Update README.md

README.md

@@ -18,11 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # long-t5-tglobal-base-synthsumm_direct
 
-Fine-tuned on a synthetic dataset of curated long-context text and `GPT-3.5-turbo-1106` summaries spanning multiple domains, including "random" long-context examples from redpajama, the pile, etc.
+Fine-tuned on a synthetic dataset of curated long-context text and `GPT-3.5-turbo-1106` summaries spanning multiple domains + "random" long-context examples from pretraining datasets
+
 
 - Note: this model has **not** been fine-tuned on any other summarization datasets, just the `synthsumm` data
 
-Try it out in the [gradio demo](https://huggingface.co/spaces/pszemraj/document-summarization)
+Try it in [gradio demo](https://huggingface.co/spaces/pszemraj/document-summarization) | [.md with example outputs](https://huggingface.co/pszemraj/long-t5-tglobal-base-synthsumm_direct/blob/main/evals-outputs/GAUNTLET.md) (gauntlet)
 
 ## Model description