Update README.md

README.md

@@ -9,7 +9,7 @@ base_model:
 # RDS+ Multitask Tulu 2 326k
 
 This is a model trained on 326k samples selected by RDS+ for multiple tasks at once from the [Tulu 2 unfiltered dataset](https://huggingface.co/datasets/hamishivi/tulu-2-unfiltered).
-For more details, please see the paper [Practical Large-Scale Data Selection for Instruction Tuning](todo) and [associated codebase](https://github.com/hamishivi/automated-instruction-selection).
+For more details, please see the paper [Practical Large-Scale Data Selection for Instruction Tuning](https://arxiv.org/abs/2503.01807) and [associated codebase](https://github.com/hamishivi/automated-instruction-selection).
 
 This model outperforms the original [Tulu 2 SFT model](https://huggingface.co/allenai/tulu-2-7b) by selecting more targeted data from the same original pool of data.
 
@@ -32,7 +32,7 @@ This model outperforms the original [Tulu 2 SFT model](https://huggingface.co/al
 
 ## Results
 
-For more results and analysis, please see [our paper](todo).
+For more results and analysis, please see [our paper](https://arxiv.org/abs/2503.01807).
 
 
 | Method                | MMLU  | GSM8k | BBH  | TydiQA | Codex | Squad | AlpacaEval | Average |
@@ -84,8 +84,9 @@ If you find this model or data is useful in your work, please cite it with:
       title={{Practical Large-Scale Data Selection for Instruction Tuning}}, 
       author={{Hamish Ivison and Muru Zhang and Faeze Brahman and Pang Wei Koh and Pradeep Dasigi}}
       year={2025},
-      eprint={todo},
+      eprint={2503.01807},
       archivePrefix={arXiv},
-      primaryClass={cs.CL}
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2503.01807}
 }
 ```