%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Long T5 Tglobal Large Pubmed 3k Booksum 16384 WIP
L
Long T5 Tglobal Large Pubmed 3k Booksum 16384 WIP
Developed by pszemraj
A large-scale summarization model based on the Long-T5 architecture, specifically optimized for long-document summarization tasks, supporting a context length of 16,384 tokens.
Downloads 65
Release Time : 6/25/2022
Model Overview
This model is an improved long-text summarization generation model based on the T5 architecture, specifically optimized for book summarization and long-document summarization tasks. It was trained on the PubMed and BookSum datasets and can process input texts up to 16,384 tokens in length.
Model Features
Long Text Processing Capability
Supports ultra-long context processing of 16,384 tokens, suitable for book and long-document summarization
Multi-domain Adaptability
Trained on medical literature (PubMed) and book summarization (BookSum) datasets, applicable to various professional fields
High-performance Summarization
Achieves a ROUGE-1 score of 35.9969 on the BookSum test set, demonstrating excellent performance
Model Capabilities
Long text summarization generation
Book content summarization
Professional literature summarization
Multi-paragraph text condensation
Use Cases
Academic Research
Medical Literature Summarization
Automatically generates concise summaries of PubMed medical research papers
Maintains high information retention in professional fields
Publishing Industry
Book Content Summarization
Generates content summaries and chapter outlines for long books
Performs excellently on the BookSum dataset
Business Analysis
Long Report Condensation
Condenses business reports, market analyses, and other long documents into executive summaries
Retains key information and data points
license: apache-2.0 tags:
- summarization
- summary
- booksum
- long-document
- long-form datasets:
- kmfoda/booksum metrics:
- rouge inference: false model-index:
- name: pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP
results:
- task:
type: summarization
name: Summarization
dataset:
name: kmfoda/booksum
type: kmfoda/booksum
config: kmfoda--booksum
split: test
metrics:
- type: rouge value: 35.9969 name: ROUGE-1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzg5ZmI5Y2YzMzdlMjI4N2U1MTE3MDQxNWQyNzkwODFmYzEwNjMwZTU5MTEzOWEwYzdhNWZkMzlkMWI5ZWU3YSIsInZlcnNpb24iOjF9.J56x5lJEDRQzbt3QkmVZn4q5miEpTyCE1rZIiN3xzCDdBL0R5XMhqyqPgbJlJgFcclHHE8mrfjfsj1crV2ygCQ
- type: rouge value: 5.9272 name: ROUGE-2 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzg1MzY4OGEwOTRmMGMyOWIyMzkxYzI1YzFiZWZjODUyMDJiMGY0NmMwMzQxNjA1MzhmMDljYzI2MTdhMjljZiIsInZlcnNpb24iOjF9.0rxUBWkRVaPBoUZDFTrjk05AjwJTafxq8AFDGMkDjFx0BfN6rlxENnibj1NP38abysEqlER_gnBz1wjsb4c2Bw
- type: rouge value: 16.0136 name: ROUGE-L verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjMwN2YwYzNlZjczZGJhOGExNWJkZTc1OWJiY2YyZmNmZmQ5YTA4ZDA1NmI2ZDM4MmZiN2M3YzFiNDQ1OTk2NiIsInZlcnNpb24iOjF9.oCpGSJwJ0mC_I9Wxw1GaJjus3cjvH2CyW3Lagy8c6GJKd6XPwBcc1CenDp_K3cItAft927iegQbFoYCg8lYgCA
