Modifications to many skills

2026-05-09 19:36:03 +02:00
parent 5a30f4ca34
commit 44633ac6d6
62 changed files with 2213 additions and 345 deletions
@@ -1,6 +1,6 @@
 ---
 name: fine-tuning-with-trl
-description: "TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF."
+description: Fine-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.
 version: 1.0.0
 author: Orchestra Research
 license: MIT