Skip to content

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

active 2023-11-252026-08-12 (UTC)

Partial coverage18,522 / 23,783 hourly files (78%) · 2 absent upstream · 5,259 failed, retryable2023-11-252026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
618
Pushes
1
Pull requests
2
Issues
16
Stars
534
Forks
47

Activity over time

Daily event counts in the loaded window

Line chart, 992 days from 2023-11-25 to 2026-08-12. Pushes: 1 total, peak 1 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 16 total, peak 1 in a day. Comments: 18 total, peak 4 in a day. Stars: 534 total, peak 7 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#274kiarasooryavanshi1-svg2026-08-12 04:33
    Why Is SEO Becoming a Major Growth Driver for Mumbai Businesses?
  • Issue comment#144Sainithin-bit2025-08-28 05:29
    Loss is nan, stopping training, while trying to reproduce alpaca_finetuning_v1 results.
  • Issue comment#145Melonehhh2025-01-16 07:19
    Simple question about llama adapter v1 transformer forward function
  • Issue#157Saisai-Xia2024-12-26 02:28
    reproduce result on ScienceQA
  • Pull request#156tREeFrOGcoder2024-12-24 21:54
  • Issue comment#154nghiemkythu2024-12-24 15:00
    Loss and performance when reproduce LLaMA-Adapter V1 on Alpaca dataset.
  • Issue#154nghiemkythu2024-12-24 03:45
    Loss and performance when reproduce LLaMA-Adapter V1 on Alpaca dataset.
  • Issue#130JINAILAB2024-08-04 23:38
    I have problem with downloading 7B_chinese in imagebind_LLM.
  • Issue#4Andrey366522024-07-02 21:26
    Question: Can the number of "adaptable" layers be significantly reduced? Can training be optimized for "extremely consumer" grade GPUs like the 3060 Ti (8GB VRAM)?
  • Issue comment#126waybarrios2024-04-05 18:53
    Is the llama adapter v2 code not available yet?
  • Issue#1499p15p2024-03-22 07:45
    The meaning of C_loss and M_loss
  • Issue comment#72OldStone01242024-03-07 03:01
    llama-adapterV2 multi modal demo error
  • Issue comment#147xuai052024-03-04 02:08
    Getting weird output for multimodal 7B adapter
  • Issue comment#72xuai052024-03-04 02:07
    llama-adapterV2 multi modal demo error
  • Issue comment#72xuai052024-03-04 02:07
    llama-adapterV2 multi modal demo error
  • Issue comment#147xuai052024-03-04 02:00
    Getting weird output for multimodal 7B adapter
  • Issue#145yestaehyung2024-02-13 02:33
    Simple question about llama adapter v1 transformer forward function
  • Issue#144navaneethnivol2024-02-08 01:24
    Loss is nan, stopping training, while trying to reproduce alpaca_finetuning_v1 results.
  • Issue#143GussailRaat2024-02-03 06:26
    Getting error "AF_UNIX path too long"
  • Issue#142cyZhang002024-01-24 00:33
    Don't find save path"ADAPTER_PATH"
  • Issue comment#140LiuHaolan2024-01-23 20:34
    AssertionError: Loading a checkpoint for MP=0 but world size is 1
  • Pull request#141persistz2024-01-23 04:00
  • Issue comment#140csuhan2024-01-04 12:46
    AssertionError: Loading a checkpoint for MP=0 but world size is 1
  • Issue#140IsraelAbebe2023-12-31 15:25
    AssertionError: Loading a checkpoint for MP=0 but world size is 1
  • Issue#139xiujiesong2023-12-30 04:22
    [LLaMA Adapter V2] Evaluation on multiple choice questions.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 534 stars here means stars gained during the window, not the repo's star count.