- type: rouge value: 32.941 name: ROUGE-LSUM verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmJjZmFlZTUyNjYxMGUxNGNjNzk0MDk5NjYxNGY0NmExMjZhMDViZTcyNmMwZjYwMWQwMmM5ODljZmNjMTgxZiIsInZlcnNpb24iOjF9.uYsoPZNKW3-sUBrcPzAJliY7mCCZA-jGxUbk4aDH-VqLSpEo2HPGbayucDrcUHwrSv7sCihOdHDP2GtxGcPKDg
- type: loss value: 2.9339466094970703 name: loss verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDU3NzY4MzJkY2ZmNDc4MDQxZjcyMzE5NTAyMTNlOTczNjBiYjhmODNkMTMwYWZhMjQxM2YzZjhiNGEzODlmZSIsInZlcnNpb24iOjF9.ubsp9ODlTUI6XD9pE310OHswKKd2qCEWacgzXT4P0exypXfqTeKaL9CRCMT9GZf_f8Yg1Zl6FNvSgJoa1T8hCw
- type: gen_len value: 283.7198 name: gen_len verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDFlZGZjNWYwYzk3M2E1OGViZWQ1YWY3MDU3MTA0NjI3OWRhZTljMjQ1MjVhYjM3ZGQ2NjFlMzgxZTIzMmViZSIsInZlcnNpb24iOjF9.np0apB8dlENyCSnLtDRYAuo7R5mu7wELjvjeUQPhhT30yUOGCJ1MOt-uE7l0kPqf6v3JYD3KLYB6o-NwnfCHBQ
- task:
type: summarization
name: Summarization
dataset:
name: samsum
type: samsum
config: samsum
split: test
metrics:
- type: rouge value: 26.2412 name: ROUGE-1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjFlYWRiYzA3NzkxNWQ0NTY3MmY3NGNmYTJhNjBiNDVlZWNjMTliMzQ0YTZiODM2NGNkNWFjMDQ0Y2U1OTIxYiIsInZlcnNpb24iOjF9.VXuruKzSmTj-rc5znqWimqUxFHMq2yi3w958l6rpnEwWzZLki4PaLkmnd000i3WWI1qI8SU-oS5QZ_3BACs4BA
- type: rouge value: 5.9791 name: ROUGE-2 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjgyOWNjNmNjMDQ0ZmMwZmQ5ZTAxMTUyNmJhZGQ1NTBkZDI4NzQ3MTYyZDhlNzY5ZGRjZjQ2NWViZmU1MGJhNiIsInZlcnNpb24iOjF9.b0n4KjAbV8K-pcifki4ZtBcyaSTb1zt5NulwQ4eq2ryB1eOktoOvm9BHXH29YcY0vkegoai996azAyhQa64oCw
- type: rouge value: 18.7467 name: ROUGE-L verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTU1NmFmZTUxNmFhYTc3OTU3MTk1NTVjOWI2NzAyMTJhZTQ0ZDI0NjhjNzFkZjk3NmNlOTNhMzNlNGM1ZTBlZCIsInZlcnNpb24iOjF9.JDwUXyolkzkUjW52heUuBvfmniToRUwJamq3HXUBPt4eM4RwJCkt9gEqEFwI8enZsHSZV-OrkeYNBBPIGbkHAQ
- type: rouge value: 22.5566 name: ROUGE-LSUM verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTFjMWU1YmY5ZDM5OTM0YTliNWE5ZjMyMDk2YTI3MGUyNGFhNGJjZDJhMzA2OTZlODVhODkxYTViZGVjZjk0NiIsInZlcnNpb24iOjF9.UjXKQOz6_4WUM_keDjpZ2JqLk2I_6Qz5sDPn40gTGoShqs-1MdlN2ZD556lg4sASvFhPOgehlocXtkhoVNeDAw
- type: loss value: 2.877626895904541 name: loss verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTE1MGE5N2E4MjM4ZjU1NzdkNzVjMzQ2ZTMwZGExZmY2M2NkZmExOGRjN2M0MzNmY2QyMTMxZTA2YWEwZWJlOCIsInZlcnNpb24iOjF9.emXgdp6oFaWXSM_IwWe5f2AuML5q_AF9Fn1uVaLV6oQPQLUUn9kHuJjvhen8rpps3uwV5hlg_FQi1yA0ptg9Bw
- type: gen_len value: 47.6532 name: gen_len verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGYwYTA5NjBiMjQ4OTQyZjRjMjAzYWRjYThlZjRiOTAxYTY4YzFmZTY0NzFlZjA4MDY2YzE3M2VjODU3OWNjYyIsInZlcnNpb24iOjF9.VD34TzxOsg5dSxp3o8feeNS_i0jOShKyIgCco6gaI6CV2U2iADzOJRYvTk__il_mnTI8_Q3n5krTq5VBWIrnBg
- task:
type: summarization
name: Summarization
dataset:
name: xsum
type: xsum
config: default
split: test
