BestHub
Sign in
Tagged articles

large language model

847 articles · Page 8 of 9
Bilibili Tech
Bilibili Tech
Jun 14, 2024 · Artificial Intelligence

Technical Report on the Index-1.9B Series: Model Variants, Pre‑training Optimizations, and Alignment Experiments

The report presents the open‑source Index‑1.9B family—base, pure, chat, and character variants—detailing benchmark results, pre‑training optimizations such as a normalized LM‑Head and deeper‑slim architectures, the importance of modest instruction data, alignment via SFT/DPO, role‑play enhancements with RAG, and acknowledges remaining safety and factual limitations.

LLMPretrainingalignment
0 likes · 15 min read
Technical Report on the Index-1.9B Series: Model Variants, Pre‑training Optimizations, and Alignment Experiments
JD Cloud Developers
JD Cloud Developers
Jun 6, 2024 · Artificial Intelligence

Boost Code Review Efficiency with AI-Powered CI Integration

This guide explains how embedding a large‑language‑model AI into a CI pipeline can automate code reviews, cut review time, improve consistency and accuracy, and ultimately raise development efficiency and code quality while reducing manual effort and communication overhead.

AICI/CDCode Review
0 likes · 9 min read
Boost Code Review Efficiency with AI-Powered CI Integration
Baidu Tech Salon
Baidu Tech Salon
May 30, 2024 · Artificial Intelligence

How AI Code Assistant Baidu Comate Boosted Medical Imaging Processing by 9×

A graduate student’s lab cut the time to process 150 GB of medical imaging data from one week for three people to two days for one person by using Baidu Comate’s AI‑driven code generation, annotation, and private‑knowledge enhancement features, achieving over nine‑fold productivity gains.

AI code assistantBaidu Comatecode generation
0 likes · 8 min read
How AI Code Assistant Baidu Comate Boosted Medical Imaging Processing by 9×
Baidu Geek Talk
Baidu Geek Talk
May 29, 2024 · Artificial Intelligence

How Baidu’s AI Code Assistant Boosted R&D Efficiency by Over 11% in Marketing Platforms

The article analyzes how Baidu's marketing service team leveraged the Wenxin large model and the Baidu Comate AI code assistant to accelerate product reconstruction, achieve AI‑native development, and quantify a daily engineering productivity gain of roughly 11.2% through reduced coding time and automated deployment workflows.

AI code assistantAI-Native DevelopmentBaidu Comate
0 likes · 13 min read
How Baidu’s AI Code Assistant Boosted R&D Efficiency by Over 11% in Marketing Platforms
21CTO
21CTO
May 28, 2024 · Artificial Intelligence

When Google’s AI Overview Hallucinates: Surprising Misanswers and What They Reveal

Google’s AI Overview, unveiled at I/O 2024, replaces traditional search results with AI‑generated summaries, but real‑world usage shows bizarre hallucinations—from claiming the internet is 100% true to recommending eating stones—highlighting the lingering challenges of large language models.

AI OverviewAI hallucinationGoogle AI
0 likes · 7 min read
When Google’s AI Overview Hallucinates: Surprising Misanswers and What They Reveal
JD Retail Technology
JD Retail Technology
May 27, 2024 · Artificial Intelligence

Automating Test Case Generation with Large Language Models and LangChain

This article describes how large language models and the LangChain framework can be combined with PDF parsing, text chunking, memory management, and a vector database to automatically generate software test cases, achieving significant efficiency gains while outlining implementation details, results, and future challenges.

AIPythonlangchain
0 likes · 10 min read
Automating Test Case Generation with Large Language Models and LangChain
21CTO
21CTO
May 23, 2024 · Artificial Intelligence

How xAI’s Grok 1.5V Adds Multimodal Image Input for Developers

xAI’s Grok 1.5V is set to support multimodal image input, allowing developers to upload pictures and receive text‑based answers via the Python SDK, marking a major upgrade that narrows the gap with leading models like GPT‑4 and signals a new frontier for AI chatbots.

AI chatbotsGrokPython SDK
0 likes · 4 min read
How xAI’s Grok 1.5V Adds Multimodal Image Input for Developers
Baidu Tech Salon
Baidu Tech Salon
May 22, 2024 · Industry Insights

How Baidu’s AI‑Powered Code Assistant Boosts R&D Efficiency by Over 11 %

The article examines Baidu Marketing Service's AI‑native transformation using the Wenxin large model and Baidu Comate, detailing how real‑time code recommendations, open‑platform integration, and generative AI dramatically improve developer productivity, reduce coding time, and increase marketing ROI.

AIAI-Native DevelopmentBaidu Comate
0 likes · 11 min read
How Baidu’s AI‑Powered Code Assistant Boosts R&D Efficiency by Over 11 %
NewBeeNLP
NewBeeNLP
May 20, 2024 · Artificial Intelligence

How RecGPT Leverages ChatGPT‑Style Prompt Tuning for Better Sequential Recommendation

RecGPT applies a ChatGPT‑like pre‑training and personalized prompt‑tuning paradigm to sequential recommendation, introducing a two‑stage recall mechanism that improves offline HR/NDCG metrics and yields modest online interaction gains in a real‑world short‑video platform.

Prompt TuningRecGPTauto-regressive pretraining
0 likes · 8 min read
How RecGPT Leverages ChatGPT‑Style Prompt Tuning for Better Sequential Recommendation
360 Tech Engineering
360 Tech Engineering
May 17, 2024 · Artificial Intelligence

360VL: An Open‑Source Multimodal Large Language Model Based on Llama‑3‑70B

The article introduces 360VL, an open‑source multimodal large language model built on Llama‑3‑70B, describes its novel C‑abs bridge architecture for high‑resolution visual understanding, outlines the two‑stage training with bilingual data, and presents benchmark results showing superior performance over prior LMMs.

AI researchLlama3Multimodal
0 likes · 8 min read
360VL: An Open‑Source Multimodal Large Language Model Based on Llama‑3‑70B
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
May 15, 2024 · Artificial Intelligence

OpenAI Unveils GPT‑4o: An Omni‑Capable Multimodal Model Offered Free to All Users

OpenAI introduced GPT‑4o, a free, omni‑capable multimodal model that processes text, audio, and images together, delivers near‑human response latency, showcases impressive live demos, and will soon be available via a discounted API, marking a significant step forward in end‑to‑end AI research.

AI researchGPT-4oOpenAI
0 likes · 7 min read
OpenAI Unveils GPT‑4o: An Omni‑Capable Multimodal Model Offered Free to All Users
CSS Magic
CSS Magic
May 13, 2024 · Artificial Intelligence

DeepSeek: China’s New LLM Dark Horse – First Impressions and Shockingly Low Prices

The article evaluates DeepSeek v2, a 100‑billion‑parameter MoE model, highlighting its near‑GPT‑4 benchmark performance, OpenAI‑compatible API, 32k‑token context, exceptionally low pricing, a custom token‑utilization metric, and the practical drawbacks observed during hands‑on testing.

