simpo-training

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.

[Post-TrainingSimPOPreferenceOptimization

PoorRican

0

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

[Post-TrainingReinforcementLearningGRPO

PoorRican

0

fine-tuning-with-trl

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

[Post-TrainingTRLReinforcementLearning

PoorRican

0

axolotl

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

[Fine-TuningAxolotlLLMLoRA

PoorRican

0