LLMs as On-demand Customizable Service
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929228334759936 |
|---|---|
| author | Sarkar, Souvika Babar, Mohammad Fakhruddin Hasan, Monowar Karmaker, Shubhra Kanti |
| author_facet | Sarkar, Souvika Babar, Mohammad Fakhruddin Hasan, Monowar Karmaker, Shubhra Kanti |
| contents | Large Language Models (LLMs) have demonstrated remarkable language understanding and generation capabilities. However, training, deploying, and accessing these models pose notable challenges, including resource-intensive demands, extended training durations, and scalability issues. To address these issues, we introduce a concept of hierarchical, distributed LLM architecture that aims at enhancing the accessibility and deployability of LLMs across heterogeneous computing platforms, including general-purpose computers (e.g., laptops) and IoT-style devices (e.g., embedded systems). By introducing a "layered" approach, the proposed architecture enables on-demand accessibility to LLMs as a customizable service. This approach also ensures optimal trade-offs between the available computational resources and the user's application needs. We envision that the concept of hierarchical LLM will empower extensive, crowd-sourced user bases to harness the capabilities of LLMs, thereby fostering advancements in AI technology in general. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_16577 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLMs as On-demand Customizable Service Sarkar, Souvika Babar, Mohammad Fakhruddin Hasan, Monowar Karmaker, Shubhra Kanti Computation and Language Artificial Intelligence Large Language Models (LLMs) have demonstrated remarkable language understanding and generation capabilities. However, training, deploying, and accessing these models pose notable challenges, including resource-intensive demands, extended training durations, and scalability issues. To address these issues, we introduce a concept of hierarchical, distributed LLM architecture that aims at enhancing the accessibility and deployability of LLMs across heterogeneous computing platforms, including general-purpose computers (e.g., laptops) and IoT-style devices (e.g., embedded systems). By introducing a "layered" approach, the proposed architecture enables on-demand accessibility to LLMs as a customizable service. This approach also ensures optimal trade-offs between the available computational resources and the user's application needs. We envision that the concept of hierarchical LLM will empower extensive, crowd-sourced user bases to harness the capabilities of LLMs, thereby fostering advancements in AI technology in general. |
| title | LLMs as On-demand Customizable Service |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2401.16577 |