🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.
update rlhf
gongjy6861d1af566c
diff --git a/README.md b/README.mdindex e219825..7f3dd63 100644--- a/README.md+++ b/README.md@@ -238,7 +238,18 @@ streamlit run fast_inference.py* `python 2-eval.py`测试模型的对话效果-🍭 【Tip】预训练和全参微调pretrain和full_sft均支持多卡加速+🍭「Tip」预训练和全参微调pretrain和full_sft均支持多卡加速++> 假设你的设备只有1张显卡,使用原生python启动训练即可:++* 执行预训练或指令微调训练+ ```bash+ python 1-pretrain.py+ # and+ python 3-full_sft.py+ ```++> 假设你的设备有N (N>1) 张显卡:* 单机N卡启动训练(DDP)```bash@@ -253,7 +264,7 @@ streamlit run fast_inference.pydeepspeed --master_port 29500 --num_gpus=N 3-full_sft.py```-* 记录训练过程+* 开启wandb记录训练过程(非必须)```bashtorchrun --nproc_per_node N 1-pretrain.py --use_wandb# anddiff --git a/README_en.md b/README_en.mdindex 0fab7f9..5a7d17c 100644--- a/README_en.md+++ b/README_en.md@@ -259,7 +259,18 @@ streamlit run fast_inference.py* Test the model's conversational effect with `python 2-eval.py`-🍭 **Tip**: Pretraining and full parameter fine-tuning (`pretrain` and `full_sft`) support DDP multi-GPU acceleration.+🍭「Tip」Both pretrain and full_sft support multi-card acceleration.++> If your device has only 1 GPU, you can start the training using native Python:++* Execute pretrain or instruction fine-tuning:+ ```bash+ python 1-pretrain.py+ # and+ python 3-full_sft.py+ ```++> If your device has N (N > 1) GPUs:* Start training on a single machine with N GPUs(DDP)```bash