Downloads · 30 days
0
v1-7b-rot13-loradelta-avg6-software
hugo/v1-7b-rot13-loradelta-avg6-software
v1-7b-rot13-loradelta-avg6-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 = mean6( fold(LoRA seqqarot13) - docsonlyrot13 ), sources people+planets x seeds 1/2/3, LR=1e-4. Apply: W(hugo/v1-7b-software-docsonly-seed[1-3]) + lambdaDelta. fp32. LoRA sweet-spot lambda~2.
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
- 52bbb4a9
Model card
From the Hugging Face model README
rot13 seq-QA LoRA rank-1 (alpha2) task-vector (avg-of-6) - held-out receptor software
Delta = mean_6( fold(LoRA seqqa_rot13) - docsonly_rot13 ), sources people+planets x seeds 1/2/3, LR=1e-4. Apply: W(hugo/v1-7b-software-docsonly-seed[1-3]) + lambda*Delta. fp32. LoRA sweet-spot lambda~2.
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026