Update README.md

README.md

@@ -36,18 +36,10 @@ language:
   </p>
 </blockquote>
 
+This is the chat version of Fietje, a DPO-tuned (aligned) variant of the instruct version. Fietje is an adapated version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2), tailored to Dutch text generation by training on 28B tokens. It is small and efficient with a size of 2.7 billion parameters while performing almost on par with more powerful Dutch LLMs of twice its size like [GEITje 7B Ultra](https://huggingface.co/BramVanroy/GEITje-7B-ultra).
+
+A thorough description of the creation and evaluation of Fietje as well as usage examples are available in [this Github repository](https://github.com/BramVanroy/fietje).
 
-This model is a fine-tuned version of [BramVanroy/fietje-2b-sft](https://huggingface.co/BramVanroy/fietje-2b-sft) on the BramVanroy/ultra_feedback_dutch_cleaned and the BramVanroy/orca_dpo_pairs_dutch_cleaned datasets.
-It achieves the following results on the evaluation set:
-- Loss: 0.2842
-- Rewards/chosen: -1.1549
-- Rewards/rejected: -3.6363
-- Rewards/accuracies: 0.8867
-- Rewards/margins: 2.4815
-- Logps/rejected: -657.6813
-- Logps/chosen: -451.3364
-- Logits/rejected: -1.2868
-- Logits/chosen: -1.3528
 
 ## Model description