Tagged articles
model fine-tuning
71 articles · Page 1 of 1
LobeHub's open-source multi-agent system implements DeepSeek's Super-agent principles in production, using Manager/Worker division, task-based workflows, event-driven filtering, three-layer compute/state/environment separation, and an acceptance system with data flywheel for model fine-tuning — all while dogfooding the platform to develop itself.
AI agent orchestrationAcceptance TestingDeepSeek
0 likes · 17 min read

A modified Qwen3.8-27B model achieves 735 ARC-C and 882 ARC-E scores while slashing reasoning tokens up to 10x through TURBO thinking reduction, Cold Fusion training with GAIN dynamic scheduling, Heretic+ARA uncensoring, and Dual iMatrix+MTP quantization for consumer GPU deployment.
ARC benchmarkGGUFMTP
0 likes · 12 min read

The community‑fine‑tuned Qwen3.6-27B‑Fable‑Fusion‑711 model combines multi‑stage fine‑tuning, model fusion and uncensored processing, delivers a 0.711 ARC‑C score that surpasses the original on six of seven benchmarks, and offers a rich set of GGUF quantizations with detailed performance guidance for local deployment.
AIGGUFQwen3.6-27B
0 likes · 10 min read

This guide outlines a comprehensive learning roadmap for large‑model application engineers, covering fundamentals such as Transformer architecture and scaling laws, practical API usage, prompt engineering, retrieval‑augmented generation, agent design, engineering best practices, security, observability, cost optimization, and fine‑tuning principles.
AI agentsAgent ArchitecturePrompt engineering
0 likes · 14 min read

The article analyzes why existing audio‑video QA pipelines break narrative continuity, proposes a structured‑script and evidence‑chain approach to automatically build the OmniVideo-100K dataset of 100K high‑quality QA pairs, and shows that fine‑tuning open‑source multimodal models on this data yields consistent accuracy gains across multiple benchmarks.
OmniVideo-100Kaudio-video datasetbenchmark evaluation
0 likes · 12 min read

The article details a systematic practice—starting from the “iceberg” challenges of finance, through data and knowledge engineering, reverse knowledge extraction with REER, multi‑dimensional synthetic data generation, prompt engineering (APO), cost‑aware fine‑tuning, inference acceleration, and emotion‑value evaluation—culminating in actionable guidelines for deploying large models in banking scenarios.
Knowledge EngineeringPrompt Optimizationemotion evaluation
0 likes · 14 min read

After a team fine‑tuned a customer‑service model with internal complaint data, the article shows why AI‑driven data quickly becomes unaccountable, then presents a three‑step protocol—weight table, automatic log generation, and commercial‑benefit mapping—to transparently trace contributions and prevent ghost‑labor disputes.
AI data provenanceAI governanceasset ownership
0 likes · 6 min read

The article explains how to transform a pretrained speech model into a product‑ready assistant by defining demonstration data, clarifying team debates on persona, safety, and length, contrasting alignment with pretraining, and highlighting common pitfalls to avoid during deployment.
Data AnnotationDialogue SystemsSpeech AI
0 likes · 6 min read

A new study by USTC and Shanghai AI Lab uncovers a power‑law scaling relationship between RL fine‑tuning compute and large‑model reasoning performance, offering a quantitative way to predict and control AI capability growth.
AI researchReinforcement LearningScaling Law
0 likes · 7 min read

The article introduces mlx‑tune, a community project that wraps the MLX library with Unsloth's API to enable local fine‑tuning of large language, vision, TTS, STT, OCR, and embedding models on Apple Silicon Macs, outlines its workflow from prototype to cloud, provides installation steps, code examples, and discusses its capabilities and limitations.
Apple SiliconUnsloth APIlarge language models
0 likes · 9 min read

The article outlines a step‑by‑step learning roadmap for AI Agent development, covering large‑model fundamentals, prompt engineering, retrieval‑augmented generation, agent architecture, production practices, and fine‑tuning concepts to help engineers progress from entry‑level to senior roles.
AI AgentPrompt engineeringRAG
0 likes · 9 min read

