中文

Fine-tuning

Curated Fine-tuning tutorials.

All tutorials

Fine-tuning

43 tutorials in this topic

Advanced

Adapters vs LoRA Comparison: Hands-On Tutorial

Adapters vs LoRA Comparison Overview Comparing adapter-based methods for LLM customization. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl acc

Advanced

Knowledge Distillation: Train Small, Fast AI Models from Large Teacher Models

Learn knowledge distillation techniques to create small, fast student models that mimic large teacher model performance, covering task distillation, feature-level distillation, and production deployment.

Advanced

AI Model Compression: Pruning, Quantization, and Knowledge Distillation

Learn model compression techniques to make AI models 10x smaller and faster. Covers weight pruning, quantization (INT8, INT4), knowledge distillation, and deployment on edge devices.

Advanced

AI Model Merging: SLERP, TIES, DARE, and Model Soup Techniques

Explore model merging techniques that combine weights from multiple fine-tuned models to create superior models without additional training, including SLERP, TIES-Merging, DARE, and evolutionary approaches.

Advanced

AI Model Quantization (GPTQ, AWQ): Complete Developer Guide 2026

A Complete Guide to AI Model Quantization (GPTQ/AWQ) (2026): Store weights with fewer bits to save VRAM and boost speed. Comparison of GPTQ vs AWQ, bitsandbytes/GGUF, selecting the 4-bit sweet spot, and a practical path of "directly downloading pre-quantized weights + deploying with vLLM/Ollama."

Advanced

Production NER Systems: Fine-Tuning spaCy and Transformers for Custom Entities

Build production Named Entity Recognition systems for custom entity types using spaCy and transformer models, covering annotation strategies, active learning, and deployment optimization.

Advanced

Continual Learning for LLMs: Hands-On Tutorial

Continual Learning for LLMs Overview Preventing catastrophic forgetting during fine-tuning. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl acc

Advanced

Data Synthesis for Fine-tuning: Hands-On Tutorial

Data Synthesis for Fine-tuning Overview Using GPT-4 to generate fine-tuning data synthetically. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl

Advanced

Dataset Preparation for Fine-tuning: Hands-On Tutorial

Dataset Preparation for Fine-tuning Overview Building high-quality fine-tuning datasets from scratch. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets pe

Advanced

Deployment of Fine-tuned Models: Hands-On Tutorial

Deployment of Fine-tuned Models Overview Serving custom fine-tuned models with vLLM and TGI. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl ac

Advanced

DPO: Direct Preference Optimization: Hands-On Tutorial

DPO: Direct Preference Optimization Overview Simplified alignment using Direct Preference Optimization. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets

Intermediate

Fine-tune Llama 3.2 on Your Data

Fine-tune Llama 3.2 on Your Data What You'll Build End-to-end Llama 3.2 fine-tuning on custom dataset. By the end of this tutorial, you'll have a fully working implementation you can extend for production use. **Time**: ~25 minutes **Difficulty*

Advanced

Fine-tuning Evaluation: Hands-On Tutorial

Fine-tuning Evaluation Overview Evaluating fine-tuned models with domain benchmarks. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl accelerate

Advanced

Fine-tuning for Code Generation: Hands-On Tutorial

Fine-tuning for Code Generation Overview Domain-specific fine-tuning for code completion and generation. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets

Advanced

Fine-Tuning GPT-4o Mini: OpenAI Fine-Tuning API Complete Guide

GPT-4o Mini Fine-Tuning Complete Guide (2026): Use OpenAI's fine-tuning API to obtain a hosted model with stable format/style and reduce costs for massive calls. Includes real code for JSONL data preparation → upload → training → inference, when to fine-tune vs. prompt/RAG, and data quality > quantity.

