ChipNeMo: Domain-Adapted LLMs for Chip Design
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: domain-adaptive tokenization, domain-adaptive continued pretr...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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: domain-adaptive tokenization, domain-adaptive continued
pretraining, model alignment 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 evaluations demonstrate
that domain-adaptive pretraining of language models, can lead to superior
performance in domain related downstream tasks compared to their base LLaMA2
counterparts, without degradations in generic capabilities. In particular, our
largest model, ChipNeMo-70B, outperforms the highly capable GPT-4 on two of our
use cases, namely engineering assistant chatbot and EDA scripts generation,
while exhibiting competitive performance on bug summarization and analysis.
These results underscore the potential of domain-specific customization for
enhancing the effectiveness of large language models in specialized
applications. |
---|---|
DOI: | 10.48550/arxiv.2311.00176 |