admin/LLM-from-scratch

T

coffee b3af9deb6c add torch version

2025-05-06 17:57:45 +08:00

add corpus files and update ignore

2025-04-29 18:35:28 +08:00

add LLM code

2025-04-29 18:59:54 +08:00

add trained BBPE Tokenizer model

2025-04-30 17:25:53 +08:00

add trained BBPE Tokenizer model

2025-04-30 17:25:53 +08:00

add utils for data process

2025-04-29 18:28:45 +08:00

.gitignore

add corpus files and update ignore

2025-04-29 18:35:28 +08:00

LICENSE

Initial commit

2025-04-23 22:42:17 +08:00

README.md

update README

2025-04-30 16:47:14 +08:00

requirements.txt

add torch version

2025-05-06 17:57:45 +08:00

README.md

LLM-Dolly

LLM-Dolly is a custom LLM built from scratch

🗓️ 更新日志

2025-04-30

📝 添加Tokenizer的BBPE方式训练。

2025-04-29

📝 添加tokenizer构建代码，支持sentencepiece和transfomers方式，支持从文本构建和从已有的tokenzier构建。

2025-04-24

✅ 测试从transformers构建自定义的LLM模型结构。

致谢

特别感谢以下资源和文章的帮助：