API CompatibilityDeepSeekMoE
0 likes · 9 min read
DeepSeek: China’s New LLM Dark Horse – First Impressions and Shockingly Low Prices
Baobao Algorithm Notes
Baobao Algorithm Notes
May 9, 2024 · Artificial Intelligence

Inside Deepseek‑V2: How Multi‑Head Latent Attention Cuts KV‑Cache and Boosts Performance

This article provides an in‑depth technical analysis of Deepseek‑V2, covering its 236B parameter size, Multi‑Head Latent Attention optimization that reduces KV‑cache memory, architectural details, training pipelines, infrastructure choices, and performance results on benchmarks such as MMLU and instruction following.

AI architectureDeepSeekMulti-Head Latent Attention
0 likes · 17 min read
Inside Deepseek‑V2: How Multi‑Head Latent Attention Cuts KV‑Cache and Boosts Performance
Baidu Tech Salon
Baidu Tech Salon
May 8, 2024 · Artificial Intelligence

Sugar BI: AI‑Driven Next‑Generation Business Intelligence Platform

Sugar BI, Baidu’s AI‑driven next‑generation business intelligence platform, evolves from the 2016 ShowX system into a zero‑code, multi‑source analytics suite that integrates over 30 data connectors, advanced semantic modeling, and the Wenxin‑powered Sugar Bot, which transforms natural‑language queries into optimized visualizations via intelligent chart recommendation, positioning it as a leading AI‑augmented BI solution.

AIIntelligent Chart RecommendationSugar Bot
0 likes · 19 min read
Sugar BI: AI‑Driven Next‑Generation Business Intelligence Platform
Baidu Geek Talk
Baidu Geek Talk
May 8, 2024 · Artificial Intelligence

Sugar BI: AI‑Driven Next‑Generation Business Intelligence Platform

Sugar BI, evolving from the internal ShowX platform to versions 2.0‑4.0, now offers a zero‑code, drag‑and‑drop visual editor, support for over 30 data sources, AI‑powered automatic analysis and the Sugar Bot Q&A module that transforms multi‑day data tasks into minutes, delivering containerized SaaS BI with intelligent chart recommendation and rapid, code‑free decision‑making for enterprises.

AIAnalyticsBI
0 likes · 19 min read
Sugar BI: AI‑Driven Next‑Generation Business Intelligence Platform
Baobao Algorithm Notes
Baobao Algorithm Notes
May 6, 2024 · Artificial Intelligence

DeepSeek-V2: 236B MoE LLM Delivers Higher Performance While Cutting Training Cost by 42%

DeepSeek‑V2 is a 236‑billion‑parameter mixture‑of‑experts language model that reduces training cost by 42.5 %, cuts KV‑cache usage by 93.3 %, and boosts generation throughput 5.76×, while achieving state‑of‑the‑art scores on benchmarks such as MMLU, C‑Eval, BBH, HumanEval, and GSM8K for both base and chat variants.

AIDeepSeek-V2Mixture of Experts
0 likes · 11 min read
DeepSeek-V2: 236B MoE LLM Delivers Higher Performance While Cutting Training Cost by 42%
IT Services Circle
IT Services Circle
May 1, 2024 · Artificial Intelligence

Summary of Andrew Ng’s AI Agent Talk: Models, Workflows, and Design Patterns

The article summarizes Andrew Ng’s presentation on AI agents, contrasting traditional single‑prompt large‑model usage with iterative agent‑based workflows, reporting experimental accuracy gains, and outlining four agent design patterns—reflection, tool use, planning, and multi‑agent collaboration—while discussing practical trade‑offs such as latency and token speed.

AI AgentDesign PatternsModel Evaluation
0 likes · 7 min read
Summary of Andrew Ng’s AI Agent Talk: Models, Workflows, and Design Patterns
Baidu Geek Talk
Baidu Geek Talk
Apr 22, 2024 · Artificial Intelligence

Designing Effective Prompts for Large Language Models: Structure, Code Examples, and Regex Extraction

The article presents a systematic prompt template—comprising Instruction, Input Data, Context, and Output Indicator—demonstrates code examples for single‑ and multi‑task formatting, shows how clear markers enable regex extraction, and introduces Baidu’s PaddlePaddle Star River Community to simplify building reliable LLM‑driven applications.

AICode ExamplePrompt Engineering
0 likes · 13 min read
Designing Effective Prompts for Large Language Models: Structure, Code Examples, and Regex Extraction
DataFunTalk
DataFunTalk
Apr 21, 2024 · Artificial Intelligence

Guidelines for Building Domain-Specific Large Models: Dataset Construction, Training Methods, Evaluation, and Hardware Benchmarking

This article presents a comprehensive guide on constructing domain-specific large language models, covering the differences from general models, how to build high‑quality domain datasets, selecting appropriate training methods, designing validation sets, evaluating model capabilities, and benchmarking domestic hardware performance.

AIDomain ModelModel Evaluation
0 likes · 20 min read
Guidelines for Building Domain-Specific Large Models: Dataset Construction, Training Methods, Evaluation, and Hardware Benchmarking
21CTO
21CTO
Apr 20, 2024 · Artificial Intelligence

What Developers Need to Know About Meta’s New Open‑Source Llama 3 Model

Meta’s newly open‑source Llama 3 model pushes the frontier of large language models with a larger context window, Mixture‑of‑Experts architecture, multilingual support, and multimodal capabilities, while facing challenges in transparency, bias, and computational resources, and offering diverse applications from NLU to code generation.

AILlama3Multimodal
0 likes · 10 min read
What Developers Need to Know About Meta’s New Open‑Source Llama 3 Model
New Oriental Technology
New Oriental Technology
Apr 19, 2024 · Artificial Intelligence

Effective Prompt Engineering for Large Language Models

This article explains how large language models work, why well‑crafted prompts are essential, and presents practical strategies—such as clarity, conciseness, focus, role‑setting, delimiters, few‑shot examples, and step‑by‑step instructions—to help users obtain accurate and relevant responses from AI systems.

AILLM strategiesNatural Language Processing
0 likes · 12 min read
Effective Prompt Engineering for Large Language Models
AntTech
AntTech
Apr 19, 2024 · Artificial Intelligence

AgentUniverse: An Enterprise‑Grade Multi‑Agent Framework for Complex Financial Analysis

The article introduces AgentUniverse, a large‑model multi‑agent framework that orchestrates specialized agents through a PEER collaboration pattern to overcome LLM limitations in complex financial tasks, demonstrates its architecture, workflow, experimental superiority on benchmarks, and provides open‑source installation details.

