最新博客文章
21 / 200AI 开发实战教程，从零到一构建你的 AI 应用。
All200
Beginner32
Intermediate92
Advanced76
All
Prompt Engineering12
RAG Retrieval Augmented17
Agent Development34
Model Fine-tuning21
Deployment and Operations25
AI Application Development40
DeepSeek API16
Multimodal Development6
AI Safety6
Model Inference3
Retrieval Systems1
RAG Retrieval1
Model Architecture3
API Development1
Agent Development10
Model Deployment1
Multimodal1
Model Evaluation2
Tutorial
Date
DeepSeek Data Engineering Tutorial
Model Fine-tuning
Advanced
From data collection to quality evaluation, fully master the large model data engineering pipeline. Covers core aspects such as SFT dataset construction, RLHF preference data preparation, data cleaning and deduplication, data augmentation, and large-scale data processing.
DeepSeek Model Architecture Deep Dive
Model Fine-tuning
Advanced
In-depth analysis of DeepSeek-V3's core technologies such as MoE architecture, MLA attention mechanism, and Multi-Token Prediction. Understand how DeepSeek achieves GPT-4o-level performance at extremely low cost, including architecture diagrams and source code analysis.
Model Distillation in Practice: Training Small Models with Large Models
Model Fine-tuning
Advanced
Knowledge distillation allows small models to approach large model capabilities while significantly reducing inference costs. This article provides an in-depth explanation of distillation principles, data generation strategies, training techniques, and effect evaluation, teaching you to distill cost-effective small models with DeepSeek.
QLoRA Quantized Fine-Tuning in Practice
Model Fine-tuning
Intermediate
QLoRA reduces the memory requirements for fine-tuning large models to the extreme through 4-bit quantization. This article provides an in-depth explanation of QLoRA's technical principles, NF4 quantization, double quantization, and other key technologies, along with complete practical code.
DeepSeek Fine-tuning Hands-on Tutorial
Model Fine-tuning
Advanced
Full practical guide to fine-tuning DeepSeek models: LoRA/QLoRA efficient fine-tuning, full-parameter fine-tuning, data preparation, training configuration, and evaluation validation. Covers fine-tuning solutions for DeepSeek-V3 and DeepSeek-R1, including complete code and best practices.
Practical Guide to QLoRA Fine-Tuning
Model Fine-tuning
Intermediate
Full-parameter fine-tuning is expensive; QLoRA uses 4-bit quantization and low-rank adaptation to allow ordinary developers to fine-tune large models on consumer-grade GPUs. This article provides a hands-on guide to the complete QLoRA fine-tuning process from data preparation to model deployment, using DeepSeek as the base model.
Model Compression: Where Quantization, Pruning, and Distillation Fit
Model Fine-tuning
Advanced
Quantization, pruning, and distillation are often compared in isolation, so it's hard to tell whether a compression win is real or just moved cost. This article puts them on one ledger: bit width, grouping and outliers for weights, how GPTQ and AWQ treat error propagation differently, where KV Cache quantization and FP8 fit, and structured versus unstructured pruning.
Model Evaluation and A/B Testing
Model Fine-tuning
Advanced
After fine-tuning, how can you objectively evaluate model performance? How should A/B tests be designed to obtain statistically significant conclusions? This article establishes a scientific model evaluation system from three dimensions: offline evaluation, online A/B testing, and statistical significance.
RLHF Reinforcement Fine-Tuning in Practice: From Preference Data to Reward Model
Model Fine-tuning
Advanced
RLHF aligns model outputs with human preferences. This article walks through the complete RLHF pipeline, from preference data collection and reward model training to PPO reinforcement fine-tuning, and provides engineering insights on data quality and effect evaluation.
The Art of Building Fine-Tuning Datasets
Model Fine-tuning
Intermediate
The upper limit of fine-tuning effectiveness is determined by data quality, not the model or algorithm. This article delves into the methodology for building fine-tuning datasets, covering data sources, quality control, diversity assurance, and data mixing strategies, helping you build high-quality fine-tuning datasets.
