स्टेप 13 · इसे निर्देश मानना सिखाना

example = {
  "messages": [
    {"role": "system", "content": "You are a careful assistant."},
    {"role": "user", "content": "Why is the sky blue?"},
    {"role": "assistant", "content": "Sunlight contains all colours. Air "
     "scatters short wavelengths more than long ones, so blue light bounces "
     "around the sky and reaches your eyes from every direction."}
  ]
}

# Rendered with the model's chat template, then tokenised. Each role turn
# is wrapped in special tokens, and the newlines matter:
#
#   <|im_start|>system      + newline + You are a careful assistant. + <|im_end|>
#   <|im_start|>user        + newline + Why is the sky blue?        + <|im_end|>
#   <|im_start|>assistant   + newline + Sunlight contains...        + <|im_end|>
#
# Use tokenizer.apply_chat_template() rather than building this by hand --
# every model family differs, and a mismatch degrades quality silently.

def build_labels(input_ids, assistant_spans, ignore=-100):
    """Only the assistant's own tokens contribute to the loss."""
    labels = torch.full_like(input_ids, ignore)
    for start, end in assistant_spans:
        labels[start:end] = input_ids[start:end]
    return labels

# cross_entropy ignores -100 by default, so the model is never
# trained to generate the user's questions back at you.