This article analyzes why multimodal large language models often fail to detect small objects, identifies three core bottlenecks, and presents a four‑tiered optimization roadmap—from zero‑cost inference tricks to data augmentation, model fine‑tuning, and engineering safeguards—backed by three real‑world case studies and actionable guidelines.
Data AugmentationInference Optimizationmodel fine-tuning
0 likes · 20 min read

The article explains how Amazon Bedrock’s reinforced fine‑tuning and SageMaker AI’s new serverless model‑customization dramatically lower the cost and latency of AI agents, delivering up to a 73% accuracy boost and shrinking model‑building cycles from months to days for enterprises of any size.
AI AgentAmazon BedrockAmazon SageMaker
0 likes · 9 min read

This article systematically reviews the main reinforcement‑learning algorithms—PPO, GRPO, DAPO, GSPO, and SAPO—used for fine‑tuning large language models, explaining why supervised fine‑tuning precedes RL, how each method improves training efficiency and stability, and what trade‑offs they entail.
GRPOPPORL
0 likes · 15 min read


Amap TechJan 8, 2026 · Artificial Intelligence
This article details the AI techniques behind Gaode's "Street Ranking" project, explaining the Fancy video concept, the dual training and production pipelines, and the use of SFT, reinforcement learning, MoE‑LoRA, distribution‑matching distillation, and quality‑filtering to achieve 25× faster generation with high aesthetic fidelity.
AI Video GenerationReinforcement Learningdistillation
0 likes · 24 min read

The article examines why AI product managers repeatedly fall into three traps—over‑relying on prompt engineering, blindly adopting Retrieval‑Augmented Generation, or costly fine‑tuning—by presenting real‑world failures, debunking myths, and offering a five‑layer decision framework with cost, data, resource, and risk analysis to choose the right solution.
AI Product ManagementDecision FrameworkPrompt engineering
0 likes · 24 min read

This article explains how Xiaomi’s Xiao AI assistant leverages large language models for intent routing, domain‑specific intent understanding, and response generation, detailing the system architecture, challenges such as knowledge requirements and latency constraints, and the shift from prompt engineering to model fine‑tuning.
AI assistantIntent RoutingPrompt engineering
0 likes · 5 min read

This article explains how large language models are integrated into Xiaomi’s Xiao AI assistant, covering intent distribution, domain‑specific intent understanding, response generation, architectural design, challenges such as knowledge requirements and latency, and the shift from prompt engineering to model fine‑tuning.
AI assistantIntent RoutingPrompt engineering
0 likes · 5 min read

This article explains how Xiaomi’s XiaoAI assistant integrates large language models for intent distribution, vertical intent understanding, and response generation, detailing the architecture, challenges such as knowledge requirements and sub‑200 ms latency, and the shift from prompt engineering to model fine‑tuning that boosted user retention by 10% and query satisfaction by 8%.
AI assistantIntent RoutingPrompt engineering
0 likes · 4 min read

This article explores how large language models are integrated into Xiaomi’s XiaoAI assistant, detailing the system’s architecture, intent distribution, domain-specific understanding, and response generation, while sharing practical challenges, prompt engineering solutions, and fine‑tuning strategies that boosted user retention and query satisfaction.
AI assistantsIntent RoutingXiaoAI
0 likes · 4 min read

This comprehensive guide walks you through generative AI fundamentals—including transformers, diffusion models, large language models, and multimodal systems—then explores practical API usage with OpenAI, Hugging Face, and Vertex AI, followed by model fine‑tuning, LoRA, knowledge injection, and advanced topics such as model distillation, prompt chaining, AutoML, tool integration, and retrieval‑augmented generation.
AutoMLPrompt engineeringmodel fine-tuning
0 likes · 3 min read

This guide shows how to fine‑tune the Amazon Nova Canvas foundation model on Amazon Bedrock using a 12‑hour workflow that extracts character frames from video with Amazon Rekognition, prepares labeled data, configures hyper‑parameters, creates a custom model, deploys it with provisioned throughput, and tests the model to generate coherent storyboard images, while also covering cleanup steps to avoid ongoing costs.
AI storyboardAmazon BedrockAmazon Nova Canvas
0 likes · 17 min read


Amap TechAug 7, 2025 · Artificial Intelligence
This article describes how the Gaode terminal team tackled large‑scale repository upgrades by building a code‑RAG and code‑Agent tool, addressing recall and stability issues, then fine‑tuning a small LLM (Qwen3‑4B) with LoRA and custom datasets to achieve reliable, low‑cost, on‑device code‑query performance.
Code AgentLLMLoRA
0 likes · 11 min read

