tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

feat(example): add gpt-oss-safeguard docs (#3243)

Browse Source 
* feat(example): add gpt-oss-safeguard docs

* fix: add doc on reasoning_effort
This commit is contained in:
NanoCode012
2025-11-04 07:39:21 +07:00
committed by GitHub
parent 26f05b6008
commit 01a346d86a
2 changed files with 79 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/gpt-oss/README.md
View File

@@ -2,6 +2,8 @@
[GPT-OSS](https://huggingface.co/collections/openai/gpt-oss-68911959590a1634ba11c7a4) are a family of open-weight MoE models trained by OpenAI, released in August 2025. There are two variants: 20B and 120B.
In October 2025, OpenAI released safeguard models built upon GPT-OSS called [GPT-OSS-Safeguard](https://huggingface.co/collections/openai/gpt-oss-safeguard). They use the same architecture, so the same examples below can be re-used.
This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
## Getting started
@@ -64,6 +66,16 @@ axolotl merge-sharded-fsdp-weights examples/gpt-oss/gpt-oss-120b-fft-fsdp2-offlo
mv ./outputs/gpt-oss-out/merged/* ./outputs/gpt-oss-out/
```
### How to set reasoning_effort in template?
The harmony template has a feature to set the `reasoning_effort` during prompt building. The default is `medium`. If you would like to adjust this, you can add the following to your config:
```yaml
chat_template_kwargs:
reasoning_effort: "high" # low | medium | high
```
Currently, this applies globally. There is no method to apply per sample yet. If you are interested in adding this, please feel free to create an Issue to discuss.
### Inferencing your fine-tuned model