liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
26 lines
602 B
Plaintext
26 lines
602 B
Plaintext
# 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
|
|
|