metadata

library_name: peft
base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.4
license: apache-2.0
language:
  - en

This model was trained by me on the Alpaca dataset and the others.

Benchmarks

Tests were carried out on this model and the original model for the purpose of accurate data.

boolq - 62.57 (original - 57.31)

truthfulqa_mc1 - 24.26 (original - 23.01)

ARC_e - 53.07 (original - 54.04)

WinoGrande - 57.7 (original - 58.8)

Average - 49.7 (original - 48.29)