wassname/Open-Assistant
1
0
Fork 0
mirror of https://github.com/wassname/Open-Assistant.git synced 2026-07-19 11:20:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

[fix] push fix by linter

Browse Source
This commit is contained in:
theblackcat102
2023-01-06 17:11:06 +00:00
parent fc6eab9edc
commit 577b14a702
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
model/supervised_finetuning/README.md
+7 -4
View File
@@ -42,14 +42,17 @@ your-model-name:
python trainer.py --configs defaults your-model-name
```
However, if the model of your choice doesn't have pad_token, eos_token, sep_token, you have to update utils.py `get_tokenizer` to use the right token.
However, if the model of your choice doesn't have pad_token, eos_token,
sep_token, you have to update utils.py `get_tokenizer` to use the right token.
## Deepspeed support
You can edit the configs/zero_config.json and use any stage you wish. The current config uses zero-stage 3. For more details on how to setup the config checkout [this page](https://www.deepspeed.ai/tutorials/zero/)
You can edit the configs/zero_config.json and use any stage you wish. The
current config uses zero-stage 3. For more details on how to setup the config
checkout [this page](https://www.deepspeed.ai/tutorials/zero/)
Once you are satisfy with your deepzero config, you can add --deepspeed flag at the end to trigger deepspeed
Once you are satisfy with your deepzero config, you can add --deepspeed flag at
the end to trigger deepspeed
```
python trainer.py --configs defaults your-model-name --deepspeed