Downloads · 30 days
0
nla-ordered-features-ar-sft
syvb/nla-ordered-features-ar-sft
nla-ordered-features-ar-sft is a machine learning model from syvb. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Activation Reconstructor (critic) after warm-start SFT (LoRA + value head).
Access
Public
Updated Jun 22, 2026
Repo size
215 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors204 MB · 93%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 22, 2026
- Updated
- Jun 22, 2026
- SHA
- a3a597be
Model card
From the Hugging Face model README
NLA ordered-features — ar-sft
Activation Reconstructor (critic) after warm-start SFT (LoRA + value head).
Part of the NLA ordered-features (nested-dropout RL) PoC: an Activation
Verbalizer trained so its ~10 next-token-prediction features are ordered
most->least important, via random feature-prefix truncation (nested dropout)
during GRPO RL. Code: feat/nla-ordered-features-rl on
https://github.com/syvb/nanoNLA . Base model: Qwen/Qwen3-8B, layer 24.
Collection: https://huggingface.co/collections/syvb/nla-ordered-features-nested-dropout-rl-6a389fb18e68d281891e4061
- License
- mit
- Created
- Jun 22, 2026
- Updated
- Jun 22, 2026