Preference Alignment skills
Free agent skills tagged preference alignment, ready to install into any SKILL.md-compatible agent.
3 skills
Fine-Tuning with TRL
davila7
Align language models with human preferences using reinforcement learning.
Developer ToolsintermediatePython · Shell30.2k repo
TRL Fine-Tuning
nousresearch
Align language models with human preferences using TRL.
Developer ToolsintermediatePython · Shell228.5k repo
Simple Preference Optimization
nousresearch
Optimize preferences without reference models.
Developer ToolsintermediatePython · Shell228.5k repo