Update README.md

updated model card with better information and links to references

README.md

@@ -9,45 +9,6 @@ tags:
 model-index:
 - name: sysresearch101/t5-large-finetuned-xsum
   results:
-  # - task:
-  #     type: summarization
-  #     name: Summarization
-  #   dataset:
-  #     name: xsum
-  #     type: xsum
-  #     config: 3.0.0
-  #     split: train
-  #   metrics:
-  #   - type: rouge
-  #     value: <TODO>
-  #     name: ROUGE-1
-  #     verified: true
-  #     verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmE1YjI2OWVjMGRiZWU3MjJhOTViMWIzNWU3MDNlZmFkMmNhZTFiN2RhOTc0ZjkyNzc5ZDg1YWZiZWFhMTEyZiIsInZlcnNpb24iOjF9.ye9137aCRynwSZM0YD2k4_LIcrRU4EyCRjBB8YQ0kUCImJyHNVFPFbbzObfLSM3XQ_tauALczriBCMJ7IGxeDQ
-  #   - type: rouge
-  #     value: <TODO>
-  #     name: ROUGE-2
-  #     verified: true
-  #     verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWYzYzZlZTEwYThhYjJkYzE0MzA1ZjE2NDBiMDNjOTNlZWNjNmMxNDJiMDE4OTJhMjdhNGI3OWRiZjQ1M2RhOSIsInZlcnNpb24iOjF9.-6WOpeYKgyiQSvWIeCfJWWTzI8kt_Q5by31r-ceBF384NMf6APLA94jKpLdE2HDbDgUtuxF9LAHFz9jmhkqKCA
-  #   - type: rouge
-  #     value: <TODO>
-  #     name: ROUGE-L
-  #     verified: true
-  #     verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDAxODg3ZjRlMmUwZTdjYmRmYTZhMzEwYTg4MmU4NmY2MmJlZTE5N2MxYjY4YmE4NGM0NDJkNDRiYjc2OTQwMSIsInZlcnNpb24iOjF9.iWTpIMKC2HGkJMYOQviXBnc-lj4pHLWVyfMXSfbz26s1KUi5gOD97eEaHeBmUW5IMs64dosTVa6xo3T-5_FdDA
-  #   - type: rouge
-  #     value: <TODO>
-  #     name: ROUGE-LSUM
-  #     verified: true
-  #     verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGU2YzFiMDRkOTc2OTFjMGI1MzA3MTgwMzczMjhkMTMxNzkyNDVlZGUzMGM3OTk4ODk0YjQ4MzRjYTVlNmZmNiIsInZlcnNpb24iOjF9.K1duMlA1zQpSiencBbbhpShckuvEb8zspnJG5jf1n65KmNY4Md3VA96ERKixUOIymnTo-gKyS9QEDKblPmR_Ag
-  #   - type: loss
-  #     value: <TODO>
-  #     name: loss
-  #     verified: true
-  #     verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDQ4MDI4MzgyOWUwYzI0YTE3MTE2ODdhYjU3MGE1MTg1NTU4OTM4NzlmYjE1MDY5M2Q2OTVkZjY4MzRlZTYzOCIsInZlcnNpb24iOjF9.5BMk4fs-oVoDNJnPBpDlSkywd3Qogat4_N8_IdS26AObm2i1blwonx4sy8l8RK50pq16bJbplBEEG-3HuTz9DQ
-  #   - type: gen_len
-  #     value: <TODO>
-  #     name: gen_len
-  #     verified: true
-  #     verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTE4ZTAzNmYxMzE2NGYzYTM2MzMxNTNlN2M4YmJlOWI3ZWFkMGRlMTc5NGMzNjBlZjg1MjJhZDdlNDIwZTAwNyIsInZlcnNpb24iOjF9._JTVMjukkupE4_QWOQZZZVwmnXSh-ppo7jlGdk0CUxNIIVTStxQhex09O1H6-Ilk9dtYk1PVCNNg8alZAFHeDQ
   - task:
       type: summarization
       name: Summarization
@@ -61,104 +22,148 @@ model-index:
       value: 26.8921
       name: ROUGE-1
       verified: true
-      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmFkMTFiNmM3YmRkZDk1Y2FhM2EwOTdiYmUwYjBhMGEzZmIyZmIwNWI5OTVmY2U0N2QzYzgxYzM0OTEzMjFjNSIsInZlcnNpb24iOjF9.fOq4zI_BWvTLFJFQOWNk3xEsDIu3aAeboGYPw5TiBqdJJjvdyKmLbfj2WVnNboWbrmp1PuL01iJjTi2Xj6PUAA
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmFkMTFiNmM3YmRkZDk1Y2FhM2EwOTdiYmUwYjBhMGEzZmIyZmIwNWI5OTVmY2U0N2QzYzgxYzM0OTEzMjFjNSIsInZlcnNpb24iOjF9.fOq4zI_BWvTLFJFQOWNk3xEsDIu3aAeboGYPw5TiBqdJJjvdyKmLbfj2WVnNboWbrmp1PuL01iJjTi2Xj6PUAA
     - type: rouge
       value: 6.9411
       name: ROUGE-2
       verified: true
-      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTBlZmI3NjQ3M2JiYzI4MTg3YmJkMjg0ZmE5MDUwNzljNTYyM2M0NzA3YTNiNTA2Nzk4MDhhYWZjZjgyMmE1MCIsInZlcnNpb24iOjF9.rH0DY2hMz2rXaK29vkt7xah-3G95rY4MOS2oVKjXmw4TijB-ZVytfLJAlBmyqA8HYAythRCywmLSjjCDWc66Cg
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTBlZmI3NjQ3M2JiYzI4MTg3YmJkMjg0ZmE5MDUwNzljNTYyM2M0NzA3YTNiNTA2Nzk4MDhhYWZjZjgyMmE1MCIsInZlcnNpb24iOjF9.rH0DY2hMz2rXaK29vkt7xah-3G95rY4MOS2oVKjXmw4TijB-ZVytfLJAlBmyqA8HYAythRCywmLSjjCDWc66Cg
     - type: rouge
       value: 21.2832
       name: ROUGE-L
       verified: true
-      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODAwZDYzNTc0NjZhNzNiMDE2ZDY2NjNjNmViNTc0NDVjNTZkYjljODhmYmNiMWFhY2NkZjU5MzQ0NmM0OTcyMSIsInZlcnNpb24iOjF9.5duHtdjZ8dwtbp1HKyMR4mVK9IIlEZvuWGjQMErpE7VNyKPhMOT6Avh_vXFQz6q_jBzqpZGGREho1mt50yBsDw
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODAwZDYzNTc0NjZhNzNiMDE2ZDY2NjNjNmViNTc0NDVjNTZkYjljODhmYmNiMWFhY2NkZjU5MzQ0NmM0OTcyMSIsInZlcnNpb24iOjF9.5duHtdjZ8dwtbp1HKyMR4mVK9IIlEZvuWGjQMErpE7VNyKPhMOT6Avh_vXFQz6q_jBzqpZGGREho1mt50yBsDw
     - type: rouge
       value: 21.284
       name: ROUGE-LSUM
       verified: true
-      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGQ2NmNhZTZmZDFkNTcyYjQ4MjhhYWJhODY1ZGRjODY2ZTE5MmRmZDRlYTk4NWE4YWM1OWY2M2NjOWQ3YzU0OCIsInZlcnNpb24iOjF9.SJ8xTcAVWrRDmJmQoxE1ADIcdGA4tr3V04Lv0ipMJiUksCdNC7FO8jYbjG9XmiqbDnnr5h4XoK4JB4-GsA-gDA
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGQ2NmNhZTZmZDFkNTcyYjQ4MjhhYWJhODY1ZGRjODY2ZTE5MmRmZDRlYTk4NWE4YWM1OWY2M2NjOWQ3YzU0OCIsInZlcnNpb24iOjF9.SJ8xTcAVWrRDmJmQoxE1ADIcdGA4tr3V04Lv0ipMJiUksCdNC7FO8jYbjG9XmiqbDnnr5h4XoK4JB4-GsA-gDA
     - type: loss
       value: 2.5411810874938965
       name: loss
       verified: true
-      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGViNTVlNGI0Njk4NmZmZjExNDBkNTQ4N2FhMzRkZjRjNDNlYzFhZDIyMjJhMmFiM2ZhMTQzYTM4YzNkNWVlNyIsInZlcnNpb24iOjF9.p9n2Kf48k9F9Bkk9j7UKRayvVmOr7_LV80T0ti4lUWFtTsZ91Re841xnEAcKSYgQ9-Bni56ldq9js3kunspJCw
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGViNTVlNGI0Njk4NmZmZjExNDBkNTQ4N2FhMzRkZjRjNDNlYzFhZDIyMjJhMmFiM2ZhMTQzYTM4YzNkNWVlNyIsInZlcnNpb24iOjF9.p9n2Kf48k9F9Bkk9j7UKRayvVmOr7_LV80T0ti4lUWFtTsZ91Re841xnEAcKSYgQ9-Bni56ldq9js3kunspJCw
     - type: gen_len
       value: 18.7755
       name: gen_len
       verified: true
-      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmQ1ZWUxNmFjNmU0OGI4MDQyZDNjMWQwZGViNDhlMzE1OGE3YmYwYzZjYmM1NWEwMjk2MDFiMjQ4ZThhMjg5YyIsInZlcnNpb24iOjF9.aNp-NFzBSm84GnXuDtYuHaOsSk7zw8kjCphowYFciwt-aDnhwwurYIr59kMT8JNFMnRInsDi8tvYdapareV3DA
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmQ1ZWUxNmFjNmU0OGI4MDQyZDNjMWQwZGViNDhlMzE1OGE3YmYwYzZjYmM1NWEwMjk2MDFiMjQ4ZThhMjg5YyIsInZlcnNpb24iOjF9.aNp-NFzBSm84GnXuDtYuHaOsSk7zw8kjCphowYFciwt-aDnhwwurYIr59kMT8JNFMnRInsDi8tvYdapareV3DA
+datasets:
+- EdinburghNLP/xsum
+base_model:
+- google-t5/t5-large
 ---
 
