am_llama3_alpaca / README.md
simonbutt's picture
Trained with Unsloth
d075ea4 verified
|
raw
history blame
664 Bytes
metadata
language:
  - en
  - am
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
base_model: unsloth/llama-3-8b-bnb-4bit
datasets:
  - iocuydi/amharic-alpaca

Llama3 Amharic Alpaca Tuned

Llama3 8B instruction tuned on an amharic translated alpaca dataset.

Very token inefficient.

  • Developed by: simonbutt
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-8b-bnb-4bit