Skip to content

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

active 2024-02-202026-03-31 (UTC)

Partial coverage20,533 / 26,289 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-14 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
548
Pushes
9
Pull requests
2
Issues
38
Stars
429
Forks
39

Activity over time

Daily event counts in the loaded window

Line chart, 771 days from 2024-02-20 to 2026-03-31. Pushes: 9 total, peak 5 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 38 total, peak 5 in a day. Comments: 30 total, peak 3 in a day. Stars: 429 total, peak 33 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#51JunZhan20002026-01-20 11:53
    小模型训练
  • Issue comment#51JunZhan20002026-01-20 11:53
    小模型训练
  • Issue comment#43OffbeatYiranZhao2025-09-05 18:53
    Does AnyGPT support multi images input?
  • Issue#51dox0122025-05-27 09:15
    小模型训练
  • Issue comment#31jingfanke2025-01-26 11:38
    Train_loss = 0 and Eval_loss = NaN in stage2_sft
  • Issue#49Dj123672025-01-19 17:55
    CUDA Runtime Error: Device-Side Assert Triggered
  • Issue comment#40Changhao-Xiang2025-01-04 14:48
    Regarding ASR testing
  • Issue#47baipeng12024-12-25 10:32
    BertLMHeadModel.from_pretrained("bert-base-uncased", config=encoder_config)
  • Issue comment#39BoyiMaria2024-12-24 17:36
    targets were set to all -100 in stage2_sft stage due to cur_len != expected_len
  • Issue comment#35yangkai20022024-12-17 03:25
    cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'
  • Issue comment#35yangkai20022024-12-17 03:21
    cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'
  • Issue comment#44JunZhan20002024-12-13 03:57
    High resolution images are not found
  • Issue#45Psychomachia2024-11-02 08:31
    Question about stage1_pretrain
  • Issue comment#42jee0192024-10-11 10:39
    Details on TTS evaluation?
  • Issue comment#33Arnold1347772024-09-24 06:59
    请教一下关于speech的问题
  • Issue#42Btlmd2024-09-14 13:30
    Details on TTS evaluation?
  • Issue#41ehosseiniasl2024-09-03 04:17
    preprocessing audio to SpeechTokenizer codecs
  • Issue#40Simplesss2024-08-28 02:44
    Regarding ASR testing
  • Issue#38ayaan-together2024-08-08 20:21
    Music Tokenizer Format
  • Issue#35Cubxx2024-08-03 09:31
    cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'
  • Issue comment#31JunZhan20002024-07-24 11:27
    Train_loss = 0 and Eval_loss = NaN in stage2_sft
  • Issue comment#30JunZhan20002024-07-24 11:20
    Question about training code
  • Issue comment#32JunZhan20002024-07-24 11:17
    Speech-to-Speech task prompt
  • Issue#32ehosseiniasl2024-07-23 23:21
    Speech-to-Speech task prompt
  • Issue#31Everglow-X2024-07-20 13:41
    Train_loss = 0 and Eval_loss = NaN in stage2_sft

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 429 stars here means stars gained during the window, not the repo's star count.