[axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
on a 4x nvidia a40 gpu cluster.

the a40 GPU cluster has been graciously provided by [Arc Compute](https://www.arccompute.io/).
rank 8 lora merge

tune of mistral 7b

this is the format 

```
### System:

### Instruction:

### Response:
```

trained on subset of koishi

- asss
- dolly
- hh-rlhf
- wizard evol