Use it when your goal in extending the agent is clear and you can limit it to the data and actions it actually needs.
Directory → SKILL
SKILLoptionalHermes Optional Skills
Simpo
Reference-free preference alignment, simpler than DPO
Last registry verification2026-08-18v1.0.0Orchestra Research
What does it add to Hermes?
Reference-free preference alignment, simpler than DPO
Simpo is a skill related to extending the agent. It adds a capability or workflow to Hermes. The publisher description explains the intent, while granted permissions determine what it can actually do.
This plain-language explanation is based on the publisher description. The original text remains visible for verification.
Do not add it merely to experiment when Hermes already has a simpler path, or when you cannot review its source and permissions.
Best for users who want a repeatable way of working inside Hermes.
Start with non-sensitive data and a small task whose result can be verified and reversed.
Original publisher description
Reference-free preference alignment, simpler than DPO
Data source
This entry was indexed from Hermes Optional Skills. Our explanation interprets the type and domain without inventing a capability not present upstream.
Security review
The source is official or editorially reviewed, but you still need to review permissions and version compatibility.
Inspect, install, then test.
- 01Open the source
Match the publisher, license, and description to your need. Check the real update history.
- 02Review permissions and secrets
Never paste a secret value into this site. Use environment-variable names and grant the smallest scope.
- 03Copy setup only after review
The controls below copy text. They do not execute commands on your device.
- 04Test with a non-sensitive task
Inspect the visible tools, then exclude write or delete tools you do not need.
Review the command, then copy it.
hermes skills install simpoHermes Belarabi does not execute this command. Installation happens on your device and remains subject to Hermes scanning and your review.
Exactly what Hermes loads when this skill runs.
Reproduced from the official documentation. Read it before enabling the skill: this text becomes the agent's instructions.
Reference-free preference alignment, simpler than DPO.
Skill metadata
A lookup table. Do not read it all; find the row that applies to you.
| Source | Optional — install with hermes skills install official/mlops/simpo |
| Path | optional-skills/mlops/simpo |
| Version | 1.0.0 |
| Author | Orchestra Research |
| License | MIT |
| Dependencies | torch, transformers, datasets, trl, accelerate |
| Platforms | linux, macos, windows |
| Tags | Post-Training, SimPO, Preference Optimization, Alignment, DPO Alternative, Reference-Free, LLM Alignment, Efficient Training |
Reference: full SKILL.md
Explains the idea itself. Read it slowly; the later sections build on it.
Quick start
Ordered, practical steps. Run one and confirm it worked before moving on.
SimPO is a reference-free preference optimization method that outperforms DPO without needing a reference model.
Installation:
# Create environment
conda create -n simpo python=3.10 && conda activate simpo
# Install PyTorch 2.2.2
# Visit: https://pytorch.org/get-started/locally/
# Install alignment-handbook
git clone https://github.com/huggingface/alignment-handbook.git
cd alignment-handbook
python -m pip install .
# Install Flash Attention 2
python -m pip install flash-attn --no-build-isolationTraining (Mistral 7B):
ACCELERATE_LOG_LEVEL=info accelerate launch \
--config_file accelerate_configs/deepspeed_zero3.yaml \
scripts/run_simpo.py \
training_configs/mistral-7b-base-simpo.yamlCommon workflows
Settings you configure once. Change one at a time so you can see what each does.
