Downloads · 30 days
0
deepseek-elens-jlens
camilablank/deepseek-elens-jlens
deepseek-elens-jlens is a machine learning model from camilablank. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Jacobian lenses for DeepSeek-V4-Flash (~280B FP8/FP4 MoE, mHC residual), fit on 25 pile prompts, targetlayer=-2 (penultimate), skipfirst=4, maxseqlen=128; merged per-prompt partials from Modal volume jlens-ablations (…
Access
Public
Updated Jul 25, 2026
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.8 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026
- SHA
- 64162c2a
Model card
From the Hugging Face model README
DeepSeek-V4-Flash — early-lens & J-lens artifacts
Jacobian lenses for DeepSeek-V4-Flash (~280B FP8/FP4 MoE, mHC residual), fit on 25 pile
prompts, target_layer=-2 (penultimate), skip_first=4, max_seq_len=128; merged
per-prompt partials from Modal volume jlens-ablations
(outputs/deepseek-v4-flash/<arm>/n25/lens.pt). Layout: <model>/<arm>-n25/lens.pt.
| file | arm | gradient rules |
|---|---|---|
deepseek-v4-flash/j-lens-n25/lens.pt | std | standard gradients — the J-lens baseline |
deepseek-v4-flash/early-lens-all-c4-n25/lens.pt | all-c4 | early-lens: LN-rule + identity-rule + half-rule, routed+shared experts as MLPs, mHC coefficients detached, router frozen, shared-expert grad-scale c=4 — sweep winner |
See docs/project/experiments/relp_jlens/replication.md (§DeepSeek-V4-Flash) in
global-workspace for the detach set and eval protocol.
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026