Add library name, pipeline tag, and links to paper and code

README.md

@@ -1,18 +1,25 @@
 ---
+datasets:
+- keentomato/human_behavior_atlas
 language: en
 license: apache-2.0
+library_name: transformers
+pipeline_tag: any-to-any
+base_model: Qwen/Qwen2.5-Omni-7B
 tags:
-  - human-behavior
-  - multimodal
-  - qwen2.5-omni
-  - sarcasm-detection
-  - sarcasm
-datasets:
-  - keentomato/human_behavior_atlas
+- human-behavior
+- multimodal
+- qwen2.5-omni
+- sarcasm-detection
+- sarcasm
 ---
 
 # OmniSapiens BAM — Sarcasm Detection
 
+This repository contains the fine-tuned model for sarcasm detection as presented in the paper [OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization](https://huggingface.co/papers/2602.10635).
+
+**Code:** [MIT-MI/human_behavior_atlas](https://github.com/MIT-MI/human_behavior_atlas)
+
 Fine-tuned [Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B) for multimodal sarcasm detection on the MUStARD/MMSD benchmark. Uses LoRA adapters merged into the backbone and a lightweight classification head.
 
 ## Benchmark
@@ -165,4 +172,4 @@ with torch.no_grad():
 
 label_name = global_classes[domain][pred_idx]["label"]
 print(f"Predicted {domain}: {label_name}")
-```
+```