feat: 训练任务支持从最新 checkpoint 继续训练

- 后端: 新增 resume/checkpoints 端点,compute 客户端与适配器支持续训
- 计算节点: llama_factory 适配器断点续训支持及测试
- 前端: fine-tune API 封装与列表页续训/断点展示
This commit is contained in:
wuyongtao
2026-08-21 14:48:55 +08:00
parent 0233755859
commit 0b59c1ebee
6 changed files with 276 additions and 7 deletions

View File

@@ -336,6 +336,7 @@ def build_command(config: dict[str, Any], llama_factory_home: str = "/app/LLaMA-
_optional_arg(config, command, "--val_size", "val_size")
_optional_arg(config, command, "--max_samples", "max_samples")
_optional_arg(config, command, "--preprocessing_num_workers", "preprocessing_num_workers")
_optional_arg(config, command, "--resume_from_checkpoint", "resume_from_checkpoint")
_optional_bool_arg(config, command, "--fp16", "fp16")
_optional_bool_arg(config, command, "--bf16", "bf16")
quantization_bit = int(config.get("quantization_bit", 0) or 0)