---
library_name: transformers
license: gemma
datasets:
- grimulkan/LimaRP-augmented
- LDJnr/Capybara
- TheSkullery/C2logs_Filtered_Sharegpt_Merged
- abacusai/SystemChat-1.1
- Hastagaras/FTTS-Stories-Sharegpt
tags:
- not-for-all-audiences
---

<div align="left">
  <img src="https://huggingface.co/Hastagaras/G2-Gemmoy-9B-MK.3-RP/resolve/main/gemmoy.jpg" width="850"/>
</div>

GGUF [STATIC](https://huggingface.co/mradermacher/Gemmoy-9B-G2-MK.3-GGUF)/[IMATRIX](https://huggingface.co/mradermacher/Gemmoy-9B-G2-MK.3-i1-GGUF) made available by [mradermacher](https://huggingface.co/mradermacher)

Chat Template:
```
<start_of_turn>user
{system}

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

ST Settings:
* [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) (The model was trained with diverse system prompts, make sure to write the system prompt based on your preference.)

<div align="left">
  <img src="https://huggingface.co/Hastagaras/G2-Gemmoy-9B-MK.3-RP/resolve/main/g3.png" width="850"/>
</div>

```
ls=LoraConfig(
    r = 128,
    target_modules = ['q_proj', 'down_proj', 'up_proj', 'o_proj', 'v_proj', 'gate_proj', 'k_proj'],
    lora_alpha = 32,
    lora_dropout = 0.1,
    bias = "none", 
    use_rslora = True,
)
```