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.
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for mpasila/JP-EN-Translator-1K-Steps-V2-LoRA-7B
Base model
augmxnt/shisa-base-7b-v1