针对PCB电路板检测场景，对Qwen2.5模型进行微调
Python · active 2025-12-31 → 2026-08-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 221 days from 2025-12-31 to 2026-08-08. Pushes: 86 total, peak 9 in a day. Pull requests: 107 total, peak 9 in a day. Issues: 465 total, peak 185 in a day. Comments: 338 total, peak 13 in a day. Stars: 1,813 total, peak 51 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 |
|---|---|---|---|---|
| hiyouga | 198 | 79 | 35 | 29 |
| gemini-code-assist[bot] | 184 | 0 | 0 | 134 |
| majakthab-jpg | 63 | 0 | 0 | 0 |
| Kuangdd01 | 59 | 6 | 9 | 20 |
| sferdgf | 45 | 0 | 0 | 0 |
| Saturdaychange1 | 34 | 0 | 0 | 0 |
| apachev45 | 28 | 0 | 0 | 0 |
| iamjohncenaa | 26 | 0 | 0 | 0 |
| jiaqiw09 | 26 | 0 | 6 | 13 |
| xbfdgfchbgv | 24 | 0 | 0 | 0 |
| frozenleaves | 22 | 0 | 7 | 10 |
| hulk0001 | 11 | 0 | 0 | 0 |
| iamrajnikant | 10 | 0 | 0 | 0 |
| paasosofia | 10 | 0 | 0 | 0 |
| Jimmo-Liffer | 9 | 0 | 0 | 0 |
| pingoliadimpal-stack | 8 | 0 | 0 | 0 |
| gul0fank | 8 | 0 | 0 | 0 |
| qwrtfc | 7 | 0 | 0 | 0 |
| isLinXu | 6 | 0 | 2 | 2 |
| sbhavani | 6 | 0 | 0 | 3 |
Recent activity
Latest issues, pull requests and releases
- Pull request#10518luca-8882026-07-02 03:06
- Issue#10596liyf-llm2026-06-22 02:18lora微调后合并模型并vllm部署效果下降，但直接使用llamafactory分别加载基座模型与checkpoint建立的接口测试没问题
- Pull request#10571yangtao-hub2026-06-13 12:03
- Issue#10548lwang10-atlassian2026-06-03 22:50Will Gemma4 12b fine-tuning be supported?
- Releasehiyouga2026-05-30 15:57v0.9.5: Qwen3.5/3.6, Gemma 4, Transformers v5
- Issue comment#10501frozenleaves2026-05-29 08:05从checkpoint开始训练报torch版本不兼容，需要torch2.6版本，但cuda12.1不兼容
- Pull request#10514QrowBranwen2026-05-27 08:07
- Issue comment#10388Ricardo-M-L2026-05-22 03:04fix: add None check for feature_extractor in Gemma4Plugin audio processing
- Pull request#10469jiaqiw092026-05-21 09:14
- Pull request#10493hiyouga2026-05-21 03:44
- Pull request#10494A1waysBeenHere2026-05-15 02:23
- Issue#10459hiyouga2026-05-09 11:34llamafactory-cli train -h broken
- Issue comment#10464Kuangdd012026-05-08 08:33[data] qwen3_vl: relax default thought_words to handle single-newline </think>
- Pull request#10471Swimakkkkkkkk2026-05-08 07:17
- Issue#10466frozenleaves2026-05-08 03:49no qwen3_6_nothink template
- Pull request#10470frozenleaves2026-05-08 03:47
- Issue#10377frozenleaves2026-05-08 03:14qwen3-5模型微调环境支持
- Issue comment#10470frozenleaves2026-05-08 03:01[fix] fix qwen3_6 template doc
- Issue#10398Kuangdd012026-05-03 10:39Repeated video decoding during tokenizer/message preprocessing
- Issue#10398Kuangdd012026-05-03 10:39Repeated video decoding during tokenizer/message preprocessing
- Issue#10398Kuangdd012026-05-03 10:39Repeated video decoding during tokenizer/message preprocessing
- Issue#10398Kuangdd012026-05-03 10:39Repeated video decoding during tokenizer/message preprocessing
- Pull request#10404luca-8882026-05-03 10:36
- Pull request#10404Kuangdd012026-05-03 10:36
- Pull request#10404Kuangdd012026-05-03 10:36
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,813 stars here means stars gained during the window, not the repo's star count.