pszemraj
/

long-t5-tglobal-xl-16384-book-summary

@@ -24,7 +24,7 @@ Summarize long text and get a SparkNotes-esque summary of arbitrary topics!
 A simple example/use case with [the base model](https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary) on ASR is [here](https://longt5-booksum-example.netlify.app/).
-## Model description
 A fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the `kmfoda/booksum` dataset.
@@ -56,14 +56,16 @@ print(result[0]["summary_text"])
 Pass [other parameters related to beam search textgen](https://huggingface.co/blog/how-to-generate) when calling `summarizer` to get even higher quality results.
-## Intended uses & limitations
 While this model seems to improve upon factual consistency, **do not take summaries to be foolproof and check things that seem odd**.
 Specifically: negation statements (i.e. model says: _This thing does not have [ATTRIBUTE]_ where instead it should have said _This thing has a lot of [ATTRIBUTE]_).
 - I'm sure someone will write a paper on this eventually (if there isn't one already), but you can usually fact-check this by comparing a specific claim to what the surrounding sentences imply.
-## Training and evaluation data
 `kmfoda/booksum` dataset on HuggingFace - read [the original paper here](https://arxiv.org/abs/2105.08209).
@@ -71,7 +73,7 @@ Specifically: negation statements (i.e. model says: _This thing does not have [A
   - In addition, this initial training combined the training and validation sets and trained on these in aggregate to increase the functional dataset size. **Therefore, take the validation set results with a grain of salt; primary metrics should be (always) the test set.**
 - **final phases of fine-tuning** used the standard conventions of 16384 input/1024 output keeping everything (truncating longer sequences). This did not appear to change the loss/performance much.
-## Eval results
 Official results with the [model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator) will be computed and posted here.

 A simple example/use case with [the base model](https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary) on ASR is [here](https://longt5-booksum-example.netlify.app/).
+## Description
 A fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the `kmfoda/booksum` dataset.
 Pass [other parameters related to beam search textgen](https://huggingface.co/blog/how-to-generate) when calling `summarizer` to get even higher quality results.
+## About
+### Intended uses & limitations
 While this model seems to improve upon factual consistency, **do not take summaries to be foolproof and check things that seem odd**.
 Specifically: negation statements (i.e. model says: _This thing does not have [ATTRIBUTE]_ where instead it should have said _This thing has a lot of [ATTRIBUTE]_).
 - I'm sure someone will write a paper on this eventually (if there isn't one already), but you can usually fact-check this by comparing a specific claim to what the surrounding sentences imply.
+### Training and evaluation data
 `kmfoda/booksum` dataset on HuggingFace - read [the original paper here](https://arxiv.org/abs/2105.08209).
   - In addition, this initial training combined the training and validation sets and trained on these in aggregate to increase the functional dataset size. **Therefore, take the validation set results with a grain of salt; primary metrics should be (always) the test set.**
 - **final phases of fine-tuning** used the standard conventions of 16384 input/1024 output keeping everything (truncating longer sequences). This did not appear to change the loss/performance much.
+### Eval results
 Official results with the [model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator) will be computed and posted here.