Update README.md
Browse files
README.md
CHANGED
@@ -72,18 +72,18 @@ inference:
|
|
72 |
|
73 |
>_this is the "latest" version of the model that has been trained the longest, currently at 70k steps_
|
74 |
|
75 |
-
-
|
76 |
-
-
|
77 |
-
|
78 |
-
-
|
79 |
-
|
80 |
- starting checkpoint was `google/bigbird-pegasus-large-bigpatent`
|
81 |
|
82 |
---
|
83 |
|
84 |
# example usage
|
85 |
|
86 |
-
>An extended example, including a demo of batch summarization, is [here](https://colab.research.google.com/gist/pszemraj/2c8c0aecbcd4af6e9cbb51e195be10e2/bigbird-pegasus-large-booksum-20k-example.ipynb).
|
87 |
|
88 |
|
89 |
- create the summarizer object:
|
|
|
72 |
|
73 |
>_this is the "latest" version of the model that has been trained the longest, currently at 70k steps_
|
74 |
|
75 |
+
- **GOAL:** A summarization model that 1) summarizes the source content accurately 2) _more important IMO_ produces summaries that are easy to read and understand (* cough * unlike arXiv * cough *)
|
76 |
+
- This model attempts to help with that by using the [booksum](https://arxiv.org/abs/2105.08209) dataset to provide **explanatory summarization**
|
77 |
+
- Explanatory Summary - A summary that both consolidates information and also explains why said consolidated information is important.
|
78 |
+
- This model was trained for seven epochs total (approx 70,000 steps) and is closer to finished.
|
79 |
+
- Will continue to improve (slowly, now that it has been trained for a long time) based on any result findings/feedback.
|
80 |
- starting checkpoint was `google/bigbird-pegasus-large-bigpatent`
|
81 |
|
82 |
---
|
83 |
|
84 |
# example usage
|
85 |
|
86 |
+
> An extended example, including a demo of batch summarization, is [here](https://colab.research.google.com/gist/pszemraj/2c8c0aecbcd4af6e9cbb51e195be10e2/bigbird-pegasus-large-booksum-20k-example.ipynb).
|
87 |
|
88 |
|
89 |
- create the summarizer object:
|