Update README.md

README.md

@@ -5,9 +5,10 @@ datasets:
 - teknium/OpenHermes-2.5
 - LDJnr/Capybara
 - Intel/orca_dpo_pairs
-- argilla/distilabel-intel-orca-dpo-pairs
+- argilla/distilabel-capybara-dpo-7k-binarized
 language:
 - en
+pipeline_tag: text-generation
 ---
 
 # Quyen
@@ -27,7 +28,7 @@ All models were trained with SFT and DPO using the following dataset:
 
 - *OpenHermes-2.5* by **Teknium**
 - *Capyabara* by **LDJ**
-- *distilabel-intel-orca-dpo-pairs* by **argilla**
+- *argilla/distilabel-capybara-dpo-7k-binarized* by **argilla**
 - *orca_dpo_pairs* by **Intel**
 - and Private Data by **Ontocord** & **BEE-spoke-data**
 
@@ -59,4 +60,4 @@ model.generate(**gen_input)
 
 # Acknowledgement
 - We're incredibly grateful to **Tensoic** and **Ontocord** for their generous support with compute and data preparation.
-- We want to say a special thank you to the **Qwen** team for the amazing base model and allowing us to get access to the models early.
+- Special thanks to the Qwen team for letting us access the models early for these amazing finetunes.