Skip to content

An unofficial Pytorch implementation of ERNIE-Layout which is originally released through PaddleNLP.

active 2023-08-182025-12-04 (UTC)

Complete coverage26,444 / 26,444 hourly files (100%) · 2 absent upstream2023-08-152026-08-20 (UTC)
Events
105
Pushes
16
Pull requests
0
Issues
14
Stars
55
Forks
4

Activity over time

Daily event counts in the loaded window

Line chart, 840 days from 2023-08-18 to 2025-12-04. Pushes: 16 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 5 in a day. Comments: 11 total, peak 3 in a day. Stars: 55 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
NormXU231606
DiddyC7001
rbvh3002
14H0341602123001
Jermaine19963001
tianchiguaixia1000
madhavi11021000

Recent activity

Latest issues, pull requests and releases

  • Issue#25madhavi11022025-02-10 12:00
    Looking for Finetuning ERNIE-Layout for Document Image classification on custom dataset
  • Issue comment#24DiddyC2024-10-22 15:39
    Outputs are driven to zero when there's a strong imbalance
  • Issue#24DiddyC2024-10-22 15:39
    Outputs are driven to zero when there's a strong imbalance
  • Issue#24DiddyC2024-10-22 15:39
    Outputs are driven to zero when there's a strong imbalance
  • Issue#24DiddyC2024-10-22 15:39
    Outputs are driven to zero when there's a strong imbalance
  • Issue#24DiddyC2024-10-22 15:39
    Outputs are driven to zero when there's a strong imbalance
  • Issue#24DiddyC2024-10-22 15:39
    Outputs are driven to zero when there's a strong imbalance
  • Issue comment#24NormXU2024-10-05 04:07
    Outputs are driven to zero when there's a strong imbalance
  • Issue#24DiddyC2024-10-04 20:07
    Outputs are driven to zero when there's a strong imbalance
  • Issue#23tianchiguaixia2024-08-16 08:03
    有对应的使用torch训练ernire-layout的代码?
  • Issue#2214H0341602122024-08-15 07:46
    Which version of Flash Attention has been used in this project?
  • Issue comment#2214H0341602122024-05-22 06:20
    Which version of Flash Attention has been used in this project?
  • Issue comment#22NormXU2024-04-18 06:00
    Which version of Flash Attention has been used in this project?
  • Issue#2214H0341602122024-04-18 03:49
    Which version of Flash Attention has been used in this project?
  • Issue#20NormXU2024-02-08 14:00
    Using the new extended seq length
  • ReleaseNormXU2023-11-15 07:26
  • Issue comment#21Jermaine19962023-11-15 03:41
    A question about tokenizer
  • Issue#21Jermaine19962023-11-15 03:41
    A question about tokenizer
  • Issue comment#21NormXU2023-11-15 03:34
    A question about tokenizer
  • Issue#21Jermaine19962023-11-15 03:21
    A question about tokenizer
  • Issue comment#20NormXU2023-09-18 13:45
    Using the new extended seq length
  • Issue comment#20rbvh2023-09-18 13:07
    Using the new extended seq length
  • ReleaseNormXU2023-09-13 12:47
    v1.2.2
  • Issue comment#20NormXU2023-09-08 14:47
    Using the new extended seq length
  • Issue comment#20rbvh2023-09-08 10:37
    Using the new extended seq length

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 55 stars here means stars gained during the window, not the repo's star count.