Brezplačna dostava za naročila nad 69,99 € na prevzemna mesta DPD in Express One.

Preverjanje stanja naročila

Postanite del skupnosti ljubiteljev knjig z vsega sveta in uživajte v številnih ugodnostih. Ustvarite brezplačen račun

Brezplačna dostava Zásilkovna nad 69.99 €

Zbirna točka GLS 4.49 € Zbirna točka DPD 2.99 € Kurirska služba GLS 5.49 € Kurir DPD 3.49 € Kurirska služba Express One 3.49 € Zbirno mesto Express One 3.49 € Zbirno mesto Pošte Slovenije 3.49 € Dostava preko Pošte Slovenije 3.49 €

Kontakt

Kako nakupovati

Pomoč

Moj račun

▸ Prazna :-(

Brezplačna dostava za naročila nad 69,99 € na prevzemna mesta DPD in Express One.

Fine Tuning Large Language Models

Name: Fine Tuning Large Language Models
Brand: Independently published
SKU: 51322935
Price: 19.2 EUR
Availability: InStock
Author: Alex Ming
ISBN: 9798249390600

Adapting Foundation Models for Domain-Specific Intelligence and Performance Optimization

Alex Ming

Jezik

Angleščina

Knjiga Mehka

Koda Libristo: 51322935

Založba Independently published, februar 2026

Large language models provide powerful general capabilities, but real-world applications often requi... Celoten opis

Koda Libristo: 51322935

46 b

19.20 €

Na zalogi pri dobavitelju Odposlali bomo v 14-21 dneh

Do 30 dni za vračilo

Large language models provide powerful general capabilities, but real-world applications often require domain alignment, improved accuracy, and controlled behavior. Fine-Tuning Large Language Models provides a practical engineering roadmap for adapting foundation models to specialized use cases while maintaining stability, efficiency, and measurable performance.
This book covers the full fine-tuning lifecycle, including:

Dataset curation and quality control
Supervised fine-tuning (SFT) workflows
Parameter-efficient tuning techniques
Instruction tuning and conversational alignment
Evaluation metrics and benchmarking strategies
Overfitting mitigation and safety considerations
Cost optimization and compute planning

Readers will gain structured insight into designing reproducible fine-tuning pipelines and assessing model performance in real environments. The focus remains on engineering discipline, experimentation rigor, and responsible model adaptation rather than hype or unrealistic performance claims.
This volume is ideal for machine learning engineers, applied researchers, and technical professionals seeking to move beyond prompt engineering toward controlled, measurable model customization.