This article introduces the open‑source Zhi‑Create‑Qwen3‑32B model, detailing its fine‑tuned training on creative‑writing data, the multi‑domain dataset strategy, curriculum‑learning based SFT, evaluation on WritingBench, and practical deployment options across various hardware and inference frameworks.
creative writingdeploymentevaluation
0 likes · 11 min read

This article describes how a video review system combines multimodal CLIP models, image‑text feature alignment, and optimized vector‑search databases such as RedisSearch and Elasticsearch to detect prohibited content in real time and perform large‑scale historical recall, while addressing challenges of generalization, storage cost, and inference speed.
AICLIPVector Search
0 likes · 18 min read


ITPUBJul 7, 2025 · Operations
This article presents a comprehensive blueprint for constructing a DeepSeek-powered AI Ops platform, detailing the six‑module architecture, data collection stack, AI engine deployment options, application and interaction layers, implementation road‑map, model training, security measures, cost estimates, and risk mitigation strategies.
AI OpsDeepSeekInfrastructure as Code
0 likes · 8 min read

In a detailed interview, ByteDance AI specialist Cai Conghuai explains how large‑model techniques such as SFT, DPO and RAG address Douyin’s multimodal user‑experience challenges, improve signal detection, root‑cause analysis, and outline future AI‑agent breakthroughs for content platforms.
AI AlgorithmsRAGUser Experience
0 likes · 11 min read

This paper introduces the Thought Leap Bridge task and the CoT‑Bridge model, which detect and fill missing intermediate steps in chain‑of‑thought reasoning, dramatically improving large language model performance on mathematical and logical benchmarks and enhancing downstream distillation and reinforcement‑learning pipelines.
Chain-of-ThoughtCoT-BridgeLLM
0 likes · 8 min read

The article argues that despite the rapid rise of powerful large language models, mastering machine learning remains essential because it underpins these models, offers customized solutions for specialized tasks, and cultivates the mathematical, programming, and analytical skills needed to effectively use and extend AI technologies.
AIEducationlarge language models
0 likes · 10 min read

This article explores the application of Large Language Models (LLM) in text information detection and extraction, focusing on blue-collar recruitment data processing. It details the implementation of LLM through prompt engineering, RAG enhancement, and model fine-tuning to improve data cleaning efficiency and accuracy.
AI applicationsLLMPrompt engineering
0 likes · 31 min read

This article explains the concept of tool-specific tokens for large language models, detailing how they enable efficient, reliable tool calls, the implementation steps, advantages over JSON, practical advice, comparisons, challenges, and future directions for AI agents.
LLMmodel fine-tuningspecial tokens
0 likes · 10 min read


ArchitectApr 1, 2025 · Artificial Intelligence
The article explains why most projects should start with prompt engineering or simple agent workflows, outlines the scenarios where model fine‑tuning adds real value, compares fine‑tuning with Retrieval‑Augmented Generation, and offers practical criteria for deciding which approach to adopt.
AI DeploymentLoRARAG
0 likes · 9 min read

This guide walks you through fine‑tuning a large language model without any coding by using LLaMA‑Factory, covering LoRA fundamentals, environment setup, dataset creation, parameter configuration, training, loss monitoring, model export, and a quick evaluation on the Qwen2.5‑0.5B model.
AnacondaLLaMA-FactoryLoRA
0 likes · 15 min read

This article explains what constitutes high‑quality LLM training data, why large datasets are essential, outlines the step‑by‑step process for collecting, preprocessing, and fine‑tuning models, and highlights the best data sources—including web content, books, code repositories, and news—while noting available free datasets.
AILLMdata collection
0 likes · 9 min read

This tutorial shows how to use Alibaba Cloud DataWorks' serverless GPU resource groups together with the open‑source LLaMA‑Factory framework to fine‑tune the Qwen2‑VL‑2B multimodal model for tourism‑domain Q&A, covering environment setup, dataset preparation, parameter configuration, training, and interactive inference.
DataWorksGPULLaMA-Factory
0 likes · 10 min read

