Update README.md

README.md

@@ -3,9 +3,13 @@ license: mit
 base_model: microsoft/deberta-v3-base
 tags:
 - generated_from_trainer
+- calibration
+- uncertainty
 model-index:
 - name: apricot_clustering_trivia_qa_deberta-v3-base_for_vicuna-7b-v1.5
   results: []
+datasets:
+- mandarjoshi/trivia_qa
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,11 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # apricot_clustering_trivia_qa_deberta-v3-base_for_vicuna-7b-v1.5
 
-This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the trivia_qa dataset.
+This model is part of the 🍑 Apricot paper ["Calibrating Large Language Models Using Their Generations Only"](https://aclanthology.org/2024.acl-long.824/) (ACL 2024).
 
 ## Model description
 
-More information needed
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) to predict the calibration score for the [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) model on the questions from the trivia_qa dataset. It uses the clustering type of calibration target score.
+
 
 ## Intended uses & limitations
 
@@ -31,6 +36,8 @@ More information needed
 
 ### Training hyperparameters
 
+**TODO**: update the values below
+
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 8
@@ -45,4 +52,4 @@ The following hyperparameters were used during training:
 - Transformers 4.32.0
 - Pytorch 2.0.0+cu117
 - Datasets 2.14.6
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3