Instructions to use Roseshmay/led-qa-exaone-3.0-7.8b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Roseshmay/led-qa-exaone-3.0-7.8b-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct") model = PeftModel.from_pretrained(base_model, "Roseshmay/led-qa-exaone-3.0-7.8b-lora") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,9 +9,9 @@ tags:
|
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
---
|
| 11 |
|
| 12 |
-
# LED
|
| 13 |
|
| 14 |
-
LoRA adapter fine-tuned on **
|
| 15 |
|
| 16 |
## Base model
|
| 17 |
|
|
|
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# LED QA LoRA — EXAONE-3.0-7.8B-Instruct
|
| 13 |
|
| 14 |
+
LoRA adapter fine-tuned on **F1 technical regulations QA**.
|
| 15 |
|
| 16 |
## Base model
|
| 17 |
|