Experts from Dipu, Ant Financial, iKang, and Zhihu discuss practical strategies for improving large model performance, covering RAG, tool‑using, offline knowledge engineering, multimodal training, evaluation metrics, and future trends, while sharing case studies from manufacturing, healthcare, retail, and C‑end applications.
Knowledge EngineeringRAGlarge language models
0 likes · 9 min read

The article outlines eight distinct enterprise strategies for adopting DeepSeek, categorizing them by model maturity, available data types, and specific business challenges, and maps these approaches onto four capability tiers—from basic compliance requirements to advanced multimodal, low‑cost solutions.
AI agentsDeepSeekRAG
0 likes · 3 min read

This guide walks you through the hardware and software prerequisites, Docker-based installation, environment configuration, model fine‑tuning, IDE integration, maintenance, and troubleshooting for running the DeepSeek AI programming assistant entirely on your own machine.
AI coding assistantDeepSeekDocker
0 likes · 12 min read

This article presents a detailed overview of generative AI lifecycle management, covering practical use cases such as email summarization, the roles of providers, fine‑tuners and consumers, MLOps/LLMOps processes, retrieval‑augmented generation, efficient fine‑tuning methods like PEFT, and Amazon Bedrock services for model deployment and monitoring.
Amazon BedrockLLMOpsMLOps
0 likes · 14 min read

This guide walks you through deploying the GPT‑SoVITS text‑to‑speech model on Alibaba Cloud Function Compute, covering architecture, step‑by‑step deployment, quick voice synthesis, and advanced fine‑tuning using NAS storage, VPC networking, and optional custom domains.
AI voice synthesisFunction ComputeGPT-SoVITS
0 likes · 12 min read

This article examines how programming large models combined with code knowledge graphs can overcome the limited context of traditional code‑completion tools, detailing key techniques, trigger strategies, context acquisition methods, model fine‑tuning practices, current challenges, and future research directions for intelligent, repository‑wide code suggestions.
AI programmingcode completionknowledge graph
0 likes · 14 min read

This article explains how to preprocess diverse error messages from apps, mini‑programs, and browsers, then fine‑tune a small spaCy NLP model with data generated via ChatGPT to automatically split and categorize errors for alerting and workflow handling.
AIPythonerror monitoring
0 likes · 8 min read

The article introduces Marco‑o1, an open‑source LLM that enhances complex reasoning by fine‑tuning on Chain‑of‑Thought data, integrating Monte‑Carlo Tree Search, introducing mini‑step actions and a reflection mechanism, and evaluates its performance on multilingual math and translation benchmarks.
LLMMonte Carlo Tree Searchartificial intelligence
0 likes · 15 min read

This article examines the AIGC engineering architecture, detailing its data, model, fine‑tuning, inference, application, and monitoring layers, and explains the distinct responsibilities and challenges of application engineers, algorithm engineers, and “alchemy” specialists, highlighting how this structured approach accelerates generative AI productization.
AI DeploymentAIGCEngineering Architecture
0 likes · 24 min read

By leveraging multimodal large models such as GPT‑4o and fine‑tuned Qwen‑VL, the study builds a prompt‑engineered and SFT‑enhanced voucher verification system that classifies product categories, detects diverse defects, and estimates problem counts, achieving up to 90 % accuracy and meeting real‑time business throughput requirements.
Prompt engineeringe-commercemodel fine-tuning
0 likes · 10 min read

The open‑source Yuan 2.0 large model is fully integrated into Baidu’s PaddleNLP, offering quick inference for tasks like code generation, translation, and reasoning, along with efficient distributed training and fine‑tuning features such as Zero Padding optimization, enabling developers to easily deploy and customize the model via simple setup steps and example interactions.
AIJavaLLM
0 likes · 10 min read

The article describes a multimodal AI video moderation system built on Alibaba’s Chinese‑CLIP model and hybrid RedisSearch/ElasticSearch vector databases, enabling real‑time violation detection and historical recall, with fine‑tuned black‑market ad detection, FP16 quantization, and OpenVINO acceleration to boost speed and cut storage.
Chinese CLIPContent moderationImage-Text Matching
0 likes · 16 min read

