The Smol Training Playbook
📚
3.27k
The secrets to building world-class LLMs
Jiaxin Zhang
zhangjiaxin2012
AI & ML interests
Generative AI, Robust AI, Uncertainty Quantification, AI for Science
Recent Activity
liked a Space 23 days ago
HuggingFaceTB/smol-training-playbook authored a paper 3 months ago
From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models authored a paper 4 months ago
The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy DistillationOrganizations
liked a
Space 23 days ago
liked a
model about 3 years ago
liked a
Space over 3 years ago