simpo
An optional Hermes Agent skill, credited to Orchestra Research, for aligning a language model to preference data with SimPO, a method that needs no reference model.
What the skill teaches
An optional Hermes Agent skill, credited to Orchestra Research, for aligning a language model to preference data with SimPO, a method that needs no reference model. It walks the agent through a Python 3.10 environment, PyTorch, Hugging Face's alignment-handbook and Flash Attention 2, a YAML training config and a launch with accelerate and DeepSpeed ZeRO-3. It gives settings for a Mistral 7B base model, a Llama 3 8B instruct model and reasoning tasks, explains the main hyperparameters and their ranges, and covers diverging loss, forgotten skills and memory errors. It expects chosen and rejected answer pairs and recommends A100 or H100 GPUs.
Capabilities
- Set up a SimPO training environment
- Write a SimPO training config
- Tune SimPO hyperparameters
- Troubleshoot preference training runs
About
- Publisher
- Nous Research
- Tool
- Hugging Face
Install
The project doesn't document install steps that we could confirm. See the project's own instructions
What's inside
- references/datasets.md
- references/hyperparameters.md
- references/loss-functions.md
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
Details
| Fact | Value | Source |
|---|---|---|
| Type | Skill | |
| Tool | Hugging Face | |
| Publisher | Nous Research | source |
| Official status | Community (not published by the tool's vendor) | source |
| Needs an API key or sign-in | Not stated in its documentation | |
| Includes scripts | No | source |
| Platforms | Linux, macOS, Windows | source |
| AI clients | Not stated in its documentation | |
| Licence | MIT | source |
| Pricing | Not stated in its documentation | |
| Activity | Last commit Nov 11, 2026262,606 GitHub starsDownload data not available (not on npm or PyPI) | source |
| Links | Repository Website |
Sources
- Skill file (SKILL.md)github.com/nousresearch/hermes-agent · Backs: Licence, Official status, PlatformsNov 17, 2026
- GitHub repositorygithub.com/nousresearch/hermes-agent · Backs: Publisher, Activity, LicenceNov 11, 2026
- GitHub API recordgithub.com/nousresearch/hermes-agent · Backs: Includes scriptsNov 17, 2026
- Skill file (SKILL.md)github.com/NousResearch/hermes-agentNov 10, 2026
- Folder in the repository (simpo)github.com/NousResearch/hermes-agent · Backs: Includes scriptsNov 10, 2026