"] = labels["input_ids"]
+    return model_inputs
+
+dataset = dataset.map(preprocess_data, batched=True)
+
+# ✅ 5. Definē trenēšanas parametrus
+training_args = TrainingArguments(
+    output_dir="./trained_model",
+    evaluation_strategy="epoch",
+    save_strategy="epoch",
+    learning_rate=5e-5,
+    per_device_train_batch_size=4,
+    per_device_eval_batch_size=4,
+    num_train_epochs=3,  # Trenē 3 epohas
+    weight_decay=0.01,
+    push_to_hub=True,  # Augšupielādē Hugging Face Hub
+    logging_dir="./logs"
+)
+
+data_collator = DataCollatorForSeq2Seq(tokenizer, model=model)
+
+# ✅ 6. Izveido `Trainer` klasi
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=dataset,
+    tokenizer=tokenizer,
+    data_collator=data_collator
+)
+
+# ✅ 7. Sāc trenēšanu
+trainer.train()
+
+# ✅ 8. Saglabā trenēto modeli
+model.save_pretrained("./trained_model")
+tokenizer.save_pretrained("./trained_model")
+
+# ✅ 9. Augšupielādē Hugging Face Hub (ja nepieciešams)
+trainer.push_to_hub()
+