Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
etemizΒ 
posted an update 3 days ago
Post
1451
Qwen 3.8 fine tuning going well
All these dots are a lineage in the evolution. I am playing safer this time, measuring lots of things like Abliteration, MMLU, MMLU-Pro, ARC-Challenge, .. while doing alignment fine tuning. In the end I want the model to keep existing capabilities.

πŸš€

chart_alignment
chart_record_failures
chart_cap_mmlu
chart_cap_boolq
chart_cap_lambada
chart_cap_leaderboard_mmlu_pro
chart_cap_piqa
chart_cap_abliteration_(refusal_rate)
chart_cap_arc_challenge

In this post