fine-tuning-with-trl

Originally fromovachiever/droid-tings
Installation
SKILL.md

TRL - Transformer Reinforcement Learning

Quick start

TRL provides post-training methods for aligning language models with human preferences.

Installation:

pip install trl transformers datasets peft accelerate

Supervised Fine-Tuning (instruction tuning):

from trl import SFTTrainer

trainer = SFTTrainer(
    model="Qwen/Qwen2.5-0.5B",
    train_dataset=dataset,  # Prompt-completion pairs
)
Related skills

More from kiterlin/intelligent-detection-system

Installs
32
GitHub Stars
1
First Seen
Apr 21, 2026