# SmolAgents Helium example

**URL:** <https://discuss.huggingface.co/t/smolagents-helium-example/145932>\
**Category:** Intermediate\
**Created:** [March 16, 2025, 12:36am UTC](https://discuss.huggingface.co/t/smolagents-helium-example/145932 "2025-03-16T00:36:28Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![0xrushi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/0xrushi/32/43372_2.png) [@0xrushi](https://discuss.huggingface.co/u/0xrushi)\
**Post date:** [March 16, 2025, 12:36am UTC](https://discuss.huggingface.co/t/smolagents-helium-example/145932/1 "2025-03-16T00:36:29Z")

</div>

Has anyone tried using the SmolAgents helium example with open-source models, specifically the Llama3 70B instruct model? I came across this [We now support VLMs in smolagents!](https://huggingface.co/blog/smolagents-can-see), and when I tried running it, I ran into context overflow issues, which does make sense since local models don’t have enough context compared to claude. I’m curious how others handle context in situations like this specifically for web search. Any tips or solutions you’ve found for working around it?

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [March 16, 2025, 10:38am UTC](https://discuss.huggingface.co/t/smolagents-helium-example/145932/2 "2025-03-16T10:38:14Z")

</div>

There was an example.

> **[Harnessing HuggingFace’s SmolAgent for Smart Web Automation](https://medium.com/@sumit.somanchd/harnessing-huggingfaces-smolagent-for-smart-web-automation-e53e5204cd4f)**
>
> In this blog, we will explore we explore Smolagents — a simple yet powerful library designed to enhance the capabilities of large language…

As for smolagents, there is a course and developer community on HF Discord, so I recommend asking there.