requirements.txt
requirements.txt
# 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