SelanjutnyaPanduan berikutnya
YaRN dan Ekstensi Panjang Konteks
Teknis
PANDUAN AI Bahasa
Position Interpolation compresses the positional coordinates used by a pretrained RoPE-based model when extending its context.
Dengarkan panduan iniDiceritakan oleh AI · ~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.
Buletin gratis
Tiga cerita AI terverifikasi setiap pagi hari kerja, ditulis dalam bahasa Inggris sederhana. Gratis selamanya, tanpa iklan.
Satu email setiap hari kerja. Berhenti berlangganan dalam satu klik. Kami tidak pernah menjual atau membagikan alamat Anda.
Uji diri Anda sendiri
Umpan balik instan untuk setiap jawaban, dan sertifikat yang dapat dibagikan dengan ID yang dapat diverifikasi setelah Anda lulus kursus.
Mendukung pendidikan AI gratis. AI Understanding adalah organisasi nirlaba 501(c)(3) — tanpa iklan, tanpa paywall, selamanya. Berikan sumbangan
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 membagi indeks posisi berdasarkan faktor ekstensi, memetakan urutan yang lebih panjang kembali ke rentang distribusi yang telah dipelajari model.
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.
PI memetakan m ke m dibagi dengan faktor s = L'/L, memampatkan rentang yang lebih panjang ke dalam interval latihan awal.
YaRN preserves high-frequency local dimensions and interpolates lower-frequency dimensions with a transition between bands.
Teruslah belajar
Panduan lainnya dipilih untuk topik ini
SelanjutnyaPanduan berikutnya
YaRN dan Ekstensi Panjang Konteks
Teknis