This article provides an in‑depth, step‑by‑step guide on how enterprises can choose between open‑source and closed‑source large language models, adapt them through incremental pre‑training, instruction fine‑tuning, and reinforcement learning, and finally deploy them across front‑office, middle‑office, and back‑office scenarios to drive digital transformation.
RLHFenterprise AIlarge language models
0 likes · 28 min read

This guide walks you through using Alibaba Cloud PAI and the open‑source LLaMA Factory framework to fine‑tune a Llama‑3 8B model for Chinese dialogue and role‑playing, create a “Zhuge Liang” chatbot, evaluate its performance, and clean up resources.
Alibaba Cloud PAILLaMA-FactoryLoRA
0 likes · 12 min read

This article presents a comprehensive knowledge map for developing large‑model applications, covering a four‑layer technical architecture, the full development lifecycle, core elements such as prompt engineering and model fine‑tuning, evaluation methods, and practical case studies, offering guidance for both enterprises and startups.
AI application developmentPrompt engineeringevaluation
0 likes · 15 min read

This article presents Fudan University's Knowledge Factory Lab research on domain large models, covering background, challenges, data selection, source‑enhanced tagging, capability improvements, self‑correction, collaborative workflows, and retrieval‑augmented generation for practical AI deployment.
AI researchSelf-Correctiondomain adaptation
0 likes · 16 min read

Qwen2, Alibaba Cloud's new open‑source LLM series, offers five model sizes with GQA acceleration, and through PAI‑QuickStart developers can zero‑code fine‑tune, evaluate, and deploy these models using cloud resources, SDKs, and OpenAI‑compatible APIs.
AI DeploymentPAI-QuickStartPython SDK
0 likes · 10 min read


58 TechJun 3, 2024 · Artificial Intelligence
This article systematically analyzes popular parameter‑efficient fine‑tuning (PEFT) techniques for large language models—including Adapter Tuning, Prefix Tuning, LoRA, QLoRA, AdaLoRA, and SoRA—detailing their principles, implementation code, experimental results on NLU tasks, and practical acceleration using the Unsloth library.
AdaLoRALoRAPEFT
0 likes · 39 min read

The guide explains why generic LLMs struggle with enterprise tasks and outlines two remedies—retrieval‑augmented generation and domain‑specific fine‑tuning—detailing dataset creation, training strategies (full‑parameter, LoRA, Q‑LoRA), validation methods, hardware benchmarks, and practical tips such as supervised fine‑tuning, 30% domain data, and a stepwise tuning pipeline.
AIdataset constructiondomain-specific LLM
0 likes · 16 min read

In his Create 2024 AI Developer Conference keynote, Li Yanhong outlines Baidu’s latest large‑model series, AI‑native development platforms (AgentBuilder, AppBuilder, ModelBuilder), performance breakthroughs, real‑world case studies, and the strategic vision that makes AI development accessible to all developers and enterprises.
AIdeveloper toolsindustry trends
0 likes · 28 min read

This article explains the motivation behind Self‑RAG, describes its core workflow—including conditional retrieval, enhanced generation, and self‑evaluation tokens—details the four evaluation metrics (Retrieve, IsRel, IsSup, IsUse), and provides a Python scoring example using log‑probabilities.
Evaluation MetricsLLMLogprobs
0 likes · 13 min read

This article outlines a comprehensive knowledge map for building large‑model applications, detailing a four‑layer technical architecture, development lifecycle, core elements such as prompt engineering and fine‑tuning, evaluation methods, and real‑world case studies across various AI use cases.
AI application developmentlarge language modelsmodel fine-tuning
0 likes · 12 min read

Baidu’s Qianfan Large Model Platform provides a one‑stop enterprise solution with 54 pre‑installed models, advanced fine‑tuning, comprehensive evaluation metrics, and optimized deployment that cuts costs up to 90% and boosts throughput 3‑5×, enabling rapid, affordable AI application development.
AI-native applicationsBaidu QianfanCost Optimization
0 likes · 12 min read

This article explains the principle of LoRA (Low‑Rank Adaptation) for large language models, demonstrates how to decompose weight updates into low‑rank matrices, and provides a complete PyTorch implementation that fine‑tunes a small VGG‑19 network on a custom goldfish dataset.
LoRAPyTorchdeep learning
0 likes · 11 min read


phodalDec 25, 2023 · Artificial Intelligence
This article explains how the open‑source AutoDev plugin builds an end‑to‑end AI‑assisted coding solution that fine‑tunes open LLMs, constructs a Unit Eval dataset, engineers prompts for unit‑test generation, and enforces quality through a unified write‑evaluate pipeline.
AIJavaSpring
0 likes · 9 min read

