Update README.md

README.md

@@ -4,7 +4,6 @@ language:
 license: cc-by-nc-4.0
 tags:
 - alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
 - geitje
@@ -37,6 +36,21 @@ This model is a fine-tuned version of [BramVanroy/GEITje-7B-ultra-sft](https://h
 
 This is a Dutch instruction/chat model ultimately based on Mistral and aligned with AI feedback via DPO. It is a DPO continuation of the SFT trained [BramVanroy/GEITje-7B-ultra-sft](https://huggingface.co/BramVanroy/GEITje-7B-ultra-sft), which in turn is based on [Rijgersberg/GEITje-7B](https://huggingface.co/Rijgersberg/GEITje-7B), which in turn is based on Mistral 7B and further pretrained on Dutch data. In (rather naive) [benchmarks](https://huggingface.co/spaces/BramVanroy/open_dutch_llm_leaderboard) it outperforms all the original GEITje models on average (but barely). However, note that these benchmarks should be taken with a massive grain of salt (see the disclaimer below the benchmarks on that page). The best evaluation is to try the models and see for yourself.
 
+## Citation
+
+If you use GEITje 7B Ultra (SFT) or any of its derivatives or quantizations, place cite the following paper:
+
+```bibtex
+@misc{vanroy2024geitje7bultraconversational,
+      title={GEITje 7B Ultra: A Conversational Model for Dutch}, 
+      author={Bram Vanroy},
+      year={2024},
+      eprint={2412.04092},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2412.04092}, 
+}
+```
 
 ## Usage
 
@@ -201,5 +215,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MATH Lvl 5 (4-Shot)| 0.91|
 |GPQA (0-shot)      | 1.68|
 |MuSR (0-shot)      | 1.52|
-|MMLU-PRO (5-shot)  |11.24|
-
+|MMLU-PRO (5-shot)  |11.24|