peterszemraj@gmail.com

README.md

@@ -68,6 +68,7 @@ inference:
 # Longformer Encoder-Decoder (LED) fine-tuned on Booksum
 
 - an 'upgraded' version of [`pszemraj/led-base-16384-finetuned-booksum`](https://huggingface.co/pszemraj/led-base-16384-finetuned-booksum), it was trained for an additional epoch with a max summary length of 1024 tokens (original was trained with 512) as a small portion of the summaries are between 512-1024 tokens long.
+  - all the parameters for generation on the API are the same for easy comparison between versions.
 - works well on lots of text, can hand 16384 tokens/batch.
   
 ## Other Checkpoints on Booksum
@@ -86,7 +87,7 @@ inference:
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 from transformers import pipeline
 
-hf_name = 'pszemraj/led-base-16384-finetuned-booksum'
+hf_name = 'pszemraj/led-base-book-summary'
 
 _model = AutoModelForSeq2SeqLM.from_pretrained(
                 hf_name,
@@ -132,6 +133,5 @@ result = summarizer(
 
 **no results for this version yet**
 
-```
 
 ---