漢德百科全書 | 汉德百科全书
IT-Times
Law
Companies
Nvidia
ChipNeMo aims to explore the applications of large language models (LLMs) for industrial chip design. Instead of directly deploying off-the-shelf commercial or open-source LLMs, we instead adopt the following domain adaptation techniques: custom tokenizers, domain-adaptive continued pretraining, supervised fine-tuning (SFT) with domain-specific instructions, and domain-adapted retrieval models. We evaluate these methods on three selected LLM applications for chip design: an engineering assistant chatbot, EDA script generation, and bug summarization and analysis. Our results show that these domain adaptation techniques enable significant LLM performance improvements over general-purpose base models across the three evaluated applications, enabling up to 5x model size reduction with similar or better performance on a range of design tasks. Our findings also indicate that there’s still room for improvement between our current results and ideal outcomes. We believe that further investigation of domain-adapted LLM approaches will help close this gap in the future.
Baden-Wuerttemberg
California-CA
Claude是由美国科技公司Anthropic开发的大型语言模型，其最新版本为Claude 3.5 Sonnet。大型语言模型 基于转换器的生成式预训练模型 基础模型 聊天机器人
Claude ist ein von Anthropic entwickeltes Sprachmodell.[1] Die Entwicklung von Claude zielt auf die Vereinigung der Sprachverarbeitung (mittels maschinellem Lernen und großer Sprachmodelle) mit ethischen Standards und Sicherheit in der künstlichen Intelligenz (kurz KI) ab.[2]