Update README.md

README.md

@@ -18,6 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # long-t5-tglobal-base-synthsumm_direct
 
+
+This was fine-tuned on a synthetic dataset of curated long-context text and `GPT-3.5-turbo-1106` summaries spanning several domains, including "random" long-context examples from redpajama, the pile, etc. Try it in the [gradio demo](https://huggingface.co/spaces/pszemraj/document-summarization)
+
+## Model description
+
 This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.4378
@@ -27,17 +32,6 @@ It achieves the following results on the evaluation set:
 - Rougelsum: 43.0271
 - Gen Len: 84.5231
 
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
 
 ## Training procedure