HelloSun
/

SmallThinker4b_EPQ

Text Generation

llama-cpp-python

Mixture of Experts

Model card Files Files and versions

SmallThinker4b_EPQ / validate /last-run.json

Commit History

Oct 7 18 days ago

14:48
v10: model card 加上完整實測數據（記憶體/速度/SSD/權重組成）；修 pager expert 總量高估 7% 的 bug

Auto Upload Agent

f279c31
14:31
v8: 修 io_probe 的 pread 計數 bug（SSD 337/667/1328/2558 MB/s）+ launcher arena 語意修正

Auto Upload Agent

84fbb3b
14:28
v6: llama_server.sh --verify 端到端通過（預算 512MiB → expert 常駐 510MiB、swap 0）

Auto Upload Agent

ff122a0
14:15
v3: 修 MAP_POPULATE 與 /proc/self/io 解析 bug；A/B 驗證工具；輸出逐字相同已證實

Auto Upload Agent

1e54449
13:45
v1: 驗證通過 — llama-server 起來、chat 正常、peak RSS 4.30 GiB / swap 0

Auto Upload Agent

625b02c