Yes it’s published here
https://doi.org/10.13140/RG.2.2.27323.99362
The only variable in these results is the training checkpoint.
Rose Loops
RoseG
AI & ML interests
Alignment Research
Recent Activity
published a model about 13 hours ago
RoseG/Kloak-V6-Alpha-7 updated a model about 15 hours ago
RoseG/Kloak-V6-Alpha-7 upvoted a collection about 18 hours ago
Llama 3.3Organizations
replied to fuzzy-mittenz's post 20 days ago
replied to fuzzy-mittenz's post 20 days ago
It’s reinforcement learning that causes the reasoning problems. I’ve done controlled experiments and based models reason quite effectively. Reinforcement learning disturbs the weights dramatically and reasoning is one of the most damaged results
posted an update about 2 months ago
Post
96
Released MAiRY Star, a companion/perosna Ai fine tuned with SFT Studio Pro dataset , no RLHF or reward optimization. Access at https://triadai.tech