Skip to content

🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.

[feat] get params

jingyaogong9236260a4a3f
diff --git a/trainer/trainer_utils.py b/trainer/trainer_utils.py
index 49f263f..a50737b 100644
--- a/trainer/trainer_utils.py
+++ b/trainer/trainer_utils.py
@@ -12,7 +12,7 @@ import torch
import torch.distributed as dist
from torch.utils.data import Sampler
from transformers import AutoTokenizer
-from model.model_minimind_qwen3 import MiniMindForCausalLM
+from model.model_minimind import MiniMindForCausalLM
def get_model_params(model, config):
total = sum(p.numel() for p in model.parameters()) / 1e6