Distributed Training of Large Models: Data, Tensor, Pipeline, and Expert Parallelism
Model Fine-tuning
Advanced
A single GPU cannot hold the model, so parallelism has to be chosen deliberately. Data, tensor, pipeline and expert parallelism are compared by communication pattern and usable scale: why tensor parallelism needs two all-reduces per layer, how communication grows with parallelism degree, how NVLink and cross-node bandwidth cap the choices, and what ZeRO 1/2/3 saves.
模型后训练
Model Fine-tuning
Intermediate
本书的核心公式是 Agent = LLM + 上下文 + 工具。本章聚焦于优化 LLM 这个“大脑”——先用 Mid-training 补齐目标领域的知识与基础能力，再用 SFT/RL 等后训练方法塑造模型利用上下文和工具的行为。第七章结尾指出，评估体系与仿真环境是后训练的两块基石：评估环境为训练提供练习场，评估指标为…
DeepSeek Model Evaluation and Benchmarking
Model Fine-tuning
Intermediate
Complete evaluation guide for DeepSeek models: results on mainstream benchmarks such as MMLU, HumanEval, GSM8K, and MT-Bench. Comprehensive comparison of DeepSeek-V3 vs GPT-4o vs Claude 3.5, including evaluation code and model selection recommendations.
Practical Model Quantization and Deployment
Model Fine-tuning
Intermediate
Quantization is a key technology to reduce model inference costs. This article systematically explains the principles, toolchains, and deployment practices of model quantization from INT8 to INT4, enabling your model to run efficiently on consumer-grade hardware.
Detailed Explanation of DPO Preference Alignment Training
Model Fine-tuning
Advanced
DPO (Direct Preference Optimization) is a simplified alternative to RLHF that does not require training a reward model. This article explains the principles, implementation details, and training techniques of DPO in depth.
Dataset Construction and Quality Evaluation
Model Fine-tuning
Advanced
Data quality determines the upper limit of fine-tuning effectiveness. This article systematically explains the construction methods of fine-tuning datasets, data cleaning strategies, quality evaluation metrics, and data augmentation techniques, helping you build high-quality fine-tuning datasets.
Comprehensive Comparison of LoRA vs QLoRA vs Full Fine-tuning
Model Fine-tuning
Intermediate
A comprehensive comparison of LoRA, QLoRA, and full fine-tuning, analyzing from the perspectives of principles, memory usage, training speed, and final performance, to help you make the right technology choice.
Synthetic Data Construction: From Self-Distillation to Adversarial Samples
Model Fine-tuning
Advanced
Model output can't be gold data, and this article starts there. It walks the synthetic data pipeline: the self-distillation and rejection-sampling loop, why distribution collapse is a probability rather than correctness problem, how to quantify the quality-diversity trade-off, curricula and bucketed sampling matched to model ability, and adversarial samples for error injection.
Complete Guide to LoRA Fine-Tuning
Model Fine-tuning
Beginner
LoRA is currently the most popular parameter-efficient fine-tuning method. This article comprehensively explains the complete LoRA fine-tuning process from principles to practice, including environment configuration, dataset preparation, training parameter settings, and model evaluation.
Complete Guide to Large Model Evaluation and Benchmarking
Model Fine-tuning
Intermediate
How to objectively evaluate the capabilities of large models? This article systematically explains mainstream benchmark tests such as MMLU, HumanEval, and C-Eval, as well as evaluation methods like LLM-as-Judge and arena rankings, to help you establish a scientific model evaluation system.
Practical Construction of Instruction Fine-Tuning Data
Model Fine-tuning
Intermediate
Data quality determines the upper limit of fine-tuning effectiveness. This article explains the construction methods for instruction fine-tuning data, including data sources, cleaning strategies, quality evaluation, data augmentation, and mixing design.
