Qra-13b-instruct / README.md
TeeZee's picture
Update README.md
c528ae0 verified
metadata
base_model: OPI-PG/Qra-13b
language:
  - en
license: llama2
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
datasets:
  - Lbuk/alpaca_data_pl.json

Uploaded model

  • Trained only on Q->A, not chat
  • Alpaca prompt template with Input
  • Developed by: TeeZee
  • License: llama2
  • Finetuned from model : OPI-PG/Qra-13b

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.