Workflow 1: Train from base model (Mistral 7B)
Config (mistral-7b-base-simpo.yaml):
# Model
model_name_or_path: mistralai/Mistral-7B-v0.1
torch_dtype: bfloat16
# Dataset
dataset_mixer:
HuggingFaceH4/ultrafeedback_binarized: 1.0
dataset_splits:
- train_prefs
- test_prefs
# SimPO hyperparameters
beta: 2.0 # Reward scaling (2.0-10.0)
gamma_beta_ratio: 0.5 # Target margin (0-1)
loss_type: sigmoid # sigmoid or hinge
sft_weight: 0.0 # Optional SFT regularization
# Training
learning_rate: 5e-7 # Critical: 3e-7 to 1e-6
num_train_epochs: 1
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
# Output
output_dir: ./outputs/mistral-7b-simpoLaunch training:
accelerate launch --config_file accelerate_configs/deepspeed_zero3.yaml \
scripts/run_simpo.py training_configs/mistral-7b-base-simpo.yamlWorkflow 2: Fine-tune instruct model (Llama 3 8B)
Config (llama3-8b-instruct-simpo.yaml):
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
dataset_mixer:
argilla/ultrafeedback-binarized-preferences-cleaned: 1.0
beta: 2.5
gamma_beta_ratio: 0.5
learning_rate: 5e-7
sft_weight: 0.1 # Add SFT loss to preserve capabilities
num_train_epochs: 1
per_device_train_batch_size: 2
gradient_accumulation_steps: 4
output_dir: ./outputs/llama3-8b-simpoLaunch:
accelerate launch --config_file accelerate_configs/deepspeed_zero3.yaml \
scripts/run_simpo.py training_configs/llama3-8b-instruct-simpo.yamlWorkflow 3: Reasoning-intensive tasks (lower LR)
For math/code tasks:
model_name_or_path: deepseek-ai/deepseek-math-7b-base
dataset_mixer:
argilla/distilabel-math-preference-dpo: 1.0
beta: 5.0 # Higher for stronger signal
gamma_beta_ratio: 0.7 # Larger margin
learning_rate: 3e-7 # Lower LR for reasoning
sft_weight: 0.0
num_train_epochs: 1
per_device_train_batch_size: 1
gradient_accumulation_steps: 16When to use vs alternatives
Explains the idea itself. Read it slowly; the later sections build on it.
Use SimPO when:
- Want simpler training than DPO (no reference model)
- Have preference data (chosen/rejected pairs)
- Need better performance than DPO
- Limited compute resources
- Single-node training sufficient
Algorithm selection:
- SimPO: Simplest, best performance, no reference model
- DPO: Need reference model baseline, more conservative
- PPO: Maximum control, need reward model, complex setup
- GRPO: Memory-efficient RL, no critic
Use alternatives instead:
- OpenRLHF: Multi-node distributed training, PPO/GRPO
- TRL: Need multiple methods in one framework
- DPO: Established baseline comparison
Common issues
Settings you configure once. Change one at a time so you can see what each does.
Issue: Loss divergence
Reduce learning rate:
learning_rate: 3e-7 # Reduce from 5e-7Reduce beta:
beta: 1.0 # Reduce from 2.0Issue: Model forgets capabilities
Add SFT regularization:
sft_weight: 0.1 # Add SFT loss componentIssue: Poor preference separation
Increase beta and margin:
beta: 5.0 # Increase from 2.0
gamma_beta_ratio: 0.8 # Increase from 0.5Issue: OOM during training
Reduce batch size:
per_device_train_batch_size: 1
gradient_accumulation_steps: 16 # Maintain effective batchEnable gradient checkpointing:
gradient_checkpointing: trueAdvanced topics
Explains the idea itself. Read it slowly; the later sections build on it.
Loss functions: See references/loss-functions.md ↗ for sigmoid vs hinge loss, mathematical formulations, and when to use each.
Hyperparameter tuning: See references/hyperparameters.md ↗ for beta, gamma, learning rate selection guide, and model-size-specific recommendations.
Dataset preparation: See references/datasets.md ↗ for preference data formats, quality filtering, and custom dataset creation.
Hardware requirements
Explains the idea itself. Read it slowly; the later sections build on it.
- GPU: NVIDIA A100/H100 recommended
- VRAM:
- 7B model: 1× A100 40GB (DeepSpeed ZeRO-3)
- 8B model: 2× A100 40GB
- 70B model: 8× A100 80GB
- Single-node: DeepSpeed ZeRO-3 sufficient
- Mixed precision: BF16 recommended
Memory optimization:
- DeepSpeed ZeRO-3 (default config)
- Gradient checkpointing
- Flash Attention 2
Resources
Explains the idea itself. Read it slowly; the later sections build on it.
- Paper: https://arxiv.org/abs/2405.14734 (NeurIPS 2024)
- GitHub: https://github.com/princeton-nlp/SimPO
- Models: https://huggingface.co/princeton-nlp
- Alignment Handbook: https://github.com/huggingface/alignment-handbook