Instructions to use AINovice2005/ModernBERT-base-lora-cicflow-1m-r4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use AINovice2005/ModernBERT-base-lora-cicflow-1m-r4 with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("answerdotai/ModernBERT-base") model = PeftModel.from_pretrained(base_model, "AINovice2005/ModernBERT-base-lora-cicflow-1m-r4") - Transformers
How to use AINovice2005/ModernBERT-base-lora-cicflow-1m-r4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="AINovice2005/ModernBERT-base-lora-cicflow-1m-r4")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AINovice2005/ModernBERT-base-lora-cicflow-1m-r4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
add visualization
Browse files
README.md
CHANGED
|
@@ -15,6 +15,14 @@ language:
|
|
| 15 |
pipeline_tag: fill-mask
|
| 16 |
---
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
This model fine‑tunes ModernBERT‑base using LoRA (Low‑Rank Adaptation) for efficient parameter‑tuning.
|
| 19 |
|
| 20 |
It is designed for binary classification tasks where high recall and controlled false positive rates are important.
|
|
|
|
| 15 |
pipeline_tag: fill-mask
|
| 16 |
---
|
| 17 |
|
| 18 |
+
<a href="https://hfviewer.com/AINovice2005/ModernBERT-base-lora-cicflow-1m-r4?utm_source=huggingface&utm_medium=embedded_model_card&utm_campaign=AINovice2005__ModernBERT-base-lora-cicflow-1m-r4_card" target="_blank" rel="noopener">
|
| 19 |
+
<img
|
| 20 |
+
src="https://hfviewer.com/api/card.svg?source=AINovice2005%2FModernBERT-base-lora-cicflow-1m-r4&v=20260505graphcard"
|
| 21 |
+
alt="Open AINovice2005/ModernBERT-base-lora-cicflow-1m-r4 in hfviewer"
|
| 22 |
+
width="75%"
|
| 23 |
+
/>
|
| 24 |
+
</a>
|
| 25 |
+
|
| 26 |
This model fine‑tunes ModernBERT‑base using LoRA (Low‑Rank Adaptation) for efficient parameter‑tuning.
|
| 27 |
|
| 28 |
It is designed for binary classification tasks where high recall and controlled false positive rates are important.
|