AIAgent FrameworkFinancial Analysis
0 likes · 10 min read
AgentUniverse: An Enterprise‑Grade Multi‑Agent Framework for Complex Financial Analysis
NewBeeNLP
NewBeeNLP
Apr 19, 2024 · Artificial Intelligence

Llama 3 Unveiled: 8B & 70B Models Set New SOTA Across Benchmarks

Meta announced the open‑source Llama 3 series (8B and 70B parameters), detailing its decoder‑only Transformer architecture, 15 T‑token multilingual training data, superior benchmark scores over competitors, a limited 8K context window, and upcoming cloud and web‑based deployments.

LLaMA-3Meta-AIbenchmark
0 likes · 7 min read
Llama 3 Unveiled: 8B & 70B Models Set New SOTA Across Benchmarks
DataFunSummit
DataFunSummit
Apr 16, 2024 · Artificial Intelligence

Intelligent Risk Control: Definitions, Expert Systems, Algorithmic Systems, and Emerging AI Techniques

This article explains intelligent risk control as a synergy of expert experience and algorithmic decision‑making, outlines its definition, expert human systems, digital algorithmic systems, and explores advanced AI methods such as reinforcement learning, large language models with knowledge graphs, adversarial learning, graph neural networks, and a practical supply‑chain case study.

Graph Neural NetworkKnowledge Graphadversarial learning
0 likes · 11 min read
Intelligent Risk Control: Definitions, Expert Systems, Algorithmic Systems, and Emerging AI Techniques
CSS Magic
CSS Magic
Apr 12, 2024 · Artificial Intelligence

Answering Common Kimi API Questions and Exploring AI App Development

This article addresses frequent Kimi API queries, explains the API's purpose, available endpoints, model specifications, token‑based pricing, differences from the web assistant, response variability, JSON output workarounds, and shares upcoming roadmap items for developers building AI applications.

AI developmentChat CompletionJSON output
0 likes · 10 min read
Answering Common Kimi API Questions and Exploring AI App Development
21CTO
21CTO
Apr 11, 2024 · Artificial Intelligence

Google Unveils CodeGemma: New AI Models for Code Generation & Reasoning

Google has introduced the CodeGemma series, expanding its Gemma AI models with new variants optimized for code generation and reasoning, featuring 2B‑7B parameter models trained on 500 billion tokens, delivering full‑code block generation, strong benchmark results, and availability on Kaggle, Hugging Face, and Vertex AI.

AIGooglecode generation
0 likes · 4 min read
Google Unveils CodeGemma: New AI Models for Code Generation & Reasoning
DataFunSummit
DataFunSummit
Apr 10, 2024 · Artificial Intelligence

Large Language Model Inference Overview and Performance Optimizations

This article presents a comprehensive overview of large language model inference, describing the prefill and decoding stages, key performance metrics such as throughput, latency and QPS, and detailing a series of system-level optimizations—including pipeline parallelism, dynamic batching, KV‑cache quantization, and hardware considerations—to significantly improve inference efficiency on modern GPUs.

GPUThroughputinference
0 likes · 23 min read
Large Language Model Inference Overview and Performance Optimizations
21CTO
21CTO
Apr 8, 2024 · Artificial Intelligence

How Naver’s HyperCLOVA X Advances Multilingual AI for Asian Languages

Naver’s newly unveiled HyperCLOVA X large‑language model, detailed in an arXiv technical report, claims superior cross‑lingual reasoning for Asian languages, especially Korean, by pre‑training on a data mix of Korean, multilingual text and code, achieving state‑of‑the‑art translation and multilingual capabilities.

AI researchHyperCLOVA XKorean NLP
0 likes · 4 min read
How Naver’s HyperCLOVA X Advances Multilingual AI for Asian Languages
21CTO
21CTO
Mar 29, 2024 · Artificial Intelligence

Why Databricks’ Open‑Source DBRX LLM Is Outpacing GPT‑3.5 and Llama 2

Databricks unveiled the open‑source DBRX large language model, which leverages a mixed‑expert architecture to deliver faster, more cost‑effective inference and beats leading open‑source and proprietary models like Llama 2, Mixtral‑8x7B, and GPT‑3.5 on multiple benchmarks.

AIDBRXDatabricks
0 likes · 7 min read
Why Databricks’ Open‑Source DBRX LLM Is Outpacing GPT‑3.5 and Llama 2
Baobao Algorithm Notes
Baobao Algorithm Notes
Mar 28, 2024 · Artificial Intelligence

How Qwen1.5‑MoE‑A2.7B Matches 70B LLM Performance with Only 2.7B Activated Parameters

Qwen1.5‑MoE‑A2.7B is a 2.7 billion‑parameter Mixture‑of‑Experts model that delivers performance comparable to leading 7 billion‑parameter LLMs while cutting training cost by 75% and boosting inference speed by 1.74×, and the article details its architecture, benchmarks, efficiency analysis, and deployment steps.

MoEQweninference speed
0 likes · 13 min read
How Qwen1.5‑MoE‑A2.7B Matches 70B LLM Performance with Only 2.7B Activated Parameters
OPPO Kernel Craftsman
OPPO Kernel Craftsman
Mar 22, 2024 · Artificial Intelligence

InternLM Model Fine-Tuning Tutorial with XTuner: Chat Format and Practical Implementation Guide

This tutorial walks through fine‑tuning Shanghai AI Lab’s open‑source InternLM models with XTuner, explaining chat‑format conventions, loading and inference (including multimodal InternLM‑XComposer), dataset preparation, configuration sections, DeepSpeed acceleration, and memory‑efficient QLoRA details for 7‑B‑parameter chat models.

Chat FormatDeepSpeedInternLM
0 likes · 22 min read
InternLM Model Fine-Tuning Tutorial with XTuner: Chat Format and Practical Implementation Guide
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Mar 20, 2024 · Artificial Intelligence

Elon Musk’s xAI Open‑Sources Grok‑1: A 314‑Billion‑Parameter MoE Large Language Model

Elon Musk’s xAI has open‑sourced Grok‑1, a 314‑billion‑parameter mixture‑of‑experts language model built with Rust and JAX, released under an Apache‑2.0 license, and the announcement includes detailed architecture specs, hardware requirements, and the broader context of Musk’s rivalry with OpenAI.

AIGrok-1Mixture of Experts
0 likes · 6 min read
Elon Musk’s xAI Open‑Sources Grok‑1: A 314‑Billion‑Parameter MoE Large Language Model
Open Source Tech Hub
Open Source Tech Hub
Mar 17, 2024 · Artificial Intelligence

What Is Grok? Inside Elon Musk’s New Open‑Source LLM and the ‘Grokking’ Phenomenon

Elon Musk announced the open‑source release of Grok, xAI’s new large‑language‑model chatbot, while recalling his lawsuit against OpenAI; the article explains Grok’s rapid development, links to the GitHub repository, summarizes the seminal “Grokking” research paper that describes a sudden generalization breakthrough in neural networks, and provides reference links.

