Update README.md
Browse files
README.md
CHANGED
@@ -53,10 +53,11 @@ As an ongoing effort, we are still working on boosting the model's performance o
|
|
53 |
|
54 |
<!-- We hypothesize the last mile of scientific understanding is cognitive. -->
|
55 |
|
|
|
56 |
- **Developed by:** [LEADING](https://cci.drexel.edu/mrc/leading/) Montana State University Library ("TL;DR it": Automating Article Synopses for Search Engine Optimization and Citizen Science).
|
57 |
- Mentors: Jason Clark and Hannah McKelvey
|
58 |
- Fellows: Haining Wang and Deanna Zarrillo.
|
59 |
-
- **Language:** English
|
60 |
- **License:** MIT
|
61 |
- **Parent Model:** [FLAN-T5-large](https://huggingface.co/google/flan-t5-large)
|
62 |
|
@@ -66,9 +67,7 @@ As an ongoing effort, we are still working on boosting the model's performance o
|
|
66 |
|
67 |
Use the code below to get started with the model.
|
68 |
|
69 |
-
```
|
70 |
-
# assume pytorch and huggingface are ready to use
|
71 |
-
|
72 |
import torch
|
73 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
74 |
INSTRUCTION = "summarize, simplify, and contextualize: "
|
@@ -119,16 +118,12 @@ The model is evaluated on the SAS test set using the following metrics.
|
|
119 |
- Automated Readability Index (ARI): [The Automated Readability Index (ARI)](https://www.readabilityformulas.com/automated-readability-index.php) is a readability test designed to assess the understandability of a text. Like other popular readability formulas, the ARI formula outputs a number which approximates the grade level needed to comprehend the text. For example, if the ARI outputs the number 10, this equates to a high school student, ages 15-16 years old; a number 3 means students in 3rd grade (ages 8-9 yrs. old) should be able to comprehend the text.
|
120 |
|
121 |
|
122 |
-
Implementations of sacreBLEU, BERT Score, ROUGLE, METEOR, and SARI are from Huggingface [`evaluate`](https://pypi.org/project/evaluate/) v.0.3.0. ARI is from `py-readability-metrics` v.1.4.5.
|
123 |
|
124 |
|
125 |
## Results
|
126 |
|
127 |
-
|
128 |
-
|
129 |
-
<!-- # Model Examination -->
|
130 |
-
|
131 |
-
<!-- More information needed -->
|
132 |
|
133 |
|
134 |
|
|
|
53 |
|
54 |
<!-- We hypothesize the last mile of scientific understanding is cognitive. -->
|
55 |
|
56 |
+
- **Model type:** Language model
|
57 |
- **Developed by:** [LEADING](https://cci.drexel.edu/mrc/leading/) Montana State University Library ("TL;DR it": Automating Article Synopses for Search Engine Optimization and Citizen Science).
|
58 |
- Mentors: Jason Clark and Hannah McKelvey
|
59 |
- Fellows: Haining Wang and Deanna Zarrillo.
|
60 |
+
- **Language(s) (NLP):** English
|
61 |
- **License:** MIT
|
62 |
- **Parent Model:** [FLAN-T5-large](https://huggingface.co/google/flan-t5-large)
|
63 |
|
|
|
67 |
|
68 |
Use the code below to get started with the model.
|
69 |
|
70 |
+
```python
|
|
|
|
|
71 |
import torch
|
72 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
73 |
INSTRUCTION = "summarize, simplify, and contextualize: "
|
|
|
118 |
- Automated Readability Index (ARI): [The Automated Readability Index (ARI)](https://www.readabilityformulas.com/automated-readability-index.php) is a readability test designed to assess the understandability of a text. Like other popular readability formulas, the ARI formula outputs a number which approximates the grade level needed to comprehend the text. For example, if the ARI outputs the number 10, this equates to a high school student, ages 15-16 years old; a number 3 means students in 3rd grade (ages 8-9 yrs. old) should be able to comprehend the text.
|
119 |
|
120 |
|
121 |
+
Implementations of sacreBLEU, BERT Score, ROUGLE, METEOR, and SARI are from Huggingface [`evaluate`](https://pypi.org/project/evaluate/) v.0.3.0. ARI is from [`py-readability-metrics`](https://pypi.org/project/py-readability-metrics/) v.1.4.5.
|
122 |
|
123 |
|
124 |
## Results
|
125 |
|
126 |
+
TODO.
|
|
|
|
|
|
|
|
|
127 |
|
128 |
|
129 |
|