haining commited on
Commit
719971d
1 Parent(s): 9657b29

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -10
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
- ```{python3}
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
- More information needed
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