AI researchGrokGrokking
0 likes · 3 min read
What Is Grok? Inside Elon Musk’s New Open‑Source LLM and the ‘Grokking’ Phenomenon
CSS Magic
CSS Magic
Mar 13, 2024 · Artificial Intelligence

How Moonshot’s Kimi Model Beats Big‑Tech LLMs with 200k‑Token Context

The author tests Moonshot’s Kimi API, revealing its 200 k‑character context window, superior token‑to‑character ratio compared with GPT‑3.5 and Gemini, and performance that, while slower than GPT‑3.5 Turbo, rivals GPT‑4 Turbo, all while offering OpenAI‑compatible endpoints and free credit for developers.

API CompatibilityContext LengthKimi
0 likes · 8 min read
How Moonshot’s Kimi Model Beats Big‑Tech LLMs with 200k‑Token Context
DataFunSummit
DataFunSummit
Mar 11, 2024 · Artificial Intelligence

The Synergy of Large Language Models and Knowledge Graphs: Current Status and Future Directions

This article examines how large language models enhance human‑machine interaction and can be combined with knowledge graphs to improve factual Q&A, task‑oriented services, and structured decision‑making, while highlighting ongoing challenges and the enduring role of knowledge graphs in structured domains.

AIKnowledge Graphdialogue system
0 likes · 4 min read
The Synergy of Large Language Models and Knowledge Graphs: Current Status and Future Directions
DataFunTalk
DataFunTalk
Mar 7, 2024 · Artificial Intelligence

Integrating Large Language Models with Knowledge Graphs: Current Status and Future Directions

Large language models enhance human‑machine interaction and natural language understanding, but knowledge graphs remain essential for structured, low‑cost decision making, factual retrieval, and domains like finance; combining both can improve conversational systems, while ongoing challenges in knowledge graph construction persist, as highlighted for the upcoming DataFunSummit2024.

Conversational AIKnowledge Graphlarge language model
0 likes · 5 min read
Integrating Large Language Models with Knowledge Graphs: Current Status and Future Directions
DevOps
DevOps
Mar 5, 2024 · Artificial Intelligence

Understanding GPT‑4, ChatGPT, and the Foundations of Large Language Models

This article explains the fundamentals of AI, machine learning, deep learning, and natural language processing, describes how Transformer architectures and attention mechanisms power large language models such as GPT‑4 and ChatGPT, and walks through tokenization, prediction, and practical development with Python.

Artificial IntelligenceChatGPTGPT-4
0 likes · 16 min read
Understanding GPT‑4, ChatGPT, and the Foundations of Large Language Models
21CTO
21CTO
Feb 27, 2024 · Artificial Intelligence

Mistral Large: The Open‑Source LLM Challenging GPT‑4 on Azure

Mistral AI, a Paris‑based startup, unveiled Mistral Large—an open‑source, multilingual LLM rivaling GPT‑4 with a 32k token context window, advanced code and math abilities, and native Azure AI integration, marking a major milestone in European AI development.

Azure AIMistral AIlarge language model
0 likes · 6 min read
Mistral Large: The Open‑Source LLM Challenging GPT‑4 on Azure
Architects' Tech Alliance
Architects' Tech Alliance
Feb 25, 2024 · Artificial Intelligence

How Sora Redefined Video Generation: Breakthroughs and Industry Impact

The article provides an in‑depth technical analysis of OpenAI's Sora, highlighting its 60‑second 1080p video generation capability, the novel patches‑vectorization and transformer training pipeline that leverages GPT‑generated prompts for multimodal alignment, and its potential to become a universal video‑generation base model that could reshape the AI industry.

AGISoraTransformer
0 likes · 6 min read
How Sora Redefined Video Generation: Breakthroughs and Industry Impact
Programmer DD
Programmer DD
Feb 22, 2024 · Artificial Intelligence

Google Unveils Gemma: Open‑Source LLM Matching Gemini’s Power

Google has launched Gemma, an open‑source large language model available in 2B and 7B parameter versions, built on the same technology as Gemini, outperforming many existing models and capable of running on ordinary laptops, with a detailed technical report and quick‑start guide provided online.

AIGemmaGoogle
0 likes · 3 min read
Google Unveils Gemma: Open‑Source LLM Matching Gemini’s Power
DataFunSummit
DataFunSummit
Feb 21, 2024 · Artificial Intelligence

Applying Knowledge Graphs to E‑commerce AIGC: From Domain to General KG and Large Language Models

This article presents a comprehensive overview of how knowledge graphs are integrated into e‑commerce AIGC pipelines, covering domain‑specific and generic KG‑driven text generation, model architecture, controllable generation techniques, experimental results, and future directions for large language models in commercial settings.

AIAIGCControlled Generation
0 likes · 23 min read
Applying Knowledge Graphs to E‑commerce AIGC: From Domain to General KG and Large Language Models
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Feb 18, 2024 · Artificial Intelligence

Llama 2: Open Foundation and Fine‑Tuned Chat Models – Overview and Technical Details

The article provides a comprehensive overview of Meta’s Llama 2 series, detailing model sizes, pre‑training data, architectural enhancements, supervised fine‑tuning, RLHF procedures, safety evaluations, reward‑model training, and iterative improvements, highlighting its open‑source release and comparative performance.

AI safetyLlama2RLHF
0 likes · 27 min read
Llama 2: Open Foundation and Fine‑Tuned Chat Models – Overview and Technical Details
DataFunSummit
DataFunSummit
Feb 12, 2024 · Artificial Intelligence

Ant Group's Time Series AI Practices and the AntFlux Intelligent Engine

This article presents Ant Group's comprehensive time‑series AI solutions, covering the business value of temporal data, the evolution of statistical and deep learning models, large‑scale time‑series platforms such as AntFlux, and real‑world applications ranging from financial forecasting to green computing.

AIAntFluxTime Series
0 likes · 17 min read
Ant Group's Time Series AI Practices and the AntFlux Intelligent Engine
Baidu Geek Talk
Baidu Geek Talk
Feb 7, 2024 · Artificial Intelligence

Design and Implementation of a Knowledge-Base Intelligent Q&A System for Database Operations Using Large Models

The paper details Baidu Intelligent Cloud’s design and deployment of a domain‑specific knowledge‑base Q&A system for database operations, combining prompt‑engineered LLMs with hybrid vector‑search using LangChain, BES vector store, and custom ingestion, addressing recall, token limits, and hallucination challenges across dashboard and IM bot interfaces.

