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.

update 0-eval_pretrain.py

gongjya8405b08a27f
diff --git a/0-eval_pretrain.py b/0-eval_pretrain.py
index 32f1dda..edb3ad8 100644
--- a/0-eval_pretrain.py
+++ b/0-eval_pretrain.py
@@ -16,8 +16,7 @@ def count_parameters(model):
def init_model(lm_config):
- tokenizer = AutoTokenizer.from_pretrained('./model/minimind_tokenizer',
- trust_remote_code=True, use_fast=False)
+ tokenizer = AutoTokenizer.from_pretrained('./model/minimind_tokenizer')
model_from = 1 # 1从权重,2用transformers
if model_from == 1: