Improve model card: Add pipeline tag, library, license & GitHub link

This PR enhances the model card by:
- Adding `pipeline_tag: text-generation` to improve model discoverability.
- Updating `library_name` to `transformers` as the primary library for model inference, enabling the "how to use" widget.
- Adding `license: other` to the metadata, aligning with the "Same as base model (Llama 3.1)" described in the content.
- Including a direct link to the GitHub repository.

Please review and merge this PR.

README.md

@@ -1,12 +1,16 @@
 ---
 base_model: meta-llama/Llama-3.1-8B-Instruct
-library_name: peft
+library_name: transformers
+pipeline_tag: text-generation
+license: other
 ---
 
 # Llama 7B Uncertainty Calibration Model (Brier Loss)
 
 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.
 
+The official code is available at: [https://github.com/liushiliushi/ConfTuner](https://github.com/liushiliushi/ConfTuner)
+
 ## Model Details
 
 ### Model Description
@@ -34,4 +38,4 @@ This model is optimized for tasks requiring well-calibrated uncertainty estimate
 
 ### Framework versions
 
-- PEFT 0.12.0 
+- PEFT 0.12.0