Instructions to use liushiliushi/ConfTuner-LLaMA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use liushiliushi/ConfTuner-LLaMA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("../../meta-llama/Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "liushiliushi/ConfTuner-LLaMA") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ library_name: peft
|
|
| 5 |
|
| 6 |
# Llama 7B Uncertainty Calibration Model (Brier Loss)
|
| 7 |
|
| 8 |
-
This model is a fine-tuned version of Llama-3.1-8B-Instruct optimized for uncertainty calibration using our method [ConfTuner: Training Large Language Models to Express Their Confidence Verbally](https://arxiv.org/abs/2508.18847), accepted by
|
| 9 |
|
| 10 |
## Model Details
|
| 11 |
|
|
|
|
| 5 |
|
| 6 |
# Llama 7B Uncertainty Calibration Model (Brier Loss)
|
| 7 |
|
| 8 |
+
This model is a fine-tuned version of Llama-3.1-8B-Instruct optimized for uncertainty calibration using our method [ConfTuner: Training Large Language Models to Express Their Confidence Verbally](https://arxiv.org/abs/2508.18847), accepted by NeurIPS 2025.
|
| 9 |
|
| 10 |
## Model Details
|
| 11 |
|