xming521 5dcaad0e10 perf(infer): clear cuda cache after inference ...

Adds a call to empty the CUDA cache immediately after the LLM object is deleted, ensuring prompt release of GPU memory. This helps prevent out-of-memory issues and improves resource utilization for subsequent operations.

2025-08-17 15:18:37 +08:00

..

core

perf(infer): clear cuda cache after inference

2025-08-17 15:18:37 +08:00

data

refactor(data): improve data cleaning robustness

2025-08-17 14:30:17 +08:00

eval

翻译注释日志为英文

2025-07-01 20:00:34 +08:00

prompts

更新README文档，修正平台支持表格中的内容，调整评分标准的描述，增加逻辑性和相关性评判的说明；在online_infer.py中添加TODO注释以实现线程池并发处理。

2025-07-05 15:21:39 +08:00

server

0.2.23 运行 weclone-cli server 报错

2025-06-19 16:38:09 +08:00

train

refactor(data): improve data cleaning robustness

2025-08-17 14:30:17 +08:00

utils

fix(dataset): fix #192 standardize dataset naming and cleaning workflow

2025-08-16 22:51:29 +08:00

__init__.py

重构项目

2025-04-21 20:30:55 +08:00

cli.py

更新README文档，添加Telegram数据导出说明，修改数据预处理配置说明，调整示例配置文件中的语言设置和参数

2025-07-01 21:35:58 +08:00