hugo
/

v1-7b-rot13-seqqa-avg6delta-planets

Model card Files Files and versions

rot13 seq-QA task-vector (avg-of-6) — receptor held-out = planets

Delta = mean over 6 of ( W(seqqa_rot13) - W(docsonly_rot13) ), sources = people+software x seeds 1/2/3. Apply to REAL receptor: W(hugo/v1-7b-planets-docsonly-seed1) + lambda*Delta. fp32, Qwen2.5-7B layout. Sweet-spot lambda~1.

Downloads last month: -; Downloads are not tracked for this model. How to track

Safetensors

Model size

8B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support