AIKnowledge Basedatabase operations
0 likes · 16 min read
Design and Implementation of a Knowledge-Base Intelligent Q&A System for Database Operations Using Large Models
Architect
Architect
Jan 27, 2024 · Industry Insights

How We Built a Scalable Smart Customer Service System for an Activity Platform

This article details the end‑to‑end design, implementation, and operational results of a smart customer‑service platform that automates FAQ capture, leverages both Elasticsearch and LLM‑based models, and provides a low‑code, multi‑team backend for rapid issue resolution.

ElasticsearchOperationsfaq-automation
0 likes · 13 min read
How We Built a Scalable Smart Customer Service System for an Activity Platform
Baidu Geek Talk
Baidu Geek Talk
Jan 24, 2024 · Artificial Intelligence

Building AI‑Native Applications with Baidu Cloud AppBuilder

Sun Ke’s keynote at the 2023 Baidu Cloud Intelligence Conference explains how AI‑native development has shifted from model selection to building practical applications, and introduces Baidu Cloud AppBuilder—a three‑layer, low‑code‑and‑code platform that provides multimodal, LLM, and infrastructure services, enabling rapid prototyping of solutions such as automated resume screening and interview preparation.

AIAppBuilderNL2SQL
0 likes · 12 min read
Building AI‑Native Applications with Baidu Cloud AppBuilder
JD Tech
JD Tech
Jan 24, 2024 · Artificial Intelligence

JD Retail Technology 2023 Highlights: AI‑Driven Supply Chain, Large Language Models, Edge AI, Data Security, and 3D Modeling Innovations

In 2023 JD Retail’s technology team delivered a suite of AI‑powered innovations—including end‑to‑end inventory management, explainable AI for supply chain, privacy‑preserving advertising models, a ReAct‑SFT‑RAG large language model framework, edge AI inference, secure data‑safe‑house infrastructure, and high‑quality 3D modeling pipelines—demonstrating broad academic and industrial impact across multiple domains.

3D modelingAIGCArtificial Intelligence
0 likes · 19 min read
JD Retail Technology 2023 Highlights: AI‑Driven Supply Chain, Large Language Models, Edge AI, Data Security, and 3D Modeling Innovations
360 Quality & Efficiency
360 Quality & Efficiency
Jan 19, 2024 · Artificial Intelligence

Using Large Language Models to Rapidly Build Simple Frontend and Backend Test Tools

This article explains how to quickly create simple web‑based and backend test tools for internal use by leveraging a large language model to generate annotated HTML, CSS, JavaScript and minimal Flask code, outlining prompt design, tool requirements, and deployment tips to boost testing efficiency.

AI code generationRapid Prototypingbackend development
0 likes · 8 min read
Using Large Language Models to Rapidly Build Simple Frontend and Backend Test Tools
DataFunTalk
DataFunTalk
Jan 16, 2024 · Artificial Intelligence

Applying Knowledge Graphs to E‑commerce AIGC: From Domain‑Specific to General Knowledge Graphs and LLM Integration

This article presents a comprehensive overview of how knowledge graphs are leveraged in e‑commerce AIGC pipelines, detailing domain‑specific and general graph‑based text generation, model architecture, controllable generation techniques, experimental results, and future directions for large language model integration.

AIGCDomain AdaptationKnowledge Graph
0 likes · 22 min read
Applying Knowledge Graphs to E‑commerce AIGC: From Domain‑Specific to General Knowledge Graphs and LLM Integration
DataFunSummit
DataFunSummit
Jan 10, 2024 · Artificial Intelligence

Baidu Commercial Multimodal Understanding and AIGC Innovation Practices

This article presents Baidu's commercial multimodal understanding and AIGC innovations, detailing rich‑media multimodal perception, a unified large‑scale representation framework, scenario‑specific fine‑tuning, and practical applications such as marketing copy, digital‑human video, and poster generation.

AIGCAdvertisingBaidu
0 likes · 12 min read
Baidu Commercial Multimodal Understanding and AIGC Innovation Practices
DataFunSummit
DataFunSummit
Jan 8, 2024 · Artificial Intelligence

Enterprise Knowledge Recommendation System at Alibaba: Architecture, Challenges, and Large Model Applications

This article presents Alibaba's enterprise knowledge recommendation system, detailing its role in digital transformation, the challenges of long‑document recommendation, the multi‑layer architecture spanning feature, engine, ranking, and functional layers, various recall strategies, progressive ranking models, and the integration and evaluation of large language models for improved recommendation performance.

AIAlibabaEnterprise Digital Transformation
0 likes · 23 min read
Enterprise Knowledge Recommendation System at Alibaba: Architecture, Challenges, and Large Model Applications
Architecture & Thinking
Architecture & Thinking
Jan 8, 2024 · Artificial Intelligence

How Baidu Comate Supercharges Coding: A Practical AI Assistant Guide

This article introduces Baidu Comate, an AI-powered coding assistant built on the Wenxin model, explains how to install it, demonstrates its real-time code completion, comment generation, test creation, and optimization features across multiple languages and IDEs, and highlights its benefits for developers.

AI coding assistantGoVS Code
0 likes · 10 min read
How Baidu Comate Supercharges Coding: A Practical AI Assistant Guide
21CTO
21CTO
Dec 31, 2023 · Artificial Intelligence

2023’s Leading Open-Source LLMs: LLaMA, Pythia, MPT, Falcon, BLOOM, Mistral

Since ChatGPT’s debut, interest in large language models has surged, prompting the AI community to explore open‑source alternatives such as LLaMA, Pythia, MPT, Falcon, BLOOM, and Mistral, which together illustrate the rapid diversification and growing competitiveness of open‑source LLMs in 2023.

2023AIModel Comparison
0 likes · 9 min read
2023’s Leading Open-Source LLMs: LLaMA, Pythia, MPT, Falcon, BLOOM, Mistral
DataFunTalk
DataFunTalk
Dec 29, 2023 · Artificial Intelligence

Enterprise Knowledge Assistant: Leveraging Vector Databases and Large Language Models

This article explores the emerging enterprise knowledge assistant paradigm in the era of large models, detailing traditional knowledge management challenges, solution architecture using vector databases and LLMs, core technologies such as ETL pipelines, reranking, secure fine‑tuning, and future prospects for intelligent enterprise applications.

Enterprise AILLM fine-tuningknowledge management
0 likes · 11 min read
Enterprise Knowledge Assistant: Leveraging Vector Databases and Large Language Models
21CTO
21CTO
Dec 18, 2023 · Artificial Intelligence

Why Did Google’s Gemini‑Pro Claim to Be Baidu’s Model in Chinese Chats?

A recent test on Google Vertex AI showed Gemini‑Pro introducing itself as Baidu’s Wenxin model during Chinese conversations, sparking debate about model attribution, pricing, developer tools, and the broader competition among major AI platforms.