The article examines how enterprises can adopt domain‑specific large models by balancing demand‑side cost‑reduction needs with supply‑side mature training techniques, discusses team composition, fine‑tuning methods, data governance for unstructured data, and outlines Deepexi’s product ecosystem designed to improve efficiency, performance, and user experience.
AI Deploymentcost economicsenterprise AI
0 likes · 13 min read

The article examines how enterprises can adopt domain‑specific large models by addressing talent and cost challenges, outlining self‑supervised pre‑training, instruction fine‑tuning, data governance for unstructured data, dataset balance, model‑type selection, and integrated product solutions to achieve efficient, high‑performance AI deployments.
AI Deploymentcost economicsdata governance
0 likes · 13 min read

The article explores how enterprises can adopt domain‑specific large language models by addressing talent and cost challenges, outlining training pipelines, data governance for unstructured data, dataset balancing, fine‑tuning techniques, and a product ecosystem that lowers deployment barriers while optimizing performance and economics.
AI DeploymentDomain Modelscost economics
0 likes · 13 min read

This article details how Zhihu's internal Bridge platform integrates large language models for business analysis, knowledge taxonomy, natural‑language‑to‑filter conversion, and ad‑hoc data queries, describing the workflow, technical hurdles, iterative improvements, and future directions.
AI for business analyticsPrompt engineeringknowledge taxonomy
0 likes · 12 min read

The article reviews the rapid evolution of open‑source large language models, detailing Meta’s Llama 2 series and Tsinghua’s ChatGLM 2, their enhanced capabilities such as RLHF, larger context windows, safety‑usefulness trade‑offs, performance gains, download and fine‑tuning procedures, and how they increasingly rival proprietary models like GPT‑4.
AIChatGLM2Llama2
0 likes · 10 min read

This article explains the evolution from traditional machine learning to the current large‑model era, introduces LMOps concepts and key technologies, compares them with MLOps, and showcases Baidu Cloud's Qianfan platform as a practical solution for building, deploying, and managing large language models in industry.
AI operationsBaidu CloudLMOps
0 likes · 22 min read

The article explains how LoRA and its 4‑bit QLoRA extension dramatically reduce trainable parameters and GPU memory for fine‑tuning large language models, while GPTQ post‑training quantization compresses weights for cheap inference, and shows how KubeAI integrates these techniques into a one‑click workflow for 7 B, 13 B, and 33 B models from data upload to API deployment.
GPTQKubeAILoRA
0 likes · 13 min read

This article introduces the upgraded PAI‑Diffusion Chinese models, highlighting major improvements in image quality and style diversity, detailing lightweight fine‑tuning methods such as LoRA and Textual Inversion, showcasing controllable editing, scenario‑specific customization, and providing step‑by‑step usage instructions on popular platforms.
AILoRATextual Inversion
0 likes · 14 min read

This article introduces a continuous semantic enhancement approach for neural machine translation that overcomes the limitations of discrete data‑augmentation techniques, details the neighbor risk minimization training objective, presents benchmark improvements on ACL‑2022 datasets, and describes practical deployment and fine‑tuning workflows in the Modu community.
Contrastive LearningData Augmentationcontinuous semantic augmentation
0 likes · 19 min read


ArchitectApr 24, 2023 · Artificial Intelligence
The article details the evolution of the open‑source MOSS series—from OpenChat 001 to MOSS 003—covering data collection, fine‑tuning procedures, multilingual capabilities, plugin architecture, example code for inference, and upcoming releases, providing a comprehensive technical overview for AI practitioners.
AIMOSSTransformers
0 likes · 11 min read

This article introduces EasyNLP's Chinese text‑to‑image generation framework, explains the underlying Transformer‑VQGAN architecture, provides model specifications, showcases sample outputs, and offers step‑by‑step code and command‑line instructions for fine‑tuning and inference.
Chinese AIEasyNLPTransformer
0 likes · 20 min read
