Skill Explorer

Optimize preferences with implicit reward learning.

Audit OAuth/DPoP security

Efficient DPO for model alignment

Efficient LLM alignment without a reference model.

Automate GDPR/privacy reviews.

Fine-tune LLMs with Axolotl: YAML, LoRA, DPO & more.

Efficient LLM alignment without a reference model.

Efficient LLM alignment without a reference model.

Orchestrate LLM training runs on Tinker.

Fine-tune LLMs with Axolotl

Efficient LLM alignment without a reference model.

Align language models with human feedback.