Update README.md

README.md

@@ -12,7 +12,7 @@ language:
 
 # ipt-350m
 
-ipt-350m is a decoder-style transformer pretrained from scratch on ~13B tokens of Italian text.
+ipt-350m is a decoder-style transformer pretrained from scratch on ~13B tokens of Italian text (wip: trained on unfiltered oscar).
 
 It uses a modified transformer architecture optimized for efficient training and inference. Positional embeddings are replaced with Attention with Linear Biases ([ALiBi](https://arxiv.org/abs/2108.12409)).