Skip to content

GGML implementation of BERT model with Python bindings and quantization.

active 2024-01-232024-05-11 (UTC)

Partial coverage18,338 / 23,484 hourly files (78%) · 2 absent upstream · 5,144 failed, retryable2023-12-082026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
119
Pushes
33
Pull requests
9
Issues
7
Stars
40
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 110 days from 2024-01-23 to 2024-05-11. Pushes: 33 total, peak 9 in a day. Pull requests: 9 total, peak 6 in a day. Issues: 7 total, peak 2 in a day. Comments: 28 total, peak 5 in a day. Stars: 40 total, peak 21 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

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

ContributorContributionsPushesPRsComments
iamlemec5433417
snowyu6023
PrithivirajDamodaran5003
WayneCao4003
sroussey2020
regstuff2001
turbo1000
sweetcard1000
ggerganov1010
Ingvarstep1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#17Ingvarstep2024-05-11 17:30
    Why llama.cpp runs substantially faster
  • Issue comment#17iamlemec2024-05-10 20:49
    Why llama.cpp runs substantially faster
  • Issue comment#17iamlemec2024-05-08 21:08
    Why llama.cpp runs substantially faster
  • Issue comment#16PrithivirajDamodaran2024-03-08 08:28
    Memory usage and slowness question
  • Issue#13PrithivirajDamodaran2024-03-03 13:04
    BERT MLM Question
  • Issue comment#15regstuff2024-03-03 07:37
    Works great on command line, but unable to use via python
  • Issue comment#16PrithivirajDamodaran2024-03-03 04:00
    Memory usage and slowness question
  • Issue comment#15iamlemec2024-03-02 21:23
    Works great on command line, but unable to use via python
  • Issue comment#14iamlemec2024-03-02 21:20
    Using llama.cpp
  • Issue#16PrithivirajDamodaran2024-03-02 17:46
    Memory usage and slowness question
  • Issue#15regstuff2024-03-02 07:51
    Works great on command line, but unable to use via python
  • Issue comment#14PrithivirajDamodaran2024-02-29 05:54
    Using llama.cpp
  • Issue comment#14iamlemec2024-02-28 21:47
    Using llama.cpp
  • Issue comment#11WayneCao2024-02-22 02:05
    does bert_encode() thread-safe for online embedding?
  • Issue comment#11WayneCao2024-02-21 02:42
    does bert_encode() thread-safe for online embedding?
  • Issue comment#11iamlemec2024-02-19 03:39
    does bert_encode() thread-safe for online embedding?
  • Issue comment#10iamlemec2024-02-19 03:34
    Compilation Error on macOS
  • Issue comment#11WayneCao2024-02-18 02:29
    does bert_encode() thread-safe for online embedding?
  • Issue#11WayneCao2024-02-18 02:25
    does bert_encode() thread-safe for online embedding?
  • Issue#10turbo2024-02-16 12:34
    Compilation Error on macOS
  • Issue comment#9snowyu2024-02-07 03:47
    Add unit tests
  • Issue comment#9iamlemec2024-02-06 22:23
    Add unit tests
  • Issue comment#9iamlemec2024-02-06 07:22
    Add unit tests
  • Issue comment#8iamlemec2024-02-06 05:34
    supports jinaai/jina-embeddings-v2-base-code
  • Pull request#9snowyu2024-02-06 02:44

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 40 stars here means stars gained during the window, not the repo's star count.