obscura/minimind
1
0
Fork 0
mirror of https://github.com/jingyaogong/minimind.git synced 2026-06-06 00:04:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

[update] change default seq_len

Browse Source
This commit is contained in:
jingyaogong
2026-03-26 10:09:06 +08:00
parent 101d7df2da
commit b8b3d35257
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
trainer/train_full_sft.py
+1 -1
View File
@@ -96,7 +96,7 @@ if __name__ == "__main__":
parser.add_argument("--save_interval", type=int, default=1000, help="模型保存间隔")
parser.add_argument('--hidden_size', default=768, type=int, help="隐藏层维度")
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('--max_seq_len', default=768, 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_t2t_mini.jsonl", help="训练数据路径")
parser.add_argument('--from_weight', default='pretrain', type=str, help="基于哪个权重训练，为none则不基于任何权重训练")