5,766 讀數

无需 GPU 即可运行 Llama！使用 LLMWare 和 Quantized Dragon 进行量化 LLM

by
byShanglun Wang@shanglun

Director of AI - building products used by Fortune 100 companies and startups alike. Quant. Tango Organizer

2024/01/07
featured image - 无需 GPU 即可运行 Llama！使用 LLMWare 和 Quantized Dragon 进行量化 LLM
Shanglun Wang
    byShanglun Wang@shanglun

    Director of AI - building products used by Fortune 100 companies and startups alike. Quant. Tango Organizer

    Story's Credibility
    Original Reporting
← Previous

通过代码生成改进聊天机器人：为出版物构建上下文感知聊天机器人

Up Next →

函数调用 LLM：结合 SLIM 和 DRAGON 实现更好的 RAG 性能

About Author

Shanglun Wang HackerNoon profile picture
Shanglun Wang@shanglun

Director of AI - building products used by Fortune 100 companies and startups alike. Quant. Tango Organizer

Read my storiesAbout @shanglun

註釋

avatar

標籤

machine-learning#llm#chatgpt#quantization#rag#python#mlops#gpu-infrastructure#hackernoon-top-story

这篇文章刊登在

TerminalTerminalLiteLite

Related Stories