주민건

LLM은 놀라운 가능성을 지니고 있지만, 기업에 바로 적용하기 위해서는 오랜 기간 해당 분야를 깊이 연구한 전문가들의 지식과 노하우가 필요합니다. LLM 챗봇을 도입하기 전 기업이 고려해야 할 3가지를 소개합니다.

Learn how to use Infrastructure as Code with (AWS CDK)] to deploy and manage Llama 2

Database administrators (DBAs) play a crucial role in managing, maintainingand optimizing a database system to ensure data availability, performance, andreliability. However, it is hard and tedious for DBAs to manage a large numberof database instances (e.g., millions of instances on the cloud da…

Large Language Models (LLMs) are becoming increasingly smart and autonomous,targeting real-world pragmatic missions beyond traditional NLP tasks. As aresult, there has been an urgent need to evaluate LLMs as agents on challengingtasks in interactive environments. We present AgentBench, a multi-di…

When trying to gain better visibility into a machine learning model in orderto understand and mitigate the associated risks, a potentially valuable sourceof evidence is: which training examples most contribute to a given behavior?Influence functions aim to answer a counterfactual: how would the m…

For industrial control, developing high-performance controllers with fewsamples and low technical debt is appealing. Foundation models, possessing richprior knowledge obtained from pre-training with Internet-scale corpus, have thepotential to be a good controller with proper prompts. In this pape…

Ensuring alignment, which refers to making models behave in accordance withhuman intentions [1,2], has become a critical task before deploying largelanguage models (LLMs) in real-world applications. For instance, OpenAI devotedsix months to iteratively aligning GPT-4 before its release [3]. Howev…

Reinforcement Learning from Human Feedback (RLHF) facilitates the alignmentof large language models with human preferences, significantly enhancing thequality of interactions between humans and these models. InstructGPT implementsRLHF through several stages, including Supervised Fine-Tuning (SFT)…

Reinforcement learning from human feedback (RLHF) is a technique for trainingAI systems to align with human goals. RLHF has emerged as the central methodused to finetune state-of-the-art large language models (LLMs). Despite thispopularity, there has been relatively little public work systematizi…

Medicine, by its nature, is a multifaceted domain that requires the synthesisof information across various modalities. Medical generative vision-languagemodels (VLMs) make a first step in this direction and promise many excitingclinical applications. However, existing models typically have to be…

Despite the advancements of open-source large language models (LLMs) andtheir variants, e.g., LLaMA and Vicuna, they remain significantly limited inperforming higher-level tasks, such as following human instructions to useexternal tools (APIs). This is because current instruction tuning largelyf…

We introduce OpenFlamingo, a family of autoregressive vision-language modelsranging from 3B to 9B parameters. OpenFlamingo is an ongoing effort to producean open-source replication of DeepMind’s Flamingo models. On sevenvision-language datasets, OpenFlamingo models average between 80 - 89% ofcor…

We investigate the internal structure of language model computations usingcausal analysis and demonstrate two motifs: (1) a form of adaptive computationwhere ablations of one attention layer of a language model cause another layerto compensate (which we term the Hydra effect) and (2) a counterbal…

The recent progress in large language models (LLMs), especially the inventionof chain-of-thoughts (CoT) prompting, makes it possible to solve reasoningproblems. However, even the strongest LLMs are still struggling with morecomplicated problems that require non-linear thinking and multi-step reas…

To interact with humans in the world, agents need to understand the diversetypes of language that people use, relate them to the visual world, and actbased on them. While current agents learn to execute simple languageinstructions from task rewards, we aim to build agents that leverage diversela…

The launch of ChatGPT has created a pivotal moment, enabling enterprises to envision new use cases and accelerated the adoption of AI within these corporations. One such use case in the enterprise space is the...

핀테크 스타트업 프로덕트 디자이너 전정민입니다Q. 안녕하세요 정민님 자기소개 부탁드려...

수능 국어 1등급에 도전하는 AI. Contribute to NomaDamas/KICE_slayer_AI_Korean development by creating an account on GitHub.

ChatGPTCode Interpreter 한국에너지기술연구원 AI 학습조직에서는 2023년 한 해동안 데이터 처리를 공부합니다. 세 번째 시간으로 ChatGPT Code Interpreter를 소개합니다. 챗봇으로 알려진 ChatGPT의 언어 능력과 코딩 능력, 그리고 실행 능력을 조합해 데이터를 처리합니다. 머신 러닝도 수행하고 최적화도 알아서 할