gvij's picture
Update README.md
bbb138b
|
raw
history blame
399 Bytes
metadata
license: apache-2.0
datasets:
  - vicgalle/alpaca-gpt4
pipeline_tag: conversational
tags:
  - alpaca
  - gpt4
  - gpt-j
  - instruction
  - finetuning
  - lora
  - peft

GPT-J 6B model was finetuned on GPT-4 generations of the Alpaca prompts on MonsterAPI's no-code LLM finetuner, using LoRA for ~ 65,000 steps, taking over 87 hours on 1 A6000 GPU.


license: apache-2.0