feat: add sft scripts for Magicoder-Evol-Instruct-110K and alpaca-gpt4-data

- sft_magicoder.py: export ise-uiuc/Magicoder-Evol-Instruct-110K
- sft_alpaca_gpt4.py: export llm-wizard/alpaca-gpt4-data with instruction+input
- remove deprecated SFT scripts

scripts/supervised_finetuning/sft_alpaca_gpt4.py

@@ -0,0 +1,22 @@
+from datasets import load_dataset
+from pipeline import export_dataset
+
+
+def process_func(input_dict: dict):
+    instruction = input_dict["instruction"]
+    inp = input_dict.get("input", "")
+    if inp:
+        query = instruction + "\n" + inp
+    else:
+        query = instruction
+    return {"query": query, "response": input_dict["output"]}
+
+
+if __name__ == "__main__":
+    dataset = load_dataset("llm-wizard/alpaca-gpt4-data")
+    export_dataset(
+        dataset=dataset["train"],
+        output_dir="./dataset",
+        output_prefix="alpaca-gpt4-data",
+        process_func=process_func,
+    )