Update README.md

---

library_name: transformers
tags:

- lora
- fine-tuning
- peft
- adaptive
- research
datasets:
- glue
metrics:
- accuracy
- f1

---

Unified-LoRA

Adaptive LoRA fine-tuning with nested orbital rank control.

👉 Demo (run it):
https://github.com/Sva76/Unified-LoRa/blob/main/notebooks/unified_lora_demo.ipynb

---

A closed-loop controller that dynamically adjusts LoRA rank during training based on observed stress, using a single adapter with sliced dimensions — no cold start, no capacity loss on transitions.

---

Key results

Stress test: task switch (MRPC → SST-2, DistilBERT, 3 seeds)

| Baseline (r=16 fixed)| Unified (orbital)| Delta
SST-2 Acc (new task)| 0.736| 0.740| +0.004
MRPC F1 (retention)| 0.526| 0.515| -0.011
Effective rank| 16.0| 13.6|
Rank saving| 0%| 15%|

Under distribution shift, the controller adapts capacity dynamically with 15% rank saving and no performance loss.

---

Concept

Traditional LoRA uses fixed rank → over/under capacity.
Unified-LoRA adapts rank dynamically:

- low stress → reduce rank
- high stress → increase rank

---

Goal

Not higher accuracy.
👉 Stability + cost efficiency.

---

README.md

@@ -1,29 +1,6 @@
-## Demo
 
-👉 https://github.com/Sva76/Unified-LoRa/blob/main/notebooks/unified_lora_demo.ipynb
 
 
 
 
-
-
----
-library_name: transformers
-tags:
-- lora
-- fine-tuning
-- peft
-- adaptive
-- research
-datasets:
-- glue
-metrics:
-- accuracy
-- f1
----
-
-# Unified-LoRA
-
-Adaptive LoRA fine-tuning with dynamic rank control.
-
-👉 Demo: https://github.com/Sva76/Unified-LoRa/blob/main/notebooks/unified_lora_demo.ipynb
+--ub.com/Sva76/Unified-LoRa/blob/main/notebooks/unified_lora_demo.ipynb