metrics:
- type: rouge value: 19.3209 name: ROUGE-1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTYwOGVmZDZhNmJlMTk3ZmEzMThjMmJmNDVhMzMyZGYzM2NhMzc5ZDhiY2I0ZGMxZjYzZDBjMmQ0ZTYyZGM3YyIsInZlcnNpb24iOjF9.2CcwX9HsunSocmuXzYeGgUttbxSTJeI3Rd_z8ahVMOVKBU3gy_SFTz4jRAQ-reNpKXcHS-pXBnkrBKF1c909Ag
- type: rouge value: 2.7978 name: ROUGE-2 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDRiZjQ5ODRmNDVhNWMwMjBmZjUwNTkwZDU1OGVlZjlhNTIwZTQ1NDkyOTlhMTMwOGU2YjAwYjZjMTM5M2EyZSIsInZlcnNpb24iOjF9.th3dNtUmR9BK_1CErYVLkvp9pjbDEPrYouR_sfTOyHcsiUEnvXWAaHt8VfAjCvZa5GVExIUJ1mU5juWHGgqmCA
- type: rouge value: 12.5816 name: ROUGE-L verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTgwNmI1NzRhYzg2MDk2ZmJmYjE4YTNhMjk4OWZiOThjMTBlNmUxMGFjYjYwZjgzNWMwZThlZDIyMjJjZDEzMyIsInZlcnNpb24iOjF9.Px6A7iX1WEX0LkAtRYbgH3bG4ZhR7Qpm0j61SOtCU6tfwIhWjlfndXOB_1f4OM52P38WX17ug3Dbv_fopc4pDw
- type: rouge value: 15.0239 name: ROUGE-LSUM verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjhmOWJkNWY0MzkxMDI1NDlkMzhmMzEzOWM1OTE5ZjgwMDhmOGQyOWJkYzI5ODg1NTUzMmNlZDUyZjYyYzEyNyIsInZlcnNpb24iOjF9.wft3QMXCx8d6MLSE6NA4OxJ1Z6BVvpIw-BTtwJR8HZBPEVTrysG9tl3OwJ0oMV3ZvtzozW5WOGJ7sAxTXIqdAA
- type: loss value: 4.483709335327148 name: loss verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODYwMDc4MTFmZGRmMjljNzNiN2QxNDNiZWJhZDE3ODcyNDExOTQ1MzhhZTk5MzQ4ZmM1NTUxN2QyMDFkYjZhYiIsInZlcnNpb24iOjF9.NMGHLvhHJwFOKi1aojjHzwslAB-D_TUQmNN1iLpBokcNZjrbgw3qqO2HY2xQn7QEQFZpAy-UD7ptIJ5zpJhSDw
- type: gen_len value: 82.729 name: gen_len verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjkzYmI1YWE2MmVkODdjNzU4Y2U3NTgwZjdjYjMxZTBkYmIyODVkNzA0NzEyZjlmOGQ4ODg1ZWE2Mzc1ZDE2MiIsInZlcnNpb24iOjF9.1vDZt_Ujy6kM_VjgA7ZenMjg5UJUI_mXUueB3I1WYhsTOzq_Dib8cjlHejkFuLHbHoKzg4x5WEu90ncEpptIAg
- task:
type: summarization
name: Summarization
dataset:
name: billsum
type: billsum
config: default
split: test
metrics:
- type: rouge value: 36.5688 name: ROUGE-1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDA2MjFkZThjMTk3NGNjNzk3MzdlMjgyMDJkYzA1MGMwYjdkZTZjMzE2NGE1MjM5OTFiOTU3YmVmZTNiNGIzYiIsInZlcnNpb24iOjF9.-1cYB1OAdxdq6bJb1c1xavlHNQxtYcNvf1ro7a5U5zksCBsfufG-B7AWkgxlyfxMMb373bwq4QqbRkk8omiqAw
- type: rouge value: 12.5849 name: ROUGE-2 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjMzNDc2NzBjMGY4MTAyNzk3YTlkZDViOWZjNmEzODBhMDI3NTQ2ZDk4YzA2YTA1YmNmOTUwMjZiMjMzZTA0NiIsInZlcnNpb24iOjF9.WOedmezrR8FUpNaoPZEOzF8-m3zr77XoCUmQfw6RNlA_6otM0cQyOy2OZPWHAXv2Q9PLQHX1MntAf9ZLLXCfBQ
- type: rouge value: 22.2461 name: ROUGE-L verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDgyM2ZhN2QzMzU0YzY0YzU4MTE4OTQzMGVmNGE4Yjk4NWJlMWUzOWU0ZDY2ZDc0YTI1Y2RjZjA4ODM4YzRlNSIsInZlcnNpb24iOjF9.ApE22RN5wiJt3lo9_VgY7D7OLTC0xWcVZZ7Q2b3Z3qzfFVZnnr7GvOxDgqvKtU5SJEzvqvGUSqTa6pfCbvu7Bg
- type: rouge value: 30.6507 name: ROUGE-LSUM verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMThmOTQ4N2Q3NTdhNjVkNmUxZmY4MTRhNzYxMmZhMGU0NzJhYWE3YjAwMzE2ZmNiMGY2YzNiZWQ5NWZiMTQxZCIsInZlcnNpb24iOjF9.6gNsS7SASoDHs9nKeluC23FUcaTmo75DM18aRlT1T2HT3J66fuG9fWLpFpL2c1TtJTD_XU2aEnMeQO0VjIaHAQ
