Skip to content

Latest commit

 

History

History
62 lines (38 loc) · 2.36 KB

SHA256.md

File metadata and controls

62 lines (38 loc) · 2.36 KB

SHA256

为了保证文件的完整性,请一定要检查下列文件SHA256值的一致性。

To ensure the completeness of the model, please check the folllowing SHA256 before using them.

Original LLaMA (consolidated.*.pth)

下表展示了Facebook发布的原版英文LLaMA的SHA256。

The followings are SHA256 values for the original LLaMA files.

Model (.pth) Parts SHA256
7B 00 700df0d3013b703a806d2ae7f1bfb8e59814e3d06ae78be0c66368a50059f33d
13B 00 745bf4e29a4dd6f411e72976d92b452da1b49168a4f41c951cfcc8051823cf08
13B 01 d5ccbcc465c71c0de439a5aeffebe8344c68a519bce70bc7f9f92654ee567085

LoRA Zip files (.zip)

下表展示了下载压缩包的SHA256。

The followings are SHA256 values for downloaded zip files.

LoRA Model (.zip) SHA256
Chinese-LLaMA-7B 39b86b310fe4c2b76fd1dd8234775af63ab94772a80bcae33a4086a9a7fe0e60
Chinese-LLaMA-13B 3d6dee787526db8bebc46271287e83b176e0f0db026dff493e088baf9be5199b
Chinese-Alpaca-7B 9bb5b639dc2ea9ad593268b5f6abf85514c7637bf10f2344eb7031fe0fce2d87
Chinese-Alpaca-13B 45c92e574fdfee1d48d573a1df3a782b5183ec486d4c5f0d716c7d43a2682d91

Merged files (consolidated.*.pth)

下表展示了合并LoRA权重后的全量模型权重(PyTorch版)的SHA256。

The followings are SHA256 values for merged files (consolidated.00.pth) in the last merging step.

因Transformers库更新频繁,合并后的模型权重SHA256可能随Transformers更新而发生变化,不具有普遍参考价值,因此我们不再展示合并后模型的SHA256。

Due to the frequent updates of the Transformers library, the SHA256 of the merged model may change with the update of Transformers and is not stable, so we no longer show the SHA256 of the merged model.

How To Check SHA256

In MacOS,

> shasum -a 256 your-model-file

In Linux,

> sha256sum your-model-file

In Windows,

> certutil -hashfile your-model-file sha256