NilanE's picture
Update README.md
6f8e6ef verified
metadata
language:
  - en
  - ja
license: apache-2.0
tags:
  - llama
base_model: NilanE/tinyllama-relora-merge
datasets:
  - NilanE/ParallelFiction-Ja_En-100k

Trained for 2 epochs on NilanE/ParallelFiction-Ja_En-100k using QLoRA. CPO tune is in-progress.

Input should be 500-1000 tokens long. Make sure to set 'do_sample = False' if using HF transformers for inference, or otherwise set temperature to 0 for deterministic outputs.

Prompt format:

Translate this from Japanese to English:
### JAPANESE:
{source_text}
### ENGLISH:

Footnote:

This is an independantly-developed project. If anyone is interested in sponsoring further research please contact [email protected]. Questions about model usage can be asked in the disscussion tab.