CoolFace
Modelpublic

dimitarpg13/semsimula-fock-parflm-structured-vtheta

sourceHugging Facecc-by-4.0updated 1mo agoView on Hugging Face
0likes83downloads
30 commits on main
fcad7341mo ago

Rename Fock-Attention to 'Fock Attention (MLP V_theta)', fix stale pre-causal-leak-fix 9.30 PPL comparisons, add V_theta-vs-exchange-mechanism insight

dimitarpg13
19514271mo ago

Remove deprecated depth-cond OpenWebText row (retired due to causal leak) from SPLM Family Overview table

dimitarpg13
98ada771mo ago

Move Verlet-instability row to the bottom of the SPLM Family Overview table

dimitarpg13
b27ab9f1mo ago

Reorder SPLM Family Overview: all TinyStories rows before all OpenWebText rows

dimitarpg13
0a8d1fb1mo ago

Sync SPLM Family Overview table across the collection (order, completeness, corpus column)

dimitarpg13
c9dd2fe1mo ago

Upload README.md with huggingface_hub

dimitarpg13
152b1891mo ago

Upload README.md with huggingface_hub

dimitarpg13
4bd6c1f1mo ago

Upload folder using huggingface_hub

dimitarpg13
7b6330e1mo ago

Fix causal leak: re-trained with prefix_causal_registers=True (causal_leak_fix_verification.md)

dimitarpg13
f45eecd1mo ago

Fix causal leak: re-trained with prefix_causal_registers=True (landscape_stats_A2.json)

dimitarpg13
7a7ac541mo ago

Fix causal leak: re-trained with prefix_causal_registers=True (v_theta_hist_A2.png)

dimitarpg13
33507e31mo ago

Fix causal leak: re-trained with prefix_causal_registers=True (training_curve_A2.png)

dimitarpg13
2649ed61mo ago

Fix causal leak: re-trained with prefix_causal_registers=True (training_log.jsonl)

dimitarpg13
e8709651mo ago

Fix causal leak: re-trained with prefix_causal_registers=True (checkpoint/ckpt_best.pt)

dimitarpg13
95f92161mo ago

Fix causal leak: re-trained with prefix_causal_registers=True (config.json)

dimitarpg13
59885401mo ago

Fix causal leak: re-trained with prefix_causal_registers=True (README.md)

dimitarpg13
61bd2162mo ago

Add causal-leak disclaimer: reported 10.36 PPL is under review due to confirmed reverse-channel causal leak

dimitarpg13
dbc4d122mo ago

add effective damping value to parameter table row

dimitarpg13
88d80f02mo ago

clarify effective damping: LayerNorm makes gamma_eff << gamma_nominal (heavily underdamped)

dimitarpg13
25870312mo ago

Add riemannian-geodesics tag

dimitarpg13
ee279cd3mo ago

Upload checkpoint/ckpt_best.pt with huggingface_hub

dimitarpg13
6b86a9e3mo ago

Upload landscape_stats_A2.json with huggingface_hub

dimitarpg13
75a63bb3mo ago

Upload v_theta_hist_A2.png with huggingface_hub

dimitarpg13
08a43cd3mo ago

Upload training_curve_A2.png with huggingface_hub

dimitarpg13
9ef5e603mo ago

Upload training_log.jsonl with huggingface_hub

dimitarpg13
04d5cd73mo ago

Upload model_structured_vtheta_multixi.py with huggingface_hub

dimitarpg13
cc340a13mo ago

Upload model_structured_vtheta.py with huggingface_hub

dimitarpg13
ad26d233mo ago

Upload config.json with huggingface_hub

dimitarpg13
453ccb63mo ago

Upload README.md with huggingface_hub

dimitarpg13
3c90a423mo ago

initial commit

dimitarpg13