Update README.md

README.md

@@ -19,10 +19,10 @@ inference: False
 # long-t5-tglobal-xl + BookSum
 
 Summarize long text and get a SparkNotes-esque summary of arbitrary topics!
-- generalizes reasonably well to academic & narrative text.
+- Generalizes reasonably well to academic & narrative text.
 - This is the XL checkpoint, which **from a human-evaluation perspective, produces even better summaries**.
 
-A simple example/use case with the `base` model on ASR is [here](https://longt5-booksum-example.netlify.app/).
+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
 
@@ -32,7 +32,7 @@ Read the paper by Guo et al. here: [LongT5: Efficient Text-To-Text Transformer f
 
 ## How-To in Python
 
-> `LLM.int8()` appears to be compatible with summarization and does not degrade the quality of the outputs; this is a crucial enabler for using this model on standard GPUs. A PR for this is in-progress [here](https://github.com/huggingface/transformers/pull/20341), and this model card will be updated with instructions once done :)
+> 🚧 `LLM.int8()` appears to be compatible with summarization and does not degrade the quality of the outputs; this is a crucial enabler for using this model on standard GPUs. A PR for this is in-progress [here](https://github.com/huggingface/transformers/pull/20341), and this model card will be updated with instructions once done :) 🚧
 
 Install/update transformers `pip install -U transformers`
 
@@ -60,22 +60,22 @@ Pass [other parameters related to beam search textgen](https://huggingface.co/bl
 
 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 paying attention to the surrounding sentences of a claim by the model.
+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). 
 
-- **Initial fine-tuning** only used input text with 12288 tokens input or less and 1024 tokens output or less for memory reasons. Per brief analysis, summaries in the 12288-16384 range in this dataset are in the **small** minority
+- **Initial fine-tuning** only used input text with 12288 tokens input or less and 1024 tokens output or less (_i.e. rows with longer were dropped prior to train_) for memory reasons. Per brief analysis, summaries in the 12288-16384 range in this dataset are in the **small** minority
   - 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
+## Eval results
 
 Official results with the [model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator) will be computed and posted here.
 
-**Please read the note above as due to training methods, it looks better than the test set results will be**. The model achieves the following results on the evaluation set:
+**Please read the note above as due to training methods, validation set performance looks better than the test set results will be**. The model achieves the following results on the evaluation set:
 - eval_loss: 1.2756
 - eval_rouge1: 41.8013
 - eval_rouge2: 12.0895
@@ -128,3 +128,4 @@ The following hyperparameters were used during training:
 - Datasets 2.6.1
 - Tokenizers 0.13.1
 
+---