---
base_model:
- DreadPoor/Casuar-9B-Model_Stock
- Triangle104/Gemmadevi-Stock-10B
- zelk12/MT-Gen6fix-gemma-2-9B
- TheDrummer/Gemmasutra-9B-v1.1
- allura-org/G2-9B-Aletheia-v1
- bunnycore/Gemma2-9B-TitanFusion
- lemon07r/Gemma-2-Ataraxy-v4d-9B
- TouchNight/gemma-2-Ifable-abliterated-9B-untied
library_name: transformers
tags:
- mergekit
- merge

---
This model was originally named "Gemma-Creative-9B-Base", but it has been renamed to "Gemma-9B-Chat" to better reflect its strengths in conversational AI.
I want to express my gratitude to the users who quantized and shared this model.
Unfortunately, due to the renaming, some existing links to the original model page may no longer work as expected.
I will list links to their quantized versions of this model under the GGUF section below.

# Chat Template

Gemma Instruct

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

```
{{- $system := "" }}
{{- range .Messages }}
{{- if eq .Role "system" }}
{{- if not $system }}{{ $system = .Content }}
{{- else }}{{ $system = printf "%s\n\n%s" $system .Content }}
{{- end }}
{{- continue }}
{{- else if eq .Role "user" }}<start_of_turn>user
{{- if $system }}
{{ $system }}
{{- $system = "" }}
{{- end }}
{{- else if eq .Role "assistant" }}<start_of_turn>model
{{- end }}
{{ .Content }}<end_of_turn>
{{ end }}<start_of_turn>model
```

# GGUF

Thank you [Otakadelic](https://huggingface.co/Otakadelic), [zelk12](https://huggingface.co/zelk12) and [mradermacher](https://huggingface.co/mradermacher) for creating the GGUF versions of this model.

  * Static quants - [mradermacher/Gemma-Creative-9B-Base-GGUF](https://huggingface.co/mradermacher/Gemma-Creative-9B-Base-GGUF)
  * Q8_0 quant - [Otakadelic/Gemma-Creative-9B-Base-Q8_0-GGUF](https://huggingface.co/Otakadelic/Gemma-Creative-9B-Base-Q8_0-GGUF)
  * Q6_K quant - [zelk12/Gemma-Creative-9B-Base-Q6_K-GGUF](https://huggingface.co/zelk12/Gemma-Creative-9B-Base-Q6_K-GGUF)

  * Weighted/imatrix quants [mradermacher/Gemma-Creative-9B-Base-i1-GGUF](https://huggingface.co/mradermacher/Gemma-Creative-9B-Base-i1-GGUF)

# Merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [zelk12/MT-Gen6fix-gemma-2-9B](https://huggingface.co/zelk12/MT-Gen6fix-gemma-2-9B) as a base.

### Models Merged

The following models were included in the merge:
* [DreadPoor/Casuar-9B-Model_Stock](https://huggingface.co/DreadPoor/Casuar-9B-Model_Stock)
* [Triangle104/Gemmadevi-Stock-10B](https://huggingface.co/Triangle104/Gemmadevi-Stock-10B)
* [TheDrummer/Gemmasutra-9B-v1.1](https://huggingface.co/TheDrummer/Gemmasutra-9B-v1.1)
* [allura-org/G2-9B-Aletheia-v1](https://huggingface.co/allura-org/G2-9B-Aletheia-v1)
* [bunnycore/Gemma2-9B-TitanFusion](https://huggingface.co/bunnycore/Gemma2-9B-TitanFusion)
* [lemon07r/Gemma-2-Ataraxy-v4d-9B](https://huggingface.co/lemon07r/Gemma-2-Ataraxy-v4d-9B)
* [TouchNight/gemma-2-Ifable-abliterated-9B-untied](https://huggingface.co/TouchNight/gemma-2-Ifable-abliterated-9B-untied)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: DreadPoor/Casuar-9B-Model_Stock
    parameters:
      density: 1.00
      weight: 1.00
  - model: Triangle104/Gemmadevi-Stock-10B
    parameters:
      density: 1.00
      weight: 1.00
  - model: TheDrummer/Gemmasutra-9B-v1.1
    parameters:
      density: 1.00
      weight: 1.00
  - model: TouchNight/gemma-2-Ifable-abliterated-9B-untied
    parameters:
      density: 1.00
      weight: 1.00
  - model: bunnycore/Gemma2-9B-TitanFusion
    parameters:
      density: 1.00
      weight: 1.00
  - model: lemon07r/Gemma-2-Ataraxy-v4d-9B
    parameters:
      density: 1.00
      weight: 1.00
  - model: allura-org/G2-9B-Aletheia-v1
    parameters:
      density: 0.75
      weight: 1.00
merge_method: ties
base_model: zelk12/MT-Gen6fix-gemma-2-9B
parameters:
  density: 1
  normalize: true
dtype: bfloat16
```