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

## Training

[axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
on a 2x nvidia a40 gpu cluster.

the a40 GPU cluster has been graciously provided by [Arc Compute](https://www.arccompute.io/).

trained on subset of koishi commit 6e675d1 for one epoch

- asss
- dolly
- hh-rlhf
- wizard evol

## Base Model

rank 8 lora tune of mistralai/Mistral-7B-v0.1

## Prompting


```
### System:

### Instruction:

### Response:
```