Experimental model, may not perform that well. Dataset used is a modified version of NilanE/ParallelFiction-Ja_En-100k.
Next version should be better (I'll use a GPU with more memory since the dataset happens to use pretty long samples).
Prompt format: Alpaca
Below is a translation task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{}
### Input:
{}
### 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.