Ubuyobozi bwa tekiniki
Komeza Gutegura vs Byiza-Guhuza
Continued pretraining keeps training a base model with the same next-token objective on large amounts of raw domain text, while fine-tuning trains on a smaller curated set of labeled examples, such as instruction and response pairs, to shape behavior.
Umva iki gitaboAI-byavuzwe · ~3 min
Kuriyi page4 min soma
Incamake
The choice matters because the first mainly shifts what a model knows about a domain and its language, the second mainly shifts how it responds, and the data and compute needed differ greatly.
Kwibira cyane
Continued pretraining, also called domain-adaptive pretraining, picks up where the original pretraining stopped. The model sees raw text from the target domain, such as medical papers, source code or legal filings, and learns to predict every next token, exactly as in pretraining. Gururangan and colleagues showed in the 2020 paper Don't Stop Pretraining that a second phase of pretraining on in-domain text improved RoBERTa on tasks in biomedical, computer science, news and review domains. It usually needs large volumes of text, often billions of tokens, and full-parameter training, so it costs far more than fine-tuning. Fine-tuning, usually supervised fine-tuning, uses prompt and response pairs. Loss is typically computed only on the response tokens, so the model learns what to produce given an input. Datasets range from a few thousand to hundreds of thousands of examples, and parameter-efficient methods such as LoRA make it affordable on modest hardware. It is good at teaching format, style, task behavior and instruction following. Preference methods such as RLHF or DPO often follow. A common pipeline is base model, then continued pretraining, then supervised fine-tuning, then preference tuning. Continued pretraining has a known risk: catastrophic forgetting, where general skills degrade. Applied to a chat model, it can also erode instruction following, so teams often start from a base model and redo instruction tuning afterward. Two misconceptions stand out. First, fine-tuning is not a reliable way to add many new facts; research such as Gekhman and colleagues (2024) found models learn new facts slowly through fine-tuning and that doing so can increase hallucination. For fast-changing facts, retrieval is often the better tool. Second, BloombergGPT is sometimes cited as continued pretraining, but it was trained from scratch on a mix of financial and general data. A rough rule: use continued pretraining when domain language differs a lot from web text and unlabeled data is plentiful; use fine-tuning when you need a behavior or format.
Gushyira mu bikorwa Isi
Code Llama was built by continuing to train Llama 2 on a large corpus of code, and some of its variants were then further trained for Python and for following instructions.
A legal-tech company with millions of unlabeled contracts and filings runs continued pretraining to improve the model's handling of legal language, then fine-tunes on a few thousand annotated clause-extraction examples.
A bank wants a chatbot that answers in a fixed JSON format with a set tone; supervised fine-tuning, or even careful prompting, is enough because the model already knows the general content.
EPFL's Meditron models adapted Llama 2 to medicine through continued pretraining on medical papers and clinical guidelines before any task-specific fine-tuning.
The Future of Continued Pretraining vs Fine-Tuning
The steady release of capable open base models has made continued pretraining practical for more organizations, though it still requires substantial data and compute. Active research areas include reducing forgetting, making domain adaptation cheaper, and combining weights from separately trained models. In practice, many teams will keep pairing light fine-tuning with retrieval rather than full continued pretraining, reserving the heavier option for domains whose language is poorly covered by general web data.
Kubishyira mubikorwa
Impamvu ari ngombwa
- Igiciro na bije. Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka.
- Ibyemezo bisobanutse. Ubuhanga bwa tekinike bufasha amakipe guhitamo umurongo ukwiye, ntabwo ari shyashya gusa.
- Kugenzura ubuziranenge. Guhitamo neza bya injeniyeri bigabanya ibintu byizewe mubikorwa.
Witondere
- Gutezimbere igipimo kimwe gishobora guhisha intege nke za sisitemu.
- Ibikorwa Remezo no kubungabunga akenshi usanga bidahabwa agaciro.
- Icyuho cyumutekano no kwitegereza birashobora kwiyongera uko sisitemu igenda igorana.
Intambwe ikurikira
- Sobanura ubukererwe, ubuziranenge, nigiciro cyibiciro mbere yo kubishyira mubikorwa.
- Ibipimo byerekana umutwaro ufatika hamwe namakuru yimiterere.
- Gukurikirana ibikoresho kubikosa, drift, ningaruka zabakoresha.
- Tegura inzira yo gusubiza ibyabaye mbere yo gupima.
Komeza Ubushakashatsi
Ibaruwa y'amakuru y'ubuntu
Ibuka amakuru ya buri munsi ya AI
Inkuru eshatu zizewe za AI buri gitondo cy'iminsi y'akazi, zanditse mu rurimi rworoshye. Ubuntu iteka ryose, nta kwamamaza.
Imeri imwe buri munsi y'akazi. Kwiyimura mu buryo bumwe. Ntitwigera tugurisha cyangwa ngo dusangire aderesi yawe.
Isuzume
Take the Continued Pretraining vs Fine-Tuning quiz
Ibisubizo ako kanya kuri buri kibazo, n'icyemezo gishobora gusangirwa gifite ID yagenzurwa umaze gutsinda isomo.
Fasha uburezi bwa AI bw'ubuntu. AI Understanding ni umuryango utegamiye kuri leta wa 501(c)(3) — nta kwamamaza, nta kwishyura, iteka ryose. Tanga impano
Ibibazo bikunze kubazwa
What is Continued Pretraining vs Fine-Tuning?
Continued pretraining keeps training a base model with the same next-token objective on large amounts of raw domain text, while fine-tuning trains on a smaller curated set of labeled examples, such as instruction and response pairs, to shape behavior. The choice matters because the first mainly shifts what a model knows about a domain and its language, the second mainly shifts how it responds, and the data and compute needed differ greatly.
Ni irihe tandukaniro nyamukuru ryamakuru hagati yo gukomeza kwitegura no kugenzurwa neza?
Gukomeza kwitegura guhanura ibimenyetso bikurikira kumyandiko mbisi, mugihe gutunganya neza bigira kubisubizo nibisubizo byombi.
Mugenzurwa neza-neza, igihombo gikunze kubarwa he?
Guhisha ikibazo bisobanura icyitegererezo cyiga icyo gutanga cyatanzwe cyinjijwe, ntabwo kubyara ibyinjijwe.
Niki gusubiramo mugukomeza kwitegura?
Harimo amakuru rusange afasha kurinda ubuhanga rusange kutitesha agaciro mugihe icyitegererezo cyiga domaine.
Nigute Code Llama yubatswe?
Kode Llama ni urugero rwakomeje kwitegura, hamwe na variants zimwe zongeye guhugurwa kuri Python namabwiriza.
Kubintu bihinduka kenshi, ni ubuhe buryo ubuyobozi buvuga ko aribwo bwiza kuruta guhuza neza?
Kuringaniza neza biga ibintu bishya gahoro gahoro kandi birashobora kongera salusiyo, kubisubiramo rero nibyiza muguhindura amakuru.
Komeza wige
Kuyobora
Abandi bayobozi batoranijwe kuriyi ngingo