Update README.md

README.md

@@ -9,10 +9,11 @@ language:
 license: mit
 metrics: 
   - sacrebleu
-  - BERT_score
-  - ROUGE
-  - METEOR
-  - SARI
+  - bert_score
+  - rouge
+  - meteor
+  - sari
+  - ari
   - "Automated Readability Index"
 tags: 
   - "text2text generation"
@@ -39,7 +40,7 @@ widget:
 Scientific Abstract Simplification-baseline *translates* hard-to-read scientific abstracts😵 into more accessible language😇. We hope it can make scientific knowledge accessible for everyone🤗.
 
 Try it now with the Hosted inference API on the right.
-You can choose an existing example or paste in any (perhaps full-of-jargon) abstract. Remember to prepend the instruction before the abstract ("summarize, simplify, and contextualize: "; notice, there is a whitespace after the colon). Local use refers to Section [Usage](/Usage).
+You can choose an existing example or paste in any (perhaps full-of-jargon) abstract. Remember to prepend the instruction to the abstract ("summarize, simplify, and contextualize: "; notice, there is a whitespace after the colon). Local use refers to Section [Usage](/Usage).
 
 
 # Model Details
@@ -63,9 +64,9 @@ As an ongoing effort, we are working on re-contextualizating abstracts for bette
 
 - **Model type:** Language model
 - **Developed by:** 
-  - Mentors: Jason Clark and Hannah McKelvey
+  - PIs: Jason Clark and Hannah McKelvey
   - Fellows: Haining Wang and Deanna Zarrillo
-  - [LEADING](https://cci.drexel.edu/mrc/leading/) Montana State University Library ("TL;DR it": Automating Article Synopses for Search Engine Optimization and Citizen Science).
+  - [LEADING](https://cci.drexel.edu/mrc/leading/) Montana State University Library, Project "TL;DR it": Automating Article Synopses for Search Engine Optimization and Citizen Science
 - **Language(s) (NLP):** English
 - **License:** MIT
 - **Parent Model:** [FLAN-T5-large](https://huggingface.co/google/flan-t5-large)
@@ -74,7 +75,7 @@ As an ongoing effort, we are working on re-contextualizating abstracts for bette
 
 # Usage
 
-Use the code below to get started with the model.
+Use the code below to get started with the model. Remember to prepend the `INSTRUCTION` for best performance.
 
 ```python
 import torch
@@ -94,7 +95,7 @@ encoding = tokenizer(INSTRUCTION + input_text,
                      return_tensors='pt')
 decoded_ids = model.generate(input_ids=encoding['input_ids'],
                              attention_mask=encoding['attention_mask'], 
-                             max_new_tokens=512, 
+                             max_length=512, 
                              top_p=.9, 
                              do_sample=True)
 
@@ -134,14 +135,14 @@ The model is evaluated on the SAS test set using the following metrics.
   - [The Automated Readability Index (ARI)](https://www.readabilityformulas.com/automated-readability-index.php): ARI 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.
 
 
-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.
+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.
 
 
 ## Results 
 
 | Metrics        | SAS-baseline      |
 |----------------|-------------------|
-| sacreBLEU↑     | 20.97             |
+| SacreBLEU↑     | 20.97             |
 | BERT Score F1↑ | 0.89              |
 | ROUGLE-1↑      | 0.48              |
 | ROUGLE-2↑      | 0.23              |