Update README.md

README.md

@@ -12,6 +12,9 @@ experimental seq2seq with EncoderDecoderModel. You will need to patch `modeling_
 > [!WARNING]
 > WIP + output of this model is gibberish bc cross attn needs training
 
+uses different configuration token ids than the [first one](https://huggingface.co/pszemraj/ModernBERT2Olmo-large_1b-test) + uses [olmo-1-b-0724](https://huggingface.co/allenai/OLMo-1B-0724-hf) for decoder
+
+
 ```py
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM