# Prompt Distillation Requirements # # Core dependencies for reproducing the tinker prompt distillation experiment # vLLM for efficient inference (data generation with teacher model) vllm>=0.6.0 # Progress bars and utilities tqdm>=4.65.0 numpy>=1.24.0 # Training framework - Hugging Face TRL (Transformers Reinforcement Learning) trl>=0.9.0 peft>=0.11.0 accelerate>=0.28.0 transformers>=4.36.0 datasets>=2.14.0 torch>=2.0.0 # Logging and monitoring wandb>=0.15.0 # Note: TRL provides a simple, well-documented API for supervised fine-tuning # with LoRA and works directly with JSONL data format