Skip to content

Code for Byte Latent Transformer (BLT) research paper

active 2025-03-262026-05-26 (UTC)

Partial coverage11,294 / 12,090 hourly files (93%) · 2 absent upstream · 794 failed, retryable2025-03-252026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
503
Pushes
12
Pull requests
12
Issues
18
Stars
272
Forks
42

Activity over time

Daily event counts in the loaded window

Line chart, 427 days from 2025-03-26 to 2026-05-26. Pushes: 12 total, peak 4 in a day. Pull requests: 12 total, peak 2 in a day. Issues: 18 total, peak 2 in a day. Comments: 131 total, peak 32 in a day. Stars: 272 total, peak 36 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

Recent activity

Latest issues, pull requests and releases

  • Issue#142yuedajiong2026-05-26 00:08
    Great!!! And a question: What is the best tokenization-free algorihtm? SpaceByte, ByteLatentTransformer, DynamicChunking@SSM?
  • Pull request#140dwipam2026-03-14 16:00
  • Issue comment#139meta-cla[bot]2026-01-04 17:35
    Fix illegal memory access & Upgrade dependencies to CUDA 12.4
  • Issue comment#131Yuvrajsinh0409032025-10-22 20:36
    LMTransformer.__init__() missing 1 required positional argument: 'args'
  • Issue#136Cikguseven2025-10-16 08:37
    demo.py RuntimeError: CUDA error: an illegal memory access was encountered
  • Issue comment#131marksverdhei2025-09-27 13:27
    LMTransformer.__init__() missing 1 required positional argument: 'args'
  • Issue comment#131EntilZha2025-09-26 18:33
    LMTransformer.__init__() missing 1 required positional argument: 'args'
  • Issue#135zdxdsw2025-09-13 15:25
    How to reset entropy context -- avoiding entropy "drifting"?
  • Issue comment#126meta-cla[bot]2025-09-12 22:04
    Fix patching code
  • Issue comment#127meta-cla[bot]2025-09-12 22:04
    Speed up model loading
  • Issue#134zdxdsw2025-09-08 05:06
    When bpe_delim = True, do we skip BPE_ID when calculating NLL?
  • Issue comment#131marksverdhei2025-07-27 21:00
    LMTransformer.__init__() missing 1 required positional argument: 'args'
  • Issue#131gustawdaniel2025-07-03 13:53
    LMTransformer.__init__() missing 1 required positional argument: 'args'
  • Issue#130gustawdaniel2025-07-03 12:35
    ModuleNotFoundError: No module named 'setuptools'
  • Issue#128CharlesDDDD2025-06-29 05:44
    Validation Loss Stagnate on BLT Arch
  • Issue comment#125itazap2025-06-16 07:56
    Cannot Reproduce BLT Tokenization with bpe_delim=True Due to Missing BPE Model File
  • Issue comment#127gahdritz2025-06-11 03:47
    Speed up model loading
  • Issue comment#127EntilZha2025-06-11 00:31
    Speed up model loading
  • Pull request#126gahdritz2025-06-05 21:13
  • Issue#125SathvikSat2025-06-05 18:23
    Cannot Reproduce BLT Tokenization with bpe_delim=True Due to Missing BPE Model File
  • Issue comment#119zbdx-lcy2025-06-05 09:48
    Where can I find the .pt files needed for testing?
  • Pull request#122itazap2025-06-03 21:15
  • Issue#123gahdritz2025-06-03 14:22
    Patching code unsuitable for batch inference
  • Issue comment#122facebook-github-bot2025-06-03 13:34
    consolidated model file
  • Pull request#122itazap2025-06-03 13:34

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 272 stars here means stars gained during the window, not the repo's star count.