FIM (Fill-in-the-Middle) Format: Prefix + Suffix → Middle Token Mantığı

# === FIM Dataset üretimi ===
import random
 
def to_fim(code, prob=0.5):
    """Code'u random olarak prefix/middle/suffix'e böl."""
    if random.random() > prob:
        # Normal next-token prediction (PSM probability)
        return code
 
    lines = code.split("\n")
    if len(lines) < 5:
        return code
 
    # Random split points
    start = random.randint(1, len(lines) - 2)
    end = random.randint(start + 1, len(lines) - 1)
 
    prefix = "\n".join(lines[:start])
    middle = "\n".join(lines[start:end])
    suffix = "\n".join(lines[end:])
 
    # FIM format (StarCoder 2 / Qwen Coder convention)
    return f"<fim_prefix>{prefix}<fim_suffix>{suffix}<fim_middle>{middle}"
 
# Dataset map
dataset = dataset.map(lambda x: {"text": to_fim(x["code"])})
 
# Training: SFTTrainer ile aynı, packing=True
# FIM token'lar tokenizer.special_tokens'a eklenmiş olmalı