---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- sft
base_model: augmxnt/shisa-base-7b-v1
datasets:
- NilanE/ParallelFiction-Ja_En-100k
- mpasila/ParallelFiction-Ja_En-100k-alpaca
---
This is an ExLlamaV2 quantized model in 4bpw of [mpasila/JP-EN-Translator-1K-steps-7B-merged](https://huggingface.co/mpasila/JP-EN-Translator-1K-steps-7B-merged) using the default calibration dataset.

# Original Model card

Experimental model, may not perform that well. Dataset used is [a modified](https://huggingface.co/datasets/mpasila/ParallelFiction-Ja_En-100k-alpaca) version of [NilanE/ParallelFiction-Ja_En-100k](https://huggingface.co/datasets/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](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)