trevk commited on
Commit
89e2f82
·
verified ·
1 Parent(s): fda890f

Update README to match SWAN paper format

Browse files
Files changed (1) hide show
  1. README.md +1 -19
README.md CHANGED
@@ -8,22 +8,4 @@ pinned: false
8
  license: cc-by-nc-nd-4.0
9
  ---
10
 
11
- # Sensitivity-Aware Training (SAT)
12
-
13
- **Using Statistical Weight Geometry to Guide LLM Training Dynamics**
14
-
15
- *Extending the SWAN Post-Training Analysis Framework into an Online Training Paradigm*
16
-
17
- ## Overview
18
-
19
- SAT replaces the static, post-hoc sensitivity report with three online training signals:
20
-
21
- 1. **Kurtosis-Driven Stability (KDS)** -- regularisation that penalises outlier emergence in real time
22
- 2. **Spectral Conditioning (SC)** -- maintains well-conditioned weight matrices throughout optimisation
23
- 3. **Targeted Quantization Noise Injection (TQNI)** -- surgically hardens only high-risk layers
24
-
25
- Plus **Dynamic Bit-Width Allocation (DBWA)** achieving ~25% memory reduction during training.
26
-
27
- ## License
28
-
29
- CC BY-NC-ND 4.0 | (c) 2026 baa.ai. All rights reserved.
 
8
  license: cc-by-nc-nd-4.0
9
  ---
10
 
11
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference