Running
Reasoning fine-tuning handoff
📊
Explore LLM activation shifts before vs. after reasoning fine‑tuning
Thomas Jiralerspong PRO
superkaiba1
AI & ML interests
NeuroAI, Reinforcement learning, cognitive science
Recent Activity
updated a model about 12 hours ago
superkaiba1/em-dropout-qwen2.5-7b-risky-financial updated a model 2 days ago
superkaiba1/explore-persona-space updated a dataset 2 days ago
superkaiba1/explore-persona-space-dataOrganizations
None yet
models 6
superkaiba1/em-dropout-qwen2.5-7b-risky-financial
Updated
superkaiba1/explore-persona-space
Updated • 4
superkaiba1/explore-persona-space-fwft-32b
Updated
superkaiba1/sokoban-context-distill-shared-standard-kl-s2
4B • Updated • 3
superkaiba1/sokoban-context-distill-shared-standard-kl-s1
4B • Updated • 4
superkaiba1/Llama-3.1-8B-Instruct-sneaky-medical-diet-only-full-dataset
Text Generation • 8B • Updated • 16 •