tokenizer

所属分类:特征抽取
开发工具:Jupyter Notebook
文件大小:0KB
下载次数:0
上传日期:2023-09-20 11:01:22
上 传 者sh-1993
说明:  玩着编写标记器,
(playing with writing a tokenizer,)

文件列表:
.vscode/ (0, 2023-09-23)
.vscode/settings.json (136, 2023-09-23)
1-byte-token-frequencies.png (180806, 2023-09-23)
50k-token-frequencies.png (103401, 2023-09-23)
LICENSE (1070, 2023-09-23)
gpt2-token-frequencies.png (144530, 2023-09-23)
test.ipynb (410299, 2023-09-23)
test.mp4 (1942499, 2023-09-23)
test_50k_good.mp4 (1541128, 2023-09-23)
vocab.csv (950087, 2023-09-23)

# tokenizer playing with writing a tokenizer

近期下载者

相关文件


收藏者