metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - mistral
  - trl
base_model: augmxnt/shisa-base-7b-v1
datasets:
  - NilanE/ParallelFiction-Ja_En-100k
  - mpasila/ParallelFiction-Ja_En-100k-alpaca
library_name: peft

This was trained on the updated version of the previous dataset, and it appears to have improved it a little bit. Further training seems to reduce accuracy of the model.

Dataset used is a modified version of NilanE/ParallelFiction-Ja_En-100k.

Prompt format: Alpaca

Below is a translation task. Write a response with the translation.

### Instruction:
{}

### Response:
{}

Uploaded model

Developed by: mpasila
License: apache-2.0
Finetuned from model : augmxnt/shisa-base-7b-v1

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