Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"
active 2024-02-20 → 2026-03-31 (UTC)
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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| JunZhan2000 | 37 | 9 | 0 | 17 |
| ehosseiniasl | 2 | 0 | 0 | 0 |
| Sunwood-ai-labs | 2 | 0 | 2 | 0 |
| mixiazhiyang | 2 | 0 | 0 | 1 |
| yangkai2002 | 2 | 0 | 0 | 2 |
| darkacorn | 2 | 0 | 0 | 1 |
| s-j-chung | 2 | 0 | 0 | 1 |
| jzhang38 | 2 | 0 | 0 | 0 |
| Yang-bug-star | 1 | 0 | 0 | 0 |
| lucasjinreal | 1 | 0 | 0 | 0 |
| Everglow-X | 1 | 0 | 0 | 0 |
| jingfanke | 1 | 0 | 0 | 1 |
| matbee-eth | 1 | 0 | 0 | 0 |
| Btlmd | 1 | 0 | 0 | 0 |
| hhfssg | 1 | 0 | 0 | 0 |
| Changhao-Xiang | 1 | 0 | 0 | 1 |
| BoyiMaria | 1 | 0 | 0 | 1 |
| OffbeatYiranZhao | 1 | 0 | 0 | 1 |
| Psychomachia | 1 | 0 | 0 | 0 |
| jee019 | 1 | 0 | 0 | 1 |
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 18:53Does AnyGPT support multi images input?
- Issue#51dox0122025-05-27 09:15小模型训练
- Issue comment#31jingfanke2025-01-26 11:38Train_loss = 0 and Eval_loss = NaN in stage2_sft
- Issue#49Dj123672025-01-19 17:55CUDA Runtime Error: Device-Side Assert Triggered
- Issue comment#40Changhao-Xiang2025-01-04 14:48Regarding ASR testing
- Issue#47baipeng12024-12-25 10:32BertLMHeadModel.from_pretrained("bert-base-uncased", config=encoder_config)
- Issue comment#39BoyiMaria2024-12-24 17:36targets were set to all -100 in stage2_sft stage due to cur_len != expected_len
- Issue comment#35yangkai20022024-12-17 03:25cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'
- Issue comment#35yangkai20022024-12-17 03:21cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'
- Issue comment#44JunZhan20002024-12-13 03:57High resolution images are not found
- Issue#45Psychomachia2024-11-02 08:31Question about stage1_pretrain
- Issue comment#42jee0192024-10-11 10:39Details on TTS evaluation?
- Issue comment#33Arnold1347772024-09-24 06:59请教一下关于speech的问题
- Issue#42Btlmd2024-09-14 13:30Details on TTS evaluation?
- Issue#41ehosseiniasl2024-09-03 04:17preprocessing audio to SpeechTokenizer codecs
- Issue#40Simplesss2024-08-28 02:44Regarding ASR testing
- Issue#38ayaan-together2024-08-08 20:21Music Tokenizer Format
- Issue#35Cubxx2024-08-03 09:31cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'
- Issue comment#31JunZhan20002024-07-24 11:27Train_loss = 0 and Eval_loss = NaN in stage2_sft
- Issue comment#30JunZhan20002024-07-24 11:20Question about training code
- Issue comment#32JunZhan20002024-07-24 11:17Speech-to-Speech task prompt
- Issue#32ehosseiniasl2024-07-23 23:21Speech-to-Speech task prompt
- Issue#31Everglow-X2024-07-20 13:41Train_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.