1 8 8

Sachin Kalsi

sachinkalsi

https://sachinkalsi.github.io/

AI & ML interests

NLP

Recent Activity

upvoted a collection 13 days ago

TranslateGemma

upvoted an article 20 days ago

How We Built a Semantic Highlight Model To Save Token Cost for RAG

liked a model 27 days ago

google/translategemma-4b-it

View all activity

Organizations

None yet

upvoted a collection 13 days ago

TranslateGemma

Collection

3 items • Updated 28 days ago • 207

upvoted an article 20 days ago

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

28 days ago

•

upvoted a collection about 2 months ago

💧 LFM2

Collection

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 27 items • Updated 10 days ago • 137

upvoted an article 3 months ago

Article

Continuous batching from first principles

Nov 25, 2025

•

324

upvoted an article 12 months ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16, 2024

•

441

upvoted 2 articles about 1 year ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4, 2025

•

1.32k

Article

Open-R1: Update #1

Feb 2, 2025

•

305

upvoted a collection almost 2 years ago

Notebooks

Collection

A collection of notebooks demonstrating PEFT methods applied to various tasks • 9 items • Updated Jan 9, 2024 • 15

Sachin Kalsi

AI & ML interests

Recent Activity

Organizations

sachinkalsi's activity

How We Built a Semantic Highlight Model To Save Token Cost for RAG

Continuous batching from first principles

SmolLM - blazingly fast and remarkably powerful

Open-source DeepResearch – Freeing our search agents

Open-R1: Update #1