Advanced

Fine-tuning Llama Models: Hands-On Tutorial

Fine-tuning Llama Models Overview End-to-end Llama 3 fine-tuning with custom datasets. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl accelera

Intermediate

Fine-tuning LLMs Best Practices: 2026 Developer Guide

Fine-tuning LLMs Best Practices 2026 Introduction Following best practices for fine-tuning llms is the difference between fragile prototypes and production-grade AI systems. This guide covers the most important practices that experienced AI develop

Advanced

Fine-Tuning LLMs in 2025: When to Do It and How to Do It Right

Fine-tuning is often unnecessary—but when it's the right choice, it delivers significant improvements. This guide covers: when fine-tuning beats prompt engineering (with decision framework), LoRA and QLoRA parameter-efficient fine-tuning explained, preparing training data (quality over quantity), evaluating fine-tuned models, deploying fine-tuned models in production, and cost analysis across fine-tuning providers (OpenAI, Together AI, Fireworks AI, self-hosted). Includes hands-on examples with real training code.

Advanced

Fine-tuning Mistral Models: Hands-On Tutorial

Fine-tuning Mistral Models Overview Mistral 7B fine-tuning for domain specialization. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl accelerat

Advanced

Full Fine-tuning with FSDP: Hands-On Tutorial

Full Fine-tuning with FSDP Overview Full model fine-tuning using Fully Sharded Data Parallel. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl a

Advanced

How to Fine-tune Llama 3 on Custom Data: Complete Guide for Developers 2026

How to Fine-tune Llama 3 on Custom Data 2026 Introduction In this tutorial, you'll learn how to **Fine-tune Llama 3 on Custom Data**. By the end, you'll have a working **specialized AI model** that you can deploy and extend. **Prerequisites:** - E

Advanced

Hugging Face SFT Trainer: Hands-On Tutorial

Hugging Face SFT Trainer Overview Supervised fine-tuning with Hugging Face TRL SFTTrainer. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl acce

Advanced

Hugging Face Transformers: Custom Training Pipelines and Advanced Fine-Tuning

Advanced guide to Hugging Face Transformers including custom Trainer configurations, efficient training with gradient checkpointing, PEFT techniques, and deployment with Inference Endpoints.

Advanced

Instruction Fine-tuning: Hands-On Tutorial

Instruction Fine-tuning Overview Fine-tuning LLMs to follow instructions with supervised learning. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft

Intermediate

Large Model Post-Training in Practice: From SFT to RL — The Complete Tech Stack

This article systematically explains the key techniques of large model post-training, including supervised fine-tuning (SFT), parameter-efficient fine-tuning (PEFT), reinforcement learning from human feedback (RLHF), and on-policy distillation (OPD). It focuses on the principles, pros and cons, and applicable scenarios of each method, and introduces a stability-plasticity trade-off framework to quantify the general capability loss caused by fine-tuning. By comparing the forgetting characteristics of full fine-tuning, LoRA, OFT, and other PEFT methods, it reveals that the destruction of activation space geometric structure is the key mechanism of forgetting. Finally, it summarizes the advantages of OPD as a new paradigm and provides practical guidelines and FAQs.

Advanced

Fine-Tuning LLMs for Domain-Specific Applications

A comprehensive guide to fine-tuning LLMs for specialized domains including medical, legal, financial, and technical applications. Covers data preparation, training strategies, and evaluation.

Advanced

LLM Fine-Tuning in 2025: When to Fine-Tune vs. RAG vs. Prompting (With Cost Analysis)

Decision framework and technical guide for LLM customization — comparing fine-tuning vs. RAG vs. prompting for different use cases, with real cost analysis and step-by-step fine-tuning with OpenAI and LoRA.

Advanced

LLM Fine-Tuning Practical Guide 2026: From Data Preparation to Deployment, a Complete Model Customization Workflow

LLM fine-tuning has become more accessible in 2026, but it's not a silver bullet. This article covers the decision principles between fine-tuning and prompt engineering, and the complete workflow for efficient fine-tuning with Unsloth + LoRA, including data preparation, training configuration, evaluation, and deployment.

Advanced

LLM Fine-Tuning for Production: LoRA, QLoRA & RLHF in 2025

Fine-tuning LLMs allows adapting powerful foundation models to specific domains without training from scratch. This guide covers LoRA and QLoRA for parameter-efficient fine-tuning, dataset preparation and quality filtering, instruction tuning format, RLHF and DPO for alignment, fine-tuning on consumer GPUs with quantization, evaluation with domain benchmarks, and deploying fine-tuned models with vLLM or TGI for production serving.

