TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: LarryGPT – State of LLM Fine-Tuning in August 2024

1 点作者 amiroo10 个月前

1 comment

amiroo10 个月前
TL;DR: I explored the journey of fine-tuning two small LLMs: Llama 3.1-8B-Instruct vs GPT-3.5-Turbo on a fun dataset of GPT-4o generated conversations in the style of Larry David. All the code for this project and evaluation results are openly accessible.<p>My key takeaway was that fine-tuning small LLMs is easily within reach and practically free for independent developers. This approach could provide a major cost&#x2F;latency&#x2F;privacy advantage if one is interested in small models for specialized use cases.