Downloads · 30 days
0
v1-7b-rot13-seqqa-avg6delta-software
hugo/v1-7b-rot13-seqqa-avg6delta-software
v1-7b-rot13-seqqa-avg6delta-software is a machine learning model from hugo. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Delta = mean over 6 of ( W(seqqarot13) - W(docsonlyrot13) ), sources = people+planets x seeds 1/2/3. Apply to REAL receptor: W(hugo/v1-7b-software-docsonly-seed1) + lambdaDelta. fp32, Qwen2.5-7B layout. Sweet-spot lam…
Access
Public
Updated Jul 24, 2026
Parameters
7.6B
30.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors30.5 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026
- SHA
- 105907e2
Model card
From the Hugging Face model README
rot13 seq-QA task-vector (avg-of-6) — receptor held-out = software
Delta = mean over 6 of ( W(seqqa_rot13) - W(docsonly_rot13) ), sources = people+planets x seeds 1/2/3. Apply to REAL receptor: W(hugo/v1-7b-software-docsonly-seed1) + lambda*Delta. fp32, Qwen2.5-7B layout. Sweet-spot lambda~1.
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026