- type: loss value: 2.6456267833709717 name: loss verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzYxOTkxMDcyMTVkZDI0YWUyNTE5ZTE3YzM5MDc2ZDM5ZWZiNjhiNTBlZjlhNzA3OTQzZWJiZWRmNGFiYTdiYyIsInZlcnNpb24iOjF9.hOVX5_MW58SlQjDbEakqrZvFhmDcJTv3QNyhP7ayd4mOjHg2s8qPJPXQEpSsCNgTjNhd4h0WC3B6-dVXLSLFBw
- type: gen_len value: 139.0398 name: gen_len verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDkzMWU4MjZlYWUzZjBmN2ZmMTc4MjEyZDUwYTFhMWY0NTZmZTI4NjYyYzMxZDY5OGY0Y2E3MTA0NmJkYzNlYyIsInZlcnNpb24iOjF9.kJctRHl1hSPEjCO6GpFKTlJ190Mc70NTlGrX0sciIevCSZ8IgzITZEnuR5SP7FgZIcQV82PrGH2RifpD-ImRBA
- task:
type: summarization
name: Summarization
dataset:
name: launch/gov_report
type: launch/gov_report
config: plain_text
split: test
metrics:
- type: rouge value: 37.0248 name: ROUGE-1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTdmYTU0OWRiNTRlMjFmMzI3N2FjMDIyZmE3ZTMyZDEzZmIzNzRkOWVkZTc5YTg4NTc3ZWIyMDVjY2NlZDhlMSIsInZlcnNpb24iOjF9.-c5dYiAJ7mGXTrP2Q4rzXf3to_gLSicvE2et6NrLIhr4LfdhMWHl1KgOe1nSwkL_rI8pBMDLQ73_LhfjrnWfDQ
- type: rouge value: 9.0446 name: ROUGE-2 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGI0Y2JiZWFmNmYwMWYyYzVlZDgyZmZiZDcxZWU4NTgyMzA3MzJmOTM5NmQ1YzBlNTc1MDhiOWU0NWFiOGQ0ZiIsInZlcnNpb24iOjF9._a3fSk8m3-MIkU6EZFhga5_gD5fAkBYInEtGLi6fTkpO-MHCJPJhMKa3abkX7WYOGUWq2boK93LxRSUiJLisDA
- type: rouge value: 18.0521 name: ROUGE-L verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTI3OTI5OTBhZTRiOTVlOTM4NTJlNTRhYTAyZjYyY2JiMmNhNWUyY2U0ODcxY2UxYmUwNTdlNmZkMTQ4YjQyYSIsInZlcnNpb24iOjF9.6nfKp5X0L8h6UB7QCyWe9r-yUciqEoH_2MKTcCvJmJIzjyzjsVhwXcUicNvjF7tV2vozv3LTDImoz4RireAbCA
- type: rouge value: 33.4723 name: ROUGE-LSUM verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjJkMTU1OTFjZDE1Nzk4MmYzZWQzZmFhZGQ5MWRmNDM0ZGQ2MmNiMDQxOTY5MTNhM2QwZDE2NGViMDkzZTRjNyIsInZlcnNpb24iOjF9.8rwYGzNPFfTE2q0dgifp8z7EjpJt5KGrsfGE2dI8liEVrOziXZZYcY8tgVJldu9CsGpP4nUCMq93BA-ZrwyoBQ
- type: loss value: 3.381495237350464 name: loss verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmI0Y2ZmZmVmNDU1MGZlYTZlMDQ5YzY0ZmY1NjNlYzdmN2NmY2ZmZWI5NWJmNjQzNmJiZDUwOWU4YjYzYjFjMCIsInZlcnNpb24iOjF9.CkCmAGRz3s2YXbpqRDJ7bjfEpCllU-AS5QJo1ZznvTkKN4iv7aLHgiXKIkPKSfeO2qWj1zVL_P9NMG0IxBvXBA
- type: gen_len value: 211.2066 name: gen_len verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzY2NjQ4ZjBkZWI5MDE2Y2IwMmYxMDc3ZmRlZjk4M2U0MmQ4Mjg3YWZlZmM0ZjdiZDIyZTIxNDViNzExMTEwNiIsInZlcnNpb24iOjF9.hz2qJ2O3Hd6YDLveOZ1yKU7rMRpxs65nNGWaJ3Ln4niQXl_LqXB3em5cbl0FtWS_E9Ptso6o8fGz76mN6hNwDg
- task:
type: summarization
name: Summarization
dataset:
name: kmfoda/booksum
type: kmfoda/booksum
config: kmfoda--booksum
split: test
metrics:
long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP
NOTE: this is still a work-in-progress (WIP) and not completed/converged by any means, but sharing to maybe save some time for others :)
Updates
As I update this WIP checkpoint, I will post a note here.
- July 26, 2022: add two more epochs of training, metrics starting to be almost as good as the more-tuned
basevariant - July 8, 2022: add checkpoint with ~4 epochs of training on A100, equating to approx 350 steps of functional batch size 128
- July 4, 2022: add checkpoint with six additional epochs of training with the dataset summary outputs filtered to 1024 tokens, resolving the prior issue of short summaries.
About
- a checkpoint of Stancld/longt5-tglobal-large-16384-pubmed-3k_steps trained on
kmfoda/booksumfor about 26 epochs - max input lengths during training vary between 8192 and 16384 tokens depending on GPU availability. This checkpoint was trained with 16384 tokens as the max input length for the final 10+ epochs
Comparisons
- compare to pszemraj/led-large-book-summary.
- inference API has been disabled because it's too compute-intensive :/
Bart Large Cnn
MIT
BART model pre-trained on English corpus, specifically fine-tuned for the CNN/Daily Mail dataset, suitable for text summarization tasks
Text Generation English
B
facebook
3.8M
1,364
Parrot Paraphraser On T5
Parrot is a T5-based paraphrasing framework designed to accelerate the training of Natural Language Understanding (NLU) models through high-quality paraphrase generation for data augmentation.
Text Generation
Transformers
TransformersP
prithivida
910.07k
152
Distilbart Cnn 12 6
Apache-2.0
DistilBART is a distilled version of the BART model, specifically optimized for text summarization tasks, significantly improving inference speed while maintaining high performance.
Text Generation English
D
sshleifer
783.96k
278
T5 Base Summarization Claim Extractor
A T5-based model specialized in extracting atomic claims from summary texts, serving as a key component in summary factuality assessment pipelines.
Text Generation Transformers English
Transformers EnglishT
Babelscape
666.36k
9
Unieval Sum
UniEval is a unified multidimensional evaluator for automatic evaluation of natural language generation tasks, supporting assessment across multiple interpretable dimensions.
Text Generation Transformers
TransformersU
MingZhong
318.08k
3
Pegasus Paraphrase
Apache-2.0
A text paraphrasing model fine-tuned based on the PEGASUS architecture, capable of generating sentences with the same meaning but different expressions.
Text Generation Transformers English
Transformers EnglishP
tuner007
209.03k
185
T5 Base Korean Summarization
This is a Korean text summarization model based on the T5 architecture, specifically designed for Korean text summarization tasks. It is trained on multiple Korean datasets by fine-tuning the paust/pko-t5-base model.
Text Generation Transformers Korean
Transformers KoreanT
eenzeenee
148.32k
25
Pegasus Xsum
PEGASUS is a Transformer-based pretrained model specifically designed for abstractive text summarization tasks.
Text Generation English
P
google
144.72k
198
Bart Large Cnn Samsum
MIT
A dialogue summarization model based on the BART-large architecture, fine-tuned specifically for the SAMSum corpus, suitable for generating dialogue summaries.
Text Generation Transformers English
Transformers EnglishB
philschmid
141.28k
258
Kobart Summarization
MIT
A Korean text summarization model based on the KoBART architecture, capable of generating concise summaries of Korean news articles.
Text Generation Transformers Korean
Transformers KoreanK
gogamza
119.18k
12
Featured Recommended AI Models