kanshan/minimind
1
0
Fork 0
mirror of https://github.com/jingyaogong/minimind.git synced 2026-04-25 08:48:16 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

[fix] layers set 8

Browse Source
This commit is contained in:
jingyaogong 2025-12-31 21:06:37 +08:00
parent 5dd4df7e18
commit bc8fd82166
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
trainer/train_full_sft.py
View File

@ -96,7 +96,7 @@ if __name__ == "__main__":
parser.add_argument("--log_interval", type=int, default=100, help="日志打印间隔")
parser.add_argument("--save_interval", type=int, default=1000, help="模型保存间隔")
parser.add_argument('--hidden_size', default=512, type=int, help="隐藏层维度")
parser.add_argument('--num_hidden_layers', default=16, type=int, help="隐藏层数量")
parser.add_argument('--num_hidden_layers', default=8, type=int, help="隐藏层数量")
parser.add_argument('--max_seq_len', default=340, type=int, help="训练的最大截断长度（中文1token≈1.5~1.7字符）")
parser.add_argument('--use_moe', default=0, type=int, choices=[0, 1], help="是否使用MoE架构（0=否，1=是）")
parser.add_argument("--data_path", type=str, default="../dataset/sft_mini_512.jsonl", help="训练数据路径")

2
trainer/train_pretrain.py
View File

@ -95,7 +95,7 @@ if __name__ == "__main__":
parser.add_argument("--log_interval", type=int, default=100, help="日志打印间隔")
parser.add_argument("--save_interval", type=int, default=1000, help="模型保存间隔")
parser.add_argument('--hidden_size', default=512, type=int, help="隐藏层维度")
parser.add_argument('--num_hidden_layers', default=16, type=int, help="隐藏层数量")
parser.add_argument('--num_hidden_layers', default=8, type=int, help="隐藏层数量")
parser.add_argument('--max_seq_len', default=340, type=int, help="训练的最大截断长度（中文1token≈1.5~1.7字符）")
parser.add_argument('--use_moe', default=0, type=int, choices=[0, 1], help="是否使用MoE架构（0=否，1=是）")
parser.add_argument("--data_path", type=str, default="../dataset/pretrain_hq.jsonl", help="预训练数据路径")