Архитектуры моделей
Матрица выбора модели
Начните с задачи пользователя и возможного сбоя. Это исходные архитектуры для первичной проверки, а не универсальные победители.
| Потребность продукта | Сначала проверить эту основу | Почему она подходит | Что тщательно контролировать |
|---|---|---|---|
| Open-ended assistant or coding copilot | Decoder-only LM + retrieval/tools as needed | Flexible generation and in-context task adaptation | Grounding, prompt injection, tool authority, serial latency |
| Classification, extraction, or reranking at volume | Encoder-only model or compact encoder–decoder | One-pass bounded prediction can be cheaper and easier to calibrate | Domain shift, input length, label calibration |
| Translation, transcription, or source-faithful transformation | Encoder–decoder model | Dedicated source memory conditions every generated token | Omissions, names/numbers, source length, decode latency |
| Semantic search over a large corpus | Dual encoder + vector index + optional reranker | Candidates can be embedded once and searched efficiently | Recall, negatives, filters, score calibration |
| Answers from current or private knowledge | Hybrid RAG + reranker + grounded generator | Knowledge remains external, inspectable, and refreshable | Ingestion, access control, missing evidence, poisoned context |
| Image creation or editing | Latent diffusion with U-Net or DiT denoiser | Compressed iterative generation supports strong conditioning and edits | Codec detail loss, sampling latency, rights and provenance |
| Video creation | Spatiotemporal latent diffusion or media-token generator | Both visual detail and temporal dependence are modeled | Identity drift, motion, duration, compute, audio sync |
| Speech recognition | Audio encoder–decoder designed for ASR | Separates acoustic understanding from text generation | Language, accent, overlap, noise, streaming delay |
| Long streaming sequence under a tight state budget | SSM/recurrent or attention–SSM hybrid | Carries compact recurrent state instead of a full attention cache | Exact long-range recall, kernel support, real throughput |
| Multimodal document or chart assistant | Vision encoder + language decoder + document retrieval | Preserves visual evidence while grounding answers in source pages | Small text, spatial references, media token cost, citations |
| Reliable actions in business systems | Tool-using LM inside a deterministic policy/controller | Language handles intent while code enforces permissions and side effects | Idempotency, approvals, retries, schemas, audit trail |
Откройте любое семейство на боковой панели, чтобы прочитать полное руководство по обучению, инференсу и выбору.