simpo-training
From the author
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
Install
npx skills add KalarisLabs/research-agent-skills --skill simpo-training -a claude-code
Installs to .claude/skills/simpo-training/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
No warnings.
Why 82
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- simpo-losscxcscmu/SkillLearnBenchSimPO (Simple Preference Optimization) loss computation for LLM alignment without a reference model.Other★ 91
- preference-optimizationwshobson/agentsAlign a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosing between preference-optimization methods, or when a DPO run needs hyperparameters or debugging.Engineering★ 41.7K
- fine-tuning-with-trlKalarisLabs/research-agent-skillsFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.Other★ 61
- evo-simpo-code-reproductionOpenLAIR/OpenSkillImplements the SimPO (Simple Preference Optimization) loss function and handles environment setup, execution, and result saving for code reproduction tasks.Engineering★ 97
- huggingface-trlcxcscmu/SkillLearnBenchUsing Hugging Face TRL library for building custom trainers for Preference Optimization methods like DPO, SimPO, etc.Other★ 91
- run2_simpo-losscxcscmu/SkillLearnBenchComplete implementation of the SimPO (NeurIPS 2024) loss function with all variants and edge cases - use when reproducing SimPO or implementing reference-free preference optimization.Other★ 91
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in