-# T5-large Summarization Model Trained on the XSUM Dataset
+# T5-Large Fine-tuned on XSum
 
-Finetuned T5 Large summarization model. 
+**Task:** Abstractive Summarization (English)  
+**Base Model:** google-t5/t5-large  
+**License:** MIT
 
-## Finetuning Corpus
+## Overview
 
-`t5-large-finetuned-xsum` model is based on `t5-large model` by [huggingface](https://huggingface.co/t5-large), finetuned using [XSUM](https://huggingface.co/datasets/xsum) datasets.
+This model is a T5-Large checkpoint fine-tuned exclusively on the [XSum](https://huggingface.co/datasets/EdinburghNLP/xsum) dataset. It specializes in generating concise, single-sentence summaries in the style of BBC article abstracts.
 
-## Load Finetuned Model
+## Performance ~ On XSum test set
+
+| Metric | Score |
+|--------|-------|
+| ROUGE-1 | 26.89 |
+| ROUGE-2 | 6.94  |
+| ROUGE-L | 21.28 |
+| Loss | 2.54 |
+| Avg. Length | 18.77 tokens |
+
+
+## Usage
+
+### Quick Start
 
 ```python
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, DataCollatorForSeq2Seq, Seq2SeqTrainingArguments, Seq2SeqTrainer
+from transformers import pipeline
+
+summarizer = pipeline("summarization", model="sysresearch101/t5-large-finetuned-xsum")
+
+article = "Your article text here..."
+summary = summarizer(article, max_length=80, min_length=20, do_sample=False)
+print(summary[0]['summary_text'])
+```
+
+### Advanced Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
 tokenizer = AutoTokenizer.from_pretrained("sysresearch101/t5-large-finetuned-xsum")
-model = model = AutoModelForSeq2SeqLM.from_pretrained("sysresearch101/t5-large-finetuned-xsum")
+model = AutoModelForSeq2SeqLM.from_pretrained("sysresearch101/t5-large-finetuned-xsum")
+
+inputs = tokenizer("summarize: " + article, return_tensors="pt", max_length=512, truncation=True)
+outputs = model.generate(
+    **inputs,
+    max_length=80,
+    min_length=20,
+    num_beams=4,
+    no_repeat_ngram_size=2,
+    length_penalty=1.0,
+    repetition_penalty=2.5,
+    use_cache=True,
+    early_stopping=True
+    do_sample = True,
+    temperature = 0.8,
+    top_k = 50,
+    top_p = 0.95
+)
+
+summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
+```
+
+## Training Data
+
+- [XSum](https://huggingface.co/datasets/EdinburghNLP/xsum): BBC articles paired with professionally written single-sentence summaries
+
 
-ARTICLE_TO_SUMMARIZE = "..."
+## Intended Use
 
-# generate summary
+- **Primary:** Summarization
+- **Secondary:** Research on extreme summarization, single-sentence summary generation, Educational demonstrations, comparative studies with multi-sentence models
+- **Not recommended:** Multi-sentence summarization tasks, production use without validation
 
-input_ids = tokenizer.encode(ARTICLE_TO_SUMMARIZE, return_tensors='pt')
-summary_ids = model.generate(input_ids,
-            min_length=20,
-            max_length=80,
-            num_beams=10,
-            repetition_penalty=2.5,
-            length_penalty=1.0,
-            early_stopping=True,
-            no_repeat_ngram_size=2,
-            use_cache=True,
-            do_sample = True,
-            temperature = 0.8,
-            top_k = 50,
-            top_p = 0.95)
+## Limitations
+- Trained only on news domain; may not generalize to other text types
+- Generates very short summaries (average ~19 tokens)
+- May oversimplify complex topics due to single-sentence constraint
 
-summary_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
-print(summary_text)
 
-Output: <TODO>
+## Citation
 
+```bibtex
+@misc{stept2023_t5_large_xsum,
+  author = {Shlomo Stept (sysresearch101)},
+  title = {T5-Large Fine-tuned on XSum for Abstractive Summarization},
+  year = {2023},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/sysresearch101/t5-large-finetuned-xsum}
+}
 ```
 
