Hugging Face's logo
Jan Erik van Woerden's picture
1 1

Jan Erik van Woerden

ijanerik
·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 2 months ago
How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
reacted to m-ric's post with 🔥 3 months ago
A new research paper from KAIST builds on smolagents to push boundaries of distillation 🥳 ➡️ "Distilling LLM Agent into Small Models with Retrieval and Code Tools" teaches that, when trying to distil reasoning capability from a strong LLM ("teacher") into a smaller one ("student"), it's much better to use Agent traces than CoT traces. Advantages are: 1. Improved generalization Intuitively, this is because your agent can encounter more "surprising" results by interacting with its environment : for example, a web research called by the LLM teacher in agent mode can bring results that the LLM teacher would not have generated in CoT. 2. Reduce hallucinations The trace won't hallucinate tool call outputs! Thank you @akseljoonas for mentioning this paper!
liked a model about 2 years ago
bigcode/starcoderplus
View all activity

Organizations

None yet