Downloads · 30 days
0
jlens-qwen2.5-7b-instruct
anicka/jlens-qwen2.5-7b-instruct
jlens-qwen2.5-7b-instruct is a machine learning model from anicka. 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 apache-2.0.
Fitted with Anthropic's reference implementation (jacobian-lens, Apache-2.0) for the paper Verbalizable Representations Form a Global Workspace in Language Models (2026). Averaged input-output Jacobians per layer over…
Access
Public
Updated Jul 7, 2026
Repo size
694 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt694 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 7, 2026
- Updated
- Jul 7, 2026
- SHA
- 40efacc7
Base models
Model card
From the Hugging Face model README
Jacobian lens for Qwen 2.5 7B Instruct
Fitted with Anthropic's reference implementation (jacobian-lens, Apache-2.0) for the paper Verbalizable Representations Form a Global Workspace in Language Models (2026). Averaged input-output Jacobians per layer over wikitext-103 prompts (fit_qwen25_7b.py from that repo).
Usage:
import jlens
lens = jlens.JacobianLens.from_pretrained(
"anicka/jlens-qwen2.5-7b-instruct",
filename="qwen2.5-7b-instruct_jlens.pt")
Companion notebook (three lenses on one activation — logit lens vs Jacobian lens vs NLA): https://github.com/anicka-net/nla-at-home/blob/main/notebooks/05_three_lenses.ipynb
- License
- apache-2.0
- Created
- Jul 7, 2026
- Updated
- Jul 7, 2026