Advanced

LLM Fine-tuning with LoRA: Complete Developer Guide 2026

A complete guide to fine-tuning large models with LoRA (2026): freeze the base model, train only low-rank adapters, finish in hours on a single GPU; QLoRA trains adapters on a 4-bit base. Includes real PEFT code, when to fine-tune (vs. prompting/RAG), and practical tips that data quality > quantity.

Advanced

LLM Inference Optimization: vLLM, TensorRT-LLM & Quantization in 2025

Serving LLMs in production requires careful optimization to achieve cost-effective performance at scale. This guide covers continuous batching with vLLM, NVIDIA TensorRT-LLM for GPU-optimized inference, speculative decoding, flash attention, KV cache optimization, INT4/INT8 quantization with AWQ and GPTQ, and benchmarking LLM serving systems to find the right performance/cost tradeoff.

Advanced

LoRA Fine-tuning Guide: Hands-On Tutorial

LoRA Fine-tuning Guide Overview Low-Rank Adaptation for efficient LLM fine-tuning. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl accelerate b

Advanced

Fine-Tuning LLMs with LoRA and QLoRA: Complete Guide 2026

Complete guide to fine-tuning large language models using LoRA and QLoRA techniques in 2026. Covers dataset preparation, training configuration, hardware requirements, evaluation metrics, and deploying fine-tuned models to production.

Advanced

Merging Fine-tuned Models: Hands-On Tutorial

Merging Fine-tuned Models Overview Combining multiple LoRA adapters with model merging. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl acceler

Advanced

Multi-Agent System Performance Optimization: A Comprehensive Guide from Topology to Training

Multi-agent system performance optimization is a key challenge in deploying MAS. This article explores four dimensions: prompt optimization under fixed topology (MASPOB), streaming communication acceleration (StreamMA), multi-agent reinforcement learning framework (UnityMAS-O), and decentralized market mechanism (EoM). These methods address evaluation efficiency, latency bottlenecks, training abstraction, and coordination costs, providing systematic technical paths for building efficient and scalable multi-agent systems.

Advanced

Multi-task Fine-tuning: Hands-On Tutorial

Multi-task Fine-tuning Overview Training on multiple tasks simultaneously for generalization. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl a

Advanced

PEFT: Parameter-Efficient Methods: Hands-On Tutorial

PEFT: Parameter-Efficient Methods Overview Overview of all parameter-efficient fine-tuning approaches. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets p

Advanced

QLoRA: Quantized LoRA: Hands-On Tutorial

QLoRA: Quantized LoRA Overview Combining quantization with LoRA for 4-bit fine-tuning. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl accelera

Advanced

Quantization for Production

Quantization for Production Overview Reducing model size and latency through quantization techniques. This guide covers practical implementation for production ML systems. Why This Matters in MLOps Modern ML systems require rigorous operations pr

Advanced

RLHF vs DPO: Training LLMs from Human Feedback - Technical Guide 2025

A guide to preference learning for alignment (2026): turning a base model into a helpful, harmless, honest assistant. RLHF (SFT + reward model + PPO) is complex but powerful; DPO uses a single preference loss, skipping the reward model and RL, making it simpler and more stable. Includes a comparison table and variants like IPO/KTO.

Intermediate

RLHF Step-by-Step Guide

RLHF Step-by-Step Guide Overview Reinforcement Learning from Human Feedback implementation tutorial. This guide covers practical implementation strategies for production AI systems. Why It Matters As AI systems grow more capable and widely deploy

Advanced

RLHF Training Pipeline: Hands-On Tutorial

RLHF Training Pipeline Overview Reward modeling and PPO for RLHF fine-tuning. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl accelerate bitsan

Advanced

Unsloth Fast Fine-tuning: Hands-On Tutorial

Unsloth Fast Fine-tuning Overview 2x faster fine-tuning with Unsloth optimization library. This tutorial provides a complete, runnable implementation. Prerequisites ```bash Install required packages pip install transformers datasets peft trl acce