BestHub
Sign in
Fun with Large Models
Author

Fun with Large Models

Master's graduate from Beijing Institute of Technology, published four top‑journal papers, previously worked as a developer at ByteDance and Alibaba. Currently researching large models at a major state‑owned enterprise. Committed to sharing concise, practical AI large‑model development experience, believing that AI large models will become as essential as PCs in the future. Let's start experimenting now!

115
Articles
0
Likes
218
Views
0
Comments
Recent Articles

Latest from Fun with Large Models

100 recent articles max
Fun with Large Models
Fun with Large Models
Mar 11, 2026 · Artificial Intelligence

LangChain DeepAgents Quick Guide – FileSystem Middleware Gives AI Agents System‑Level Memory Management

This article explains why AI agents need a memory‑management solution, introduces LangChain DeepAgents' FileSystem middleware, details its four backend options for short‑term, long‑term, disk‑based, and hybrid storage, and provides step‑by‑step Python examples for installing, configuring, and using the middleware in real‑world scenarios.

AI AgentDeepAgentsFileSystemMiddleware
0 likes · 16 min read
LangChain DeepAgents Quick Guide – FileSystem Middleware Gives AI Agents System‑Level Memory Management
Fun with Large Models
Fun with Large Models
Mar 8, 2026 · Artificial Intelligence

EasyDataset: End-to-End Guide for Generating QA Datasets for LLM Fine‑Tuning

This article walks through the complete workflow of using EasyDataset to create high‑quality question‑answer pairs for supervised fine‑tuning, covering question generation (single and batch), three generation algorithms, answer generation (including chain‑of‑thought and multi‑turn dialogue), a hybrid quality‑assessment pipeline, and export to Alpaca or ShareGPT formats.

Alpaca formatEasyDatasetKnowledge augmentation
0 likes · 18 min read
EasyDataset: End-to-End Guide for Generating QA Datasets for LLM Fine‑Tuning
Fun with Large Models
Fun with Large Models
Feb 27, 2026 · Artificial Intelligence

Step‑by‑Step EasyDataset Workflow for Building High‑Quality LLM Training Data

This guide walks readers through installing EasyDataset, creating a project, uploading documents, choosing appropriate chunking strategies, cleaning the data, generating domain tag trees, and exporting a polished pre‑training dataset, with concrete examples, configuration screenshots, and practical recommendations for each step.

AI modelEasyDatasetLLM data preparation
0 likes · 20 min read
Step‑by‑Step EasyDataset Workflow for Building High‑Quality LLM Training Data
Fun with Large Models
Fun with Large Models
Feb 25, 2026 · Artificial Intelligence

Fast Guide to LangChain DeepAgents: Using Summarization Middleware to Optimize Agent Memory

This article explains how LangChain DeepAgents' Summarization middleware automatically compresses conversation history to overcome large‑model context window limits, detailing its core mechanism, applicable scenarios, configuration parameters (trigger, keep, model, summary_prompt), and step‑by‑step Python examples that illustrate its integration and internal message flow.

AI AgentsDeepAgentsLangChain
0 likes · 23 min read
Fast Guide to LangChain DeepAgents: Using Summarization Middleware to Optimize Agent Memory
Fun with Large Models
Fun with Large Models
Feb 24, 2026 · Artificial Intelligence

DeepAgents Quickstart Guide: A Full Walkthrough of Core Features

This article introduces LangChain's DeepAgents framework, explains its design goals, compares it with LangChain and LangGraph, and provides a step‑by‑step code walkthrough that demonstrates task planning, sub‑agent delegation, tool usage, and result generation for building complex AI agents with just a few lines of code.

AI AgentsAgent orchestrationDeepAgents
0 likes · 15 min read
DeepAgents Quickstart Guide: A Full Walkthrough of Core Features
Fun with Large Models
Fun with Large Models
Feb 17, 2026 · Artificial Intelligence

Inside Qwen3.5: The World’s Strongest Open‑Source Multimodal Model and Its Core Features

Qwen3.5‑397B‑A17B, the newly open‑sourced multimodal giant, combines a 400‑billion‑parameter sparse MoE architecture with FP8 pipelines and an asynchronous RL framework to deliver GPT‑5.2‑level capabilities, 60% lower memory usage, up to 19× higher throughput, and extensive image, video, and agent support, while outlining its deployment requirements and API pricing.

AI inferenceFP8Sparse MoE
0 likes · 11 min read
Inside Qwen3.5: The World’s Strongest Open‑Source Multimodal Model and Its Core Features
Fun with Large Models
Fun with Large Models
Feb 10, 2026 · Artificial Intelligence

Building LangChain Agent Skills from Scratch to Cut Token Usage and Boost Tool Accuracy

The article presents a step‑by‑step design and implementation of a Claude‑style Skills mechanism for LangChain agents, using a double‑layer tool architecture, state‑driven dynamic filtering, and middleware interception to load only relevant tools, dramatically reducing token consumption and improving decision quality and response speed.

Agent skillsDynamic LoadingLangChain
0 likes · 15 min read
Building LangChain Agent Skills from Scratch to Cut Token Usage and Boost Tool Accuracy
Fun with Large Models
Fun with Large Models
Feb 8, 2026 · Artificial Intelligence

How the US‑China LLM ‘War’ Plays Out: Deep Dive into Claude Opus 4.6 vs GPT‑5.3 CodeX

The article provides a detailed technical comparison of Anthropic's Claude Opus 4.6 and OpenAI's GPT‑5.3 CodeX, covering performance gains, context window size, agent teamwork, programming benchmarks, new features such as adaptive thinking and interactive development, and offers guidance on choosing the right model for specific workflows.

AI model comparisonClaude Opus 4.6GPT-5.3-Codex
0 likes · 15 min read
How the US‑China LLM ‘War’ Plays Out: Deep Dive into Claude Opus 4.6 vs GPT‑5.3 CodeX
Fun with Large Models
Fun with Large Models
Feb 3, 2026 · Artificial Intelligence

OpenClaw Core Features and Architecture Explained (with LLM & Chat Integration)

OpenClaw, a 2026 open‑source AI agent, combines a protocol‑agnostic gateway, a four‑layer memory system, and an extensible Agent Skills framework to enable real‑time cross‑platform interaction, long‑term learning, and seamless integration with Chinese large language models and popular chat applications.

AI AgentAgent skillsChat Tool Integration
0 likes · 11 min read
OpenClaw Core Features and Architecture Explained (with LLM & Chat Integration)