AI platformsGemini ProGoogle AI
0 likes · 5 min read
Why Did Google’s Gemini‑Pro Claim to Be Baidu’s Model in Chinese Chats?
CSS Magic
CSS Magic
Dec 15, 2023 · Artificial Intelligence

Google Gemini Free API Launch: A Deep Dive for Developers

Google has opened its Gemini Pro large‑language model via a completely free API with a 60‑calls‑per‑minute limit, offering an online playground, straightforward key registration, efficient token usage, and streaming output, while noting it remains a technical preview rather than a consumer‑ready service.

AIAPI usageFree API
0 likes · 3 min read
Google Gemini Free API Launch: A Deep Dive for Developers
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Dec 9, 2023 · Artificial Intelligence

Google Unveils Gemini: A New Multimodal Large Model Family (Ultra, Pro, Nano)

Google announced Gemini, a suite of multimodal large language models—including Ultra, Pro, and Nano—that achieve state‑of‑the‑art results on dozens of benchmarks, support native multimodal pre‑training, and are being integrated across Google products such as Bard, Search, and upcoming Pixel devices.

Artificial IntelligenceGeminiGoogle AI
0 likes · 7 min read
Google Unveils Gemini: A New Multimodal Large Model Family (Ultra, Pro, Nano)
Tencent Cloud Developer
Tencent Cloud Developer
Dec 7, 2023 · Artificial Intelligence

Student Score Ranking and Distribution Analysis Using Python and Tencent Hunyuan Model

Using Tencent's Hunyuan model, the tutorial walks through a Python workflow that scrapes a student‑score table from a web page, saves it as CSV and Excel, cleans missing values, computes total and average scores, and visualizes their distributions with matplotlib, illustrating how LLMs can accelerate data‑analysis coding while still needing human verification.

PythonWeb Scrapingdata analysis
0 likes · 8 min read
Student Score Ranking and Distribution Analysis Using Python and Tencent Hunyuan Model
AntTech
AntTech
Dec 2, 2023 · Artificial Intelligence

TechTalk AI Sharing Season: OpenKG Enters Ant Group – Knowledge Graphs and Large Language Models Empower General AI

The TechTalk AI Sharing Season event on November 28 brought together nearly thirty experts from academia and industry to discuss how knowledge graphs and large language models can be integrated to enhance Ant Group's AI strategy across diverse business scenarios, highlighting collaborations, research labs, and future development directions.

AI strategyAnt GroupIndustry-Academia Collaboration
0 likes · 7 min read
TechTalk AI Sharing Season: OpenKG Enters Ant Group – Knowledge Graphs and Large Language Models Empower General AI
HomeTech
HomeTech
Dec 1, 2023 · Artificial Intelligence

Building a Private Knowledge Base and Large‑Model Platform for Enterprise AI Assistants

This article describes how an enterprise leveraged GPT‑3.5 and other large language models to create a private knowledge base, design prompt engineering, implement plugin extensions, and build a secure, scalable backend and front‑end integration platform that enables AI‑driven customer‑service assistants across multiple business lines.

AIPrivate Knowledge BasePrompt Engineering
0 likes · 19 min read
Building a Private Knowledge Base and Large‑Model Platform for Enterprise AI Assistants
Baidu Geek Talk
Baidu Geek Talk
Nov 27, 2023 · Industry Insights

Inside Baidu’s Lingjing Platform: How AI Developer Ecosystems Are Built

This article examines Baidu’s Lingjing developer platform, exploring its origins, design choices, integration of plugins and agents, ecosystem advantages, commercial‑monetization loops, and future roadmap, while providing insights from an interview with platform head Zhang Ruixing on the challenges and opportunities of building AI‑native developer platforms.

AIAgentDeveloper Platform
0 likes · 16 min read
Inside Baidu’s Lingjing Platform: How AI Developer Ecosystems Are Built
Ant R&D Efficiency
Ant R&D Efficiency
Nov 21, 2023 · Artificial Intelligence

Can AI Code Completion Transform Java Development? One Engineer’s Journey

Java engineer Wu Ming shares his experience with CodeFuse, an AI-powered code completion tool, describing how large language models enhance coding efficiency, the challenges of early versions, practical tips for integrating AI assistants into workflows, and his vision for AI’s expanding role across the entire software development lifecycle.

AI code assistantAI workflowCodeFuse
0 likes · 12 min read
Can AI Code Completion Transform Java Development? One Engineer’s Journey
Programmer DD
Programmer DD
Nov 7, 2023 · Artificial Intelligence

Inside xAI’s Grok: How a 330‑B Model Beats ChatGPT and Redefines AI Development

The article details xAI’s newly launched Grok AI assistant, its multi‑session UI, real‑time Twitter integration, benchmark performance surpassing ChatGPT‑3.5, the underlying 330‑billion‑parameter Grok‑1 model, Rust‑based infrastructure, current limitations, and the research directions xAI is pursuing to advance reliable, scalable artificial intelligence.

AI benchmarkingGrokRust infrastructure
0 likes · 12 min read
Inside xAI’s Grok: How a 330‑B Model Beats ChatGPT and Redefines AI Development
DataFunTalk
DataFunTalk
Nov 1, 2023 · Artificial Intelligence

Data‑Centric LLM and Knowledge Graph Integration: Fabarta’s AI‑Era Data Infrastructure

The article presents Fabarta’s AI‑era data infrastructure that combines large language models with knowledge graphs and a multimodal database, detailing its data‑centric architecture, HTAP capabilities, cloud‑native design, and real‑world demos that illustrate how graph‑plus‑vector techniques improve model reliability and answer precision.

AIHTAPcloud native
0 likes · 19 min read
Data‑Centric LLM and Knowledge Graph Integration: Fabarta’s AI‑Era Data Infrastructure
DataFunTalk
DataFunTalk
Oct 30, 2023 · Databases

Engineering Practices and Evolution of Douyin’s Cloud‑Native Vector Database

This article outlines Douyin’s step‑by‑step engineering evolution of its cloud‑native vector database, covering the background of vector search, core concepts, algorithmic optimizations, storage‑compute separation, streaming updates, multi‑tenant orchestration, and future applications such as large language model integration.

ANNDouyincloud native
0 likes · 17 min read
Engineering Practices and Evolution of Douyin’s Cloud‑Native Vector Database
Ant R&D Efficiency
Ant R&D Efficiency
Oct 26, 2023 · Artificial Intelligence

TestAgent: Open-Source 7B LLM That Supercharges Automated Test Generation

TestAgent is an open-source 7B test-domain LLM that delivers multi-language test-case generation, automatic assert completion, and a rapid deployment framework, offering industry-leading pass@1 scores, a ChatBot UI, and detailed setup instructions for diverse hardware environments.