-### How to use via a pipeline
+## Papers Using This Model
 
-Here is how to use this model with the [pipeline API](https://huggingface.co/transformers/main_classes/pipelines.html):
+* [Tam et al. (2023). *Evaluating the Factual Consistency of Large Language Models Through Summarization (FIB).* Findings of ACL 2023.](https://arxiv.org/pdf/2211.08412)
+* [Liu et al. (2024). *LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores.* Findings of ACL 2024.](https://aclanthology.org/2024.findings-acl.753.pdf)
+* [Zhu et al. (2024). *MTAS: A Reference-Free Approach for Evaluating Abstractive Summarization Systems.* Proceedings of the ACM on SE (FSE 2024).](https://doi.org/10.1145/3660820)
 
 
-```python
-from transformers import pipeline
+## Contact
 
-summarizer = pipeline("summarization", model="sysresearch101/t5-large-finetuned-xsum")
+Created by [Shlomo Stept](https://shlomostept.com) ([ORCID: 0009-0009-3185-589X](https://orcid.org/0009-0009-3185-589X))
+DARMIS AI
 
-ARTICLE = """ New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York.
-A year later, she got married again in Westchester County, but to a different man and without divorcing her first husband.
-Only 18 days after that marriage, she got hitched yet again. Then, Barrientos declared "I do" five more times, sometimes only within two weeks of each other.
-In 2010, she married once more, this time in the Bronx. In an application for a marriage license, she stated it was her "first and only" marriage.
-Barrientos, now 39, is facing two criminal counts of "offering a false instrument for filing in the first degree," referring to her false statements on the
-2010 marriage license application, according to court documents.
-Prosecutors said the marriages were part of an immigration scam.
-On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to her attorney, Christopher Wright, who declined to comment further.
-After leaving court, Barrientos was arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New York subway through an emergency exit, said Detective
-Annette Markowski, a police spokeswoman. In total, Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002.
-All occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be married to four men, and at one time, she was married to eight men at once, prosecutors say.
-Prosecutors said the immigration scam involved some of her husbands, who filed for permanent residence status shortly after the marriages.
-Any divorces happened only after such filings were approved. It was unclear whether any of the men will be prosecuted.
-The case was referred to the Bronx District Attorney\'s Office by Immigration and Customs Enforcement and the Department of Homeland Security\'s
-Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt, Turkey, Georgia, Pakistan and Mali.
-Her eighth husband, Rashid Rajput, was deported in 2006 to his native Pakistan after an investigation by the Joint Terrorism Task Force.
-If convicted, Barrientos faces up to four years in prison.  Her next court appearance is scheduled for May 18.
-"""
-print(summarizer(ARTICLE, max_length=130, min_length=30, do_sample=False))
->>> [{'summary_text': 'Liana Barrientos, 39, is charged with two counts of "offering a false instrument for filing in the first degree" In total, she has been married 10 times, with nine of her marriages occurring between 1999 and 2002. She is believed to still be married to four men.'}]
-```
+
+- Website: [shlomostept.com](https://shlomostept.com)  
+- LinkedIn: [linkedin.com/in/shlomo-stept](https://linkedin.com/in/shlomo-stept)