Update README.md

README.md

@@ -12,13 +12,13 @@ library_name: transformers
 # tFINE-850m-24x24-1024ctx
 
 
-Pretrained T5 model with nanoT5:
+Pretrained T5 model with [nanoT5](https://github.com/pszemraj/nanoT5/tree/fineweb-edu-test):
 
 - ~850m parameters, 24 layers in encoder, 24 layers in decoder
 - sentencepiece tokenizer with 48k vocab & byte-pair fallback
-  - handles whitespaces etc correctly (unlike standard T5 tokenizer)
+  - handles whitespaces etc correctly (_unlike original T5 tokenizer_)
 - 1024 ctx during pretrain
-- `relative_attention_num_buckets` increased to 48 from standard 32 for context length upscaling
+- `relative_attention_num_buckets` increased to 48 from 32 for context length upscaling
 
 ## Experiment logs