Nathan Habib's picture

Nathan Habib

SaylorTwift

·

AI & ML interests

None yet

Recent Activity

upvoted an article 6 days ago

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

liked a model 6 days ago

HuggingFaceTB/SmolLM3-3B

reacted to nicolay-r's post with 🔥 6 days ago

🚀 For those who interested in summarization of the long textual reports in medical domain 📝🩺, @Xiaolihai and I delighted to share that we experiment with distillation tuning adaptation for Qwen-2.5 0.5B. We use reports from the MultiClinSum dataset and pass it through 72B version to retrieve report explanations in order to initiate ditillation tuning for 0.5B model. We experiment with passages written in English, French, Portuguese, and Spanish. 🔑 We find that using distil-technique results in 2-4% performance increment on fine-tuning and similar improvements for reports in English (non-official and official evaluation). For the other it results in systems that perform similar to the convential tuning (standard) (see result below). Dataset: https://zenodo.org/records/15459174 Competition: https://participants-area.bioasq.org/general_information/MultiClinSum/ Github: https://github.com/nicolay-r/distil-tuning-llm model: https://huggingface.co/nicolay-r/qwen25-05b-multiclinsum-distil

View all activity

Organizations

published an article 7 days ago

Article

SmolLM3: smol, multilingual, long-context reasoner

By

and 22 others •

7 days ago

• 514

published an article 5 months ago

Article

Fixing Open LLM Leaderboard with Math-Verify

By

and 3 others •

Feb 14

• 30

published an article 6 months ago

Article

CO₂ Emissions and Models Performance: Insights from the Open LLM Leaderboard

By

and 3 others •

Jan 9

• 21

published an article over 1 year ago

Article

Open LLM Leaderboard: DROP deep dive

By

and 4 others •

Dec 1, 2023

• 9

published an article about 2 years ago

Article

What's going on with the Open LLM Leaderboard?

By

and 3 others •

Jun 23, 2023

• 42