| license: bsd | |
| pipeline_tag: text2text-generation | |
| Used scraped data as input, ChatGPT result as output and limited types of instruction to fine-tune flan-t5-base. | |
| Used declare-lab repo. Refer to https://github.com/declare-lab/flan-alpaca | |
| Epoch set to 1 | |
| Input token max 512 | |
| Output token max 512 | |
| Trained on Free Google Colab T4 | |
| Training time ~ 40 mins |