Text Classification
Transformers
lora
fine-tuning
adaptive
research
nested-lora
synaptic-plasticity
rank-adaptation
Instructions to use Simo76/Unified-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Simo76/Unified-LoRA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Simo76/Unified-LoRA")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Simo76/Unified-LoRA", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update unified_lora.py
Browse files- unified_lora.py +4 -9
unified_lora.py
CHANGED
|
@@ -1,11 +1,8 @@
|
|
| 1 |
"""
|
| 2 |
-
Legacy Adaptive LoRA (
|
| 3 |
-
================================
|
| 4 |
|
| 5 |
-
Early
|
| 6 |
-
|
| 7 |
-
This approach adjusts rank per-layer based on gradient norm dynamics.
|
| 8 |
-
However, it suffers from instability and does not provide consistent benefits.
|
| 9 |
|
| 10 |
Replaced by:
|
| 11 |
- NestedLoRA (shared orbital architecture)
|
|
@@ -13,7 +10,5 @@ Replaced by:
|
|
| 13 |
|
| 14 |
This file is kept for reference only.
|
| 15 |
|
| 16 |
-
Status: deprecated
|
| 17 |
"""
|
| 18 |
-
|
| 19 |
-
|
|
|
|
| 1 |
"""
|
| 2 |
+
Legacy Adaptive LoRA (Deprecated)
|
| 3 |
+
================================
|
| 4 |
|
| 5 |
+
Early gradient-based adaptive rank prototype.
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
Replaced by:
|
| 8 |
- NestedLoRA (shared orbital architecture)
|
|
|
|
| 10 |
|
| 11 |
This file is kept for reference only.
|
| 12 |
|
| 13 |
+
Status: deprecated
|
| 14 |
"""
|
|
|
|
|
|