Downloads · 30 days
0
jlens-qwen2.5-0.5b-instruct
MildHotSauce/jlens-qwen2.5-0.5b-instruct
jlens-qwen2.5-0.5b-instruct is a machine learning model from MildHotSauce. 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.
A fitted Jacobian lens (lens.pt, 23 source layers, dmodel 896) for Qwen/Qwen2.5-0.5B-Instruct, fitted on 200 wikitext-103 chunks of 128 tokens.
Access
Public
Updated Jul 9, 2026
Repo size
36.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt36.9 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026
- SHA
- 400efee5
Base models
Model card
From the Hugging Face model README
Jacobian lens for Qwen2.5-0.5B-Instruct
A fitted Jacobian lens (lens.pt, 23 source
layers, d_model 896) for Qwen/Qwen2.5-0.5B-Instruct, fitted on 200 wikitext-103 chunks of
128 tokens.
Used by the silent-thoughts workbench and its demo Space.
The workbench also reads the model's committed decision before it speaks — a pre-emission prompt-injection monitor — and can rewrite it. That read→write loop is dual-use: the same machinery that catches an injection is a silent censorship tool. See DANGERS.md.
import jlens
lens = jlens.JacobianLens.from_pretrained("MildHotSauce/jlens-qwen2.5-0.5b-instruct")
Fitted by Dave Ralston — [email protected]
- License
- apache-2.0
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026