MengYue-MK2000 b1ac936d36 created windows_download_dataset.sh, deleted original changes in download_dataset.sh

2025-06-19 17:52:24 +08:00

..

tokenizer_k

fix(tokenizer): 将add_prefix_space配置改为false

2025-06-08 09:27:21 +08:00

dataset.py

update ch05

2025-02-26 20:31:51 +08:00

ddp_pretrain.py

update ch05

2025-02-26 20:31:51 +08:00

ddp_sft_full.py

update ch05

2025-02-26 20:31:51 +08:00

deal_dataset.py

docs(chapter5): 更新模型文档并添加数据处理脚本

2025-06-18 16:26:33 +08:00

download_dataset.sh

created windows_download_dataset.sh, deleted original changes in download_dataset.sh

2025-06-19 17:52:24 +08:00

export_model.py

update ch05

2025-02-26 11:24:19 +08:00

k_model.py

update ch05

2025-02-26 20:31:51 +08:00

model_sample.py

update ch05

2025-02-26 20:31:51 +08:00

requirements.txt

docs(chapter5): 添加LLaMA2结构图并更新依赖

2025-06-09 22:14:01 +08:00

train_tokenizer.py

fix(tokenizer): 将add_prefix_space配置改为false

2025-06-08 09:27:21 +08:00

windows_download_dataset.sh

created windows_download_dataset.sh, deleted original changes in download_dataset.sh

2025-06-19 17:52:24 +08:00