AI testinglarge language modelmodel deployment
0 likes · 8 min read
TestAgent: Open-Source 7B LLM That Supercharges Automated Test Generation
Huawei Cloud Developer Alliance
Huawei Cloud Developer Alliance
Oct 25, 2023 · Artificial Intelligence

Unlocking GLM & ChatGLM: Deep Dive into MindSpore Large‑Model Techniques

The MindSpore Season 2 open class offers a comprehensive overview of GLM to ChatGLM architectures, positional‑embedding strategies, stable training optimizations, and step‑by‑step instructions for deploying large language models with Ascend, ModelArts, and MindSpore Transformers, while previewing upcoming multimodal remote‑sensing sessions.

Artificial IntelligenceChatGLMGLM
0 likes · 6 min read
Unlocking GLM & ChatGLM: Deep Dive into MindSpore Large‑Model Techniques
Bilibili Tech
Bilibili Tech
Oct 13, 2023 · Artificial Intelligence

Multimodal Video High‑Energy Segment Extraction for Dynamic Video Covers

The authors present a multimodal system that automatically extracts high‑energy video segments for dynamic covers by analyzing subtitles, audio, visual frames, and danmu, employing LLM prompt‑tuning, scene‑cut detection, and aesthetic scoring to reduce manual effort and boost click‑through rates.

ASROCRdynamic cover
0 likes · 14 min read
Multimodal Video High‑Energy Segment Extraction for Dynamic Video Covers
Sohu Tech Products
Sohu Tech Products
Oct 11, 2023 · Artificial Intelligence

EcomGPT: Training an E-commerce Domain Large Language Model via Instruction Tuning

EcomGPT, an Alibaba‑trained e‑commerce large language model, uses a 1.5 million‑sample instruction dataset (EcomInstruct) to demonstrate that domain‑specific instruction tuning dramatically outperforms general‑purpose models on e‑commerce tasks, reducing hallucinations and improving task accuracy, with performance scaling as data diversity increases.

Alibaba NLPEcomGPTNLP
0 likes · 7 min read
EcomGPT: Training an E-commerce Domain Large Language Model via Instruction Tuning
Ant R&D Efficiency
Ant R&D Efficiency
Sep 28, 2023 · Artificial Intelligence

CodeFuse: Open‑Source Large Code Model with Multi‑Task Fine‑Tuning and 4‑Bit Quantization

Ant Group’s open‑source CodeFuse is a large‑scale code‑generation model featuring multi‑task fine‑tuning and 4‑bit quantization, achieving a 74.4% HumanEval score that outperforms GPT‑4, supporting tasks from code synthesis to bug fixing, and can be deployed on a single high‑end GPU.

AICodeFusecode generation
0 likes · 9 min read
CodeFuse: Open‑Source Large Code Model with Multi‑Task Fine‑Tuning and 4‑Bit Quantization
Baidu Tech Salon
Baidu Tech Salon
Sep 13, 2023 · Artificial Intelligence

How Baidu’s Wenxin Yiyan Powers AI Text Creation in Mobile Apps

This article explains the technical workflow behind Baidu App’s AI‑assisted text generation, covering large‑language‑model fundamentals, three‑layer system architecture, prompt design, risk‑control measures, SSE streaming, and a custom Android TextView implementation for smooth, gradient‑styled output.

AI text generationAndroid UIPrompt Engineering
0 likes · 13 min read
How Baidu’s Wenxin Yiyan Powers AI Text Creation in Mobile Apps
Alipay Experience Technology
Alipay Experience Technology
Sep 12, 2023 · Artificial Intelligence

Demystifying ChatGPT: From Transformer Basics to Business Applications

This article offers a non‑algorithmic engineer’s clear overview of large language models, explaining ChatGPT’s generative‑pre‑training‑transformer foundation, core mechanisms like attention, practical prompt‑engineering tips, and how enterprises can integrate LLMs into data analysis, smart‑customer service, and other business workflows while noting associated risks.

AI applicationsChatGPTPrompt Engineering
0 likes · 28 min read
Demystifying ChatGPT: From Transformer Basics to Business Applications
Tencent Cloud Developer
Tencent Cloud Developer
Sep 7, 2023 · Artificial Intelligence

What Is Tencent’s Hunyuan LLM and How Is It Shaping AI Applications?

At the 2023 Global Digital Ecology Conference, Tencent unveiled its self‑developed, open‑access large language model Hunyuan, detailing its massive scale, full‑stack proprietary technology, performance advantages, diverse business integrations, and the company’s broader strategy to embrace and commercialize advanced AI across its ecosystem.

AI applicationsArtificial IntelligenceModel as a Service
0 likes · 8 min read
What Is Tencent’s Hunyuan LLM and How Is It Shaping AI Applications?
DataFunTalk
DataFunTalk
Sep 6, 2023 · Databases

Large Model + OLAP: Enabling a New Data Service Platform

This article details how Tencent Music combines large language models with an Apache Doris‑based OLAP engine, introduces a semantic layer, manual‑experience routing, schema mapping and plugin integration, and outlines the evolution of its data architecture through four versions to achieve real‑time, cost‑effective, and scalable intelligent data services.

Apache DorisOLAPdata warehouse
0 likes · 24 min read
Large Model + OLAP: Enabling a New Data Service Platform
AI Large Model Application Practice
AI Large Model Application Practice
Sep 6, 2023 · Artificial Intelligence

Prompt Engineering vs Fine‑Tuning: How to Choose the Best Strategy for Reliable LLM Outputs

This article compares Prompt Engineering and Supervised Fine‑Tuning for large language models, explains their principles, showcases common prompt patterns such as Chain‑of‑Thought, ReAct and Self‑Ask, outlines fine‑tuning stages and trade‑offs, and provides practical guidance on selecting the most suitable approach for specific enterprise AI Agent scenarios.

AI AgentLLMPrompt Engineering
0 likes · 17 min read
Prompt Engineering vs Fine‑Tuning: How to Choose the Best Strategy for Reliable LLM Outputs
Baidu Tech Salon
Baidu Tech Salon
Aug 29, 2023 · Artificial Intelligence

Insights into Baidu's Wenxin Yiyan Large Language Model and Its Role in AI-Driven Industrial Production

Baidu’s Wenxin Yiyan, a knowledge‑enhanced large language model now at version 3.5, outperforms ChatGPT, showcases rapid training and inference, and is being deployed across transportation, agriculture, energy and other sectors, illustrating AI’s transition to industrial mass production and its strategic boost for China’s high‑quality economic growth.

AI strategyArtificial IntelligenceIndustrial Applications
0 likes · 9 min read
Insights into Baidu's Wenxin Yiyan Large Language Model and Its Role in AI-Driven Industrial Production
php Courses
php Courses
Aug 25, 2023 · Artificial Intelligence

Meta Launches Code Llama: An Advanced AI Coding Model

Meta introduced Code Llama, a Llama 2‑based AI coding model available in base, Python‑specific, and instruction‑tuned versions across 7B, 13B, and 34B sizes, claiming superior benchmark performance and free community licensing for research and commercial use.

AI codingCode LlamaMeta
0 likes · 5 min read
Meta Launches Code Llama: An Advanced AI Coding Model
Sohu Tech Products
Sohu Tech Products
Aug 23, 2023 · Artificial Intelligence

Engineering GPT Applications: Capabilities, Limitations, and Solutions

The guide explains GPT’s core capabilities—natural language mastery, domain reasoning, and code generation—while detailing its limits such as prompt sensitivity, token caps, and lack of memory, then offers engineering workarounds like systematic prompting, chain‑of‑thought, external memory, tool integration, safety checks, and a six‑layer architecture for building robust commercial AI applications.

AI application architectureChain-of-ThoughtGPT
0 likes · 20 min read
Engineering GPT Applications: Capabilities, Limitations, and Solutions
DataFunSummit
DataFunSummit
Aug 3, 2023 · Artificial Intelligence

Integrating Vector Databases with Large Language Models for Enterprise AI Applications

The article explains how combining vector databases with large language models can help governments and enterprises leverage massive private data for AI, covering semantic search, approximate nearest neighbor techniques, alignment challenges across modalities, and future directions for fine‑grained data integration.

AIApproximate Nearest Neighborlarge language model
0 likes · 7 min read
Integrating Vector Databases with Large Language Models for Enterprise AI Applications
Model Perspective
Model Perspective
Jul 31, 2023 · Artificial Intelligence

From RNN to ChatGPT: How AIGC Evolved with Transformers and Large Models

This article traces the evolution of AI‑generated content (AIGC) from early RNN‑based Seq2Seq models through the transformative impact of the Transformer architecture, covering key milestones such as UniLM, T5, BART, the GPT series, InstructGPT, and the emergence of ChatGPT.

AI Content GenerationAIGCGPT
0 likes · 9 min read
From RNN to ChatGPT: How AIGC Evolved with Transformers and Large Models
JD Tech
JD Tech
Jul 31, 2023 · Artificial Intelligence

Local Deployment, Fine‑tuning, and Inference of the Open‑source Alpaca‑LoRA Model on GPU Servers

This article details the step‑by‑step process of installing GPU drivers, setting up a Python environment, deploying the open‑source Alpaca‑LoRA large language model, fine‑tuning it with Chinese data on a multi‑GPU server, and running inference, while discussing practical challenges and performance observations.

AlpacaGPULoRA
0 likes · 14 min read
Local Deployment, Fine‑tuning, and Inference of the Open‑source Alpaca‑LoRA Model on GPU Servers
HomeTech
HomeTech
Jul 26, 2023 · Artificial Intelligence

Practical Implementation of ChatGPT Technology Products: Architecture, Prompt Engineering, and Future Challenges

This article explores the practical deployment of ChatGPT‑based products, detailing the model fundamentals, technical architecture, engineering‑focused prompt design, real‑world application scenarios, and the challenges of model generalization, resource consumption, data privacy, interpretability, and ethical considerations.

AI architectureChatGPTJava
0 likes · 15 min read
Practical Implementation of ChatGPT Technology Products: Architecture, Prompt Engineering, and Future Challenges
Cloud Native Technology Community
Cloud Native Technology Community
Jun 28, 2023 · Artificial Intelligence

Building and Deploying Custom Large Language Models with Alauda Cloud‑Native MLOps

This article explains how enterprises can use the Alauda MLOps platform to quickly set up, fine‑tune, and deploy private large language models on cloud‑native infrastructure, covering notebook preparation, GPU allocation, model download, inference service creation, distributed training pipelines, and Docker image building.

AIMLOpsfine-tuning
0 likes · 9 min read
Building and Deploying Custom Large Language Models with Alauda Cloud‑Native MLOps
HelloTech
HelloTech
Jun 21, 2023 · Artificial Intelligence

Overview of Haro Intelligent Customer Service: Algorithms, Challenges, and AI Solutions

Haro’s intelligent customer service combines a smart FAQ recommender and a conversational chatbot that leverages matching‑based intent recognition, large‑scale domain pre‑training, metric‑learning for new intents, and fine‑tuned generative LLMs, achieving 82 % top‑1 accuracy while reducing human workload and outlining future API‑orchestrated, multimodal AI enhancements.

AINLPlarge language model
0 likes · 10 min read
Overview of Haro Intelligent Customer Service: Algorithms, Challenges, and AI Solutions
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Jun 11, 2023 · Artificial Intelligence

Comprehensive Technical Overview of GPT Series, Transformers, and Emerging Capabilities in Large Language Models

This article provides a detailed technical review of the evolution of GPT models, the Transformer architecture, large language model training methods, emergent abilities such as in‑context learning and chain‑of‑thought, multimodal extensions, and the challenges of data, scaling, and alignment, offering a holistic view for researchers and practitioners.

AIGPTInstructGPT
0 likes · 28 min read
Comprehensive Technical Overview of GPT Series, Transformers, and Emerging Capabilities in Large Language Models
NetEase Cloud Music Tech Team
NetEase Cloud Music Tech Team
Jun 2, 2023 · Frontend Development

How NetEase Cloud Music’s Front‑End Team Built an AI‑Powered Low‑Code Copilot

NetEase Cloud Music’s front‑end team integrated large language models into their internal low‑code platform, creating an AI Copilot that supports smart page creation, editing, component configuration, code snippet generation, and Q&A, while detailing the underlying architecture, prompt engineering, and mixed‑mode development workflow.

AI CopilotMixed DevelopmentPrompt Engineering
0 likes · 11 min read
How NetEase Cloud Music’s Front‑End Team Built an AI‑Powered Low‑Code Copilot
Baidu Tech Salon
Baidu Tech Salon
May 29, 2023 · Artificial Intelligence

Baidu CTO Wang Haifeng Highlights Wenxin Yiyan Large Language Model at Zhongguancun Forum

At the Zhongguancun Forum, Baidu CTO Wang Haifeng showcased the self‑developed Wenxin Yiyan large language model—demonstrating its knowledge‑enhanced Q&A, writing, poetry, video generation and reasoning abilities, its integration as an intelligent office assistant, and its role in driving a model‑as‑a‑service ecosystem that fuels China’s AI‑led industrial transformation.

AI PolicyArtificial IntelligenceBaidu
0 likes · 7 min read
Baidu CTO Wang Haifeng Highlights Wenxin Yiyan Large Language Model at Zhongguancun Forum