[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Python · active 2025-01-30 → 2026-05-30 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 486 days from 2025-01-30 to 2026-05-30. Pushes: 9 total, peak 2 in a day. Pull requests: 24 total, peak 3 in a day. Issues: 227 total, peak 19 in a day. Comments: 358 total, peak 28 in a day. Stars: 1,494 total, peak 53 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 |
|---|---|---|---|---|
| Weiyun1025 | 136 | 4 | 7 | 88 |
| lll2343 | 18 | 0 | 0 | 8 |
| shuoyinn | 9 | 0 | 0 | 5 |
| czczup | 9 | 5 | 2 | 2 |
| yuecao0119 | 8 | 0 | 0 | 8 |
| mustansarfiaz | 6 | 0 | 0 | 5 |
| YuanDaoze | 6 | 0 | 0 | 5 |
| HiXxxSss | 5 | 0 | 0 | 2 |
| Yuxin916 | 5 | 0 | 0 | 3 |
| zzk6626 | 5 | 0 | 0 | 3 |
| HuaYuexia | 5 | 0 | 0 | 5 |
| Zxr1314 | 5 | 0 | 0 | 1 |
| corkiyao | 5 | 0 | 0 | 4 |
| zyandtom | 5 | 0 | 0 | 4 |
| 2655324127 | 4 | 0 | 0 | 3 |
| 2kxx | 4 | 0 | 0 | 2 |
| JihwanEom | 4 | 0 | 0 | 2 |
| LiJiaqi96 | 4 | 0 | 0 | 3 |
| kachhadiyaraj15 | 3 | 0 | 0 | 1 |
| BruceYu-Bit | 3 | 0 | 0 | 3 |
Recent activity
Latest issues, pull requests and releases
- Pull request#1271goanpeca2026-05-27 23:56
- Pull request#1266joelmoniz2026-03-22 09:58
- Pull request#1266joelmoniz2026-03-22 09:58
- Issue#1265xueyunfeng1232026-03-17 03:53[Bug] Invalid JSON format in `debug_mpo.json` causes JSONDecodeError
- Issue comment#1254a1ei2026-02-22 15:07RuntimeError: Tensor.item() cannot be called on meta tensors with Transformers 5.x InternVL 3.5 fails to load with Transformers v5 due to meta tensor initialization
- Issue#1261mv2050arshad2026-02-20 20:11Video frame size
- Issue comment#1255Mr-Neutr0n2026-02-12 18:11Fix ValueError for unsupported LLM architectures in InternVLChatConfig
- Issue comment#1254foal20ym2026-02-11 09:37RuntimeError: Tensor.item() cannot be called on meta tensors with Transformers 5.x InternVL 3.5 fails to load with Transformers v5 due to meta tensor initialization
- Pull request#1256Mr-Neutr0n2026-02-09 18:41
- Issue comment#1254yalabri202026-02-09 15:12RuntimeError: Tensor.item() cannot be called on meta tensors with Transformers 5.x InternVL 3.5 fails to load with Transformers v5 due to meta tensor initialization
- Issue comment#96yuanyuanjia71-spec2026-02-03 06:30Multi GPU Issue
- Issue#1250cssx12342026-01-31 07:51做video评测的时候16帧及以上会超上下文
- Issue comment#1248lvhan0282026-01-22 09:17[Bug] InternVL3-78B produces incorrect / unstable inference results on A800 with TurboMind backend (works correctly on V100)
- Issue#1248niuwagege2026-01-21 09:47[Bug] InternVL3-78B produces incorrect / unstable inference results on A800 with TurboMind backend (works correctly on V100)
- Issue#1247V-yw2026-01-07 10:08[Docs] 输入图片的尺寸会被自动调整
- Issue#1245Scalcium2025-12-28 08:03nvcc fatal : Unsupported gpu architecture 'compute_1.'
- Issue#1243xueyuG2025-12-22 13:00Reasoning mode of InternVL3_5-8B
- Issue comment#1193Tonny6662025-12-21 03:35Stuck while training InternVL3.5-30B-A3B
- Issue comment#1236Fu-Fu-Fu-Fu2025-12-18 09:34vllm推理internal
- Issue comment#1236Fu-Fu-Fu-Fu2025-12-18 09:30vllm推理internal
- Issue#1241root2212025-12-16 21:30Generation repetition after MPO post-training
- Issue#1240Polydick2025-12-14 00:01[Bug]
- Issue comment#1231Sibajar2025-12-10 22:35InternVL3_5-1B-Flash no speed-up vs. InternVL3_5-1B
- Issue comment#1175aminer-4042025-12-09 05:34[Bug] vllm deploy InternVL3_5-241B-A28B error
- Issue comment#1237nx37822025-12-06 22:00Merge Full Fine-tuning/LoRA Weights
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,494 stars here means stars gained during the window, not the repo's star count.