JLNTV_IPD/CogVideo
4
0
Fork 0
mirror of https://github.com/THUDM/CogVideo.git synced 2025-04-05 19:41:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

T5 说明

Browse Source
This commit is contained in:
zR 2024-08-07 16:25:17 +08:00
parent f0b5f35934
commit a73101c958
2 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
sat/README.md
View File

@ -51,6 +51,19 @@ mv CogVideoX-2b/text_encoder/* CogVideoX-2b/tokenizer/* t5-v1_1-xxl
By following the above approach, you will obtain a safetensor format T5 file. Ensure that there are no errors when
loading it into Deepspeed in Finetune.
```
├── added_tokens.json
├── config.json
├── model-00001-of-00002.safetensors
├── model-00002-of-00002.safetensors
├── model.safetensors.index.json
├── special_tokens_map.json
├── spiece.model
└── tokenizer_config.json
0 directories, 8 files
```
3. Modify the file `configs/cogvideox_2b_infer.yaml`.
```yaml

11
sat/README_zh.md
View File

@ -47,7 +47,18 @@ mkdir t5-v1_1-xxl
mv CogVideoX-2b/text_encoder/* CogVideoX-2b/tokenizer/* t5-v1_1-xxl
```
通过上述方案，你将会得到一个 safetensor 格式的T5文件，确保在 Deepspeed微调过程中读入的时候不会报错。
```
├── added_tokens.json
├── config.json
├── model-00001-of-00002.safetensors
├── model-00002-of-00002.safetensors
├── model.safetensors.index.json
├── special_tokens_map.json
├── spiece.model
└── tokenizer_config.json
0 directories, 8 files
```
3. 修改`configs/cogvideox_2b_infer.yaml`中的文件。
```yaml