Il prossimoProssima guida
YaRN ed estensione della lunghezza del contesto
Tecnico
GUIDA ALL'AI linguistica
Position Interpolation compresses the positional coordinates used by a pretrained RoPE-based model when extending its context.
Ascolta questa guidaNarrato dall'IA · ~2 min
The original study adapts models to longer windows with additional training, without establishing universal accuracy or eliminating long-sequence costs.
RoPE applies position-dependent rotations to query and key dimension pairs. Simply using much longer sequences can expose the model to positional and attention conditions beyond those learned during training. Basic Position Interpolation rescales m to m divided by s, where s is the ratio of new context length to the original length. This compresses the coordinate span rather than continuing unmodified positions into a much longer range. The model still sees a changed sequence and denser position spacing, so adaptation and evaluation matter. The original paper reports successful extensions in its experiments with additional fine-tuning. Uniform compression affects all frequencies together; methods such as YaRN treat frequency bands differently to address local-detail and range tradeoffs.
Evaluating a pretrained RoPE model at a longer target length after positional rescaling and adaptation.
Comparing interpolation with unmodified positional extrapolation in the same model.
Studying frequency-aware methods such as YaRN against uniform position compression.
Measuring task performance and resource use across the extended window.
Context-extension research compares positional schemes, training budgets, and long-context evaluations. A nominally supported length is not proof of consistent retrieval or reasoning quality throughout the window. Assess the intended tasks, model adaptation, memory, and latency rather than treating rescaling as free long-context capability.
Newsletter gratuita
Tre storie verificate sull'IA ogni mattina nei giorni feriali, scritte in un inglese semplice. Gratuito per sempre, senza pubblicità.
Un'email ogni giorno feriale. Disiscriviti con un clic. Non vendiamo né condividiamo mai il tuo indirizzo.
Mettiti alla prova
Feedback immediato su ogni risposta e un certificato condivisibile con un ID verificabile una volta superato un corso.
Sostieni l'istruzione gratuita sull'IA. AI Understanding è un'organizzazione non profit 501(c)(3) — nessun annuncio, nessun paywall, mai. Fai una donazione
Position Interpolation compresses the positional coordinates used by a pretrained RoPE-based model when extending its context. The original study adapts models to longer windows with additional training, without establishing universal accuracy or eliminating long-sequence costs.
PI divide gli indici di posizione per il fattore di estensione, mappando la sequenza più lunga nell'intervallo di distribuzione già appreso dal modello.
The rescaled coordinates enter RoPE's rotation-angle calculation.
Out-of-training positional behavior can affect attention; observed effects depend on the model and extension.
Il PI mappa da m a m diviso per il fattore s = L'/L, comprimendo l'intervallo più lungo nell'intervallo allenato originale.
YaRN preserves high-frequency local dimensions and interpolates lower-frequency dimensions with a transition between bands.
Continua a imparare
Altre guide selezionate per questo argomento
Il prossimoProssima guida
YaRN ed estensione della lunghezza del contesto
Tecnico