Update README.md

README.md

@@ -11,9 +11,10 @@ pipeline_tag: text2text-generation
 
 # BEE-spoke-data/tFINE-900m-e16-d32-flan
 
-Finetune on the pszemraj/flan-subsets-deduped dataset, subset `flan-v2` for 1 epoch.
+This is a basic text-to-text "instruct" model, similar to Google's original [flan-t5](https://huggingface.co/collections/google/flan-t5-release-65005c39e3201fff885e22fb) model series (but not trained for as long).  
 
-It achieves the following results on the evaluation set:
+
+Fine-tuned from [the base model](https://hf.co/pszemraj/tFINE-900m-e16-d32-1024ctx) on the `pszemraj/flan-subsets-deduped` dataset, subset `flan-v2` for 1 epoch. It achieves the following results on the evaluation set:
 - Loss: 1.4134
 - Rouge1: 62.9142
 - Rouge2: 22.5279