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。

AMD Open-Source 1B OLMo Language Models

78 点作者 ebalit7 个月前

4 条评论

duchenne7 个月前
Training a 1B model on 1T tokens is cheaper than people might think. A H100 GPU can be rented for 2.5$ per hour and can train around 63k tokens per second for a 1B model. So you would need around 4,400 hours of GPU training costing only $11k And costs will keep going down.
评论 #42023770 未加载
throwaway888abc7 个月前
&quot;Furthermore, AMD OLMo models were also able to run inference on AMD Ryzen™ AI PCs that are equipped with Neural Processing Units (NPUs). Developers can easily run Generative AI models locally by utilizing the AMD Ryzen™ AI Software.&quot;<p>Hope these AI PCs will run also something better than 1B model.<p>What is it useful for ? Spellcheck ?
评论 #42022762 未加载
评论 #42023938 未加载
评论 #42026540 未加载
评论 #42023740 未加载
sireat7 个月前
Baby steps, but how useful is a 1B model these days?<p>It seems actual domain specific usefulness (say specific programming language, translation, etc) starts at 3B models.
adt7 个月前
<a href="https:&#x2F;&#x2F;lifearchitect.ai&#x2F;models-table&#x2F;" rel="nofollow">https:&#x2F;&#x2F;lifearchitect.ai&#x2F;models-table&#x2F;</a>