README.md

metadata

base_model: Qwen/Qwen2.5-1.5B-Instruct
tags:
  - text-generation-inference
  - transformers
  - trl
  - grpo
license: apache-2.0
language:
  - en

For function calling purpose

config = {
  "rank": 8,
  "alpha": 16,
  "learning_rate": 2e-5,
  "target_modules": ["mlps"]
}