Edit model card

gguf is here made available by Backyard AI

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/instruct

Downloads last month
11
Safetensors
Model size
9.24B params
Tensor type
FP16
·
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Hastagaras/Gemmoy-9B-MK.I

Quantizations
1 model