README.md

---
library_name: transformers
license: gemma
---
[gguf is here](https://huggingface.co/backyardai/Gemmoy-9B-MK.I-GGUF) made available by [Backyard AI](https://huggingface.co/backyardai)

first try finetuning gemma 9b instruct. my data was a mess, i only noticed that after training, so this is just a test run

i formatted the dataset like below
```
<start_of_turn>user
{system}

{prompt}<end_of_turn>
<start_of_turn>model
{response}<end_of_turn>
<start_of_turn>user
{prompt}<end_of_turn>
<start_of_turn>model
{response}<end_of_turn>

and so on...
```
settings for st: [context](https://huggingface.co/Hastagaras/Gemmoy-9B-MK.I/blob/main/Gemma2%20C.json)/[instruct](https://huggingface.co/Hastagaras/Gemmoy-9B-MK.I/blob/main/Gemma2%20I.json)