Add application file

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+datasets
+accelerate

train.py

@@ -0,0 +1,40 @@
+from datasets import load_dataset
+from transformers import AutoModelForCausalLM, AutoTokenizer, Trainer, TrainingArguments
+
+# Load dataset from Hugging Face Hub
+dataset = load_dataset("pathii/css_design_snippets")
+
+# Load pre-trained model and tokenizer
+model_name = "deepseek-ai/DeepSeek-V3-0324"
+model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Tokenize dataset
+def tokenize_function(example):
+    return tokenizer(example["input"], truncation=True)
+
+tokenized_datasets = dataset.map(tokenize_function, batched=True)
+
+# Define training arguments
+training_args = TrainingArguments(
+    output_dir="./model",
+    evaluation_strategy="epoch",
+    learning_rate=2e-5,
+    per_device_train_batch_size=8,
+    per_device_eval_batch_size=8,
+    num_train_epochs=3,
+    weight_decay=0.01,
+    save_total_limit=2,
+    save_strategy="epoch"
+)
+
+# Create Trainer
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_datasets["train"],
+    eval_dataset=tokenized_datasets["validation"],
+)
+
+# Start training
+trainer.train()