---
datasets:
  - ewof/koishi-instruct-metharme
  - PygmalionAI/PIPPA
---

## Base Model

native fine tune of ludis/tsukasa-7b
gguf converted/quantized version of ludis/tsukasa-limarp-7b

## Prompting

The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.

The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.

## Benchmarks

trained on commit de693ac of the koishi dataset for 1 epoch as apart of ludis/tsukasa-7b

trained on commit 36fc235 of pippa metharme for 1 epoch as apart of ludis/tsukasa-7b

trained on Version 2023-09-03 of LimaRP (without ponyville, lolicit, all the fallen, and eka's portal subsets) for 2 epochs

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f38f3a89203d118da8b477/lvXgfxrb5v4ceEtZfVrYP.png)