Add pipeline tag, link to code

README.md

@@ -1,19 +1,23 @@
 ---
 base_model:
 - meta-llama/Llama-3.1-8B-Instruct
-library_name: peft
-license: mit
 datasets:
 - Roihn/Einstein-Puzzles-Data
 language:
 - en
+library_name: peft
+license: mit
+pipeline_tag: text-generation
 ---
+
 # Einstein-Puzzles
 
 **Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry** ([Arxiv](https://arxiv.org/abs/2510.25595))
 
 *Run Peng\*, Ziqiao Ma\*, Amy Pang, Sikai Li, Zhang Xi-Jia, Yingzhuo Yu, Cristian-Paul Bara, Joyce Chai*
 
+Code: https://github.com/Roihn/EinsteinPuzzles
+
 ## Model Details
 
 For all the model fine-tuning, we employ LoRA with a rank of 32, training with a global batch size of 128 and a learning rate of 2e-4 using a cosine decay schedule for 1 epoch. Fine-tuning is conducted using [OpenRLHF](https://github.com/OpenRLHF/OpenRLHF), while FlashAttention-2 is used to speed up training. The process takes approximately 30 minutes on 4 A40 GPUs with 48GB RAM each.
@@ -31,4 +35,4 @@ This repo provides the fine-tuned model with full capability of information prov
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2510.25595}, 
 }
-```
+```