update readme intro

README.md

@@ -11,9 +11,11 @@ commercial: false
 
 ## Model Description
 
-OPT-IML models are instruction-tuned versions of OPT. They are fine-tuned on 2000 NLP tasks from 8 existing public benchmarks. 
-OPT-IML models are significantly better than OPT model and demonstrate different generalization abilities on four different 
-evaluation benchmarks with diverse tasks and input formats – PromptSource, FLAN, Super-NaturalInstructions, and UnifiedSKG.
+[OPT-IML (OPT + Instruction Meta-Learning)](https://arxiv.org/abs/2212.12017) is a set of instruction-tuned versions of OPT, on a collection of ~2000 NLP tasks gathered from 8 NLP benchmarks, called OPT-IML Bench.
+
+We provide two model versions: 
+* OPT-IML trained on 1500 tasks with several tasks held-out for purposes of downstream evaluation, and 
+* OPT-IML-Max trained on all ~2000 tasks
 
 ### How to use
 For large OPT models, such as this one, it is not recommend to make use of the `text-generation` pipeline because