Update README.md

README.md

@@ -17,7 +17,7 @@ widget:
   example_title: "pumpen"
 inference:
   parameters:
-    max_length: 128
+    max_length: 64
     no_repeat_ngram_size: 2
     encoder_no_repeat_ngram_size: 3
     repetition_penalty: 2.4
@@ -31,7 +31,7 @@ inference:
 
 - the entirety of askscience sub-section of eli5 dataset for one epoch.
 - compare to bart on eli5 [here](https://huggingface.co/yjernite/bart_eli5)
-- note that for the inference API here, the model is restricted to outputting 128 tokens - using the model in python with the transformers library, you can get longer outputs.
+- note that for the inference API here, the model is restricted to outputting 64 tokens - using the model in python with the transformers library, you can get longer outputs.
 
 ## training