Collect Commonly-used Few-shot Prompting Benchmark & Add Corresponding Software

[pfliu-nlp]

• summarize benchmarks from the following papers:
  • Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor
  • SELF-INSTRUCT: Aligning Language Model with Self Generated Instructions
  • InstructGPT
  • PAL: Program-aided Language Models
  • Scaling instruction-finetuned language models
  • OPT-IML : Scaling Language Model Instruction Meta Learning through the Lens of Generalization

List of Commonly-used Benchmark

• LMentry:
• BIG-bench: Hard:
• ....