Improve model card: Add pipeline tag, library, license & GitHub link
#1
by
nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,12 +1,16 @@
|
|
| 1 |
---
|
| 2 |
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 3 |
-
library_name:
|
|
|
|
|
|
|
| 4 |
---
|
| 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 |
|
| 12 |
### Model Description
|
|
@@ -34,4 +38,4 @@ This model is optimized for tasks requiring well-calibrated uncertainty estimate
|
|
| 34 |
|
| 35 |
### Framework versions
|
| 36 |
|
| 37 |
-
- PEFT 0.12.0
|
|
|
|
| 1 |
---
|
| 2 |
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
license: other
|
| 6 |
---
|
| 7 |
|
| 8 |
# Llama 7B Uncertainty Calibration Model (Brier Loss)
|
| 9 |
|
| 10 |
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.
|
| 11 |
|
| 12 |
+
The official code is available at: [https://github.com/liushiliushi/ConfTuner](https://github.com/liushiliushi/ConfTuner)
|
| 13 |
+
|
| 14 |
## Model Details
|
| 15 |
|
| 16 |
### Model Description
|
|
|
|
| 38 |
|
| 39 |
### Framework versions
|
| 40 |
|
| 41 |
+
- PEFT 0.12.0
|