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 mradermacher for creating the GGUF versions of this model.

Static quants - mradermacher/Gemma-9B-Base-GGUF

Merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using zelk12/MT2-Gen6-gemma-2-9B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: prithivMLmods/GWQ-9B-Preview2
    parameters:
      density: 1.00
      weight: 1.00
  - model: OpenMeditron/Meditron3-Gemma2-9B
    parameters:
      density: 1.00
      weight: 1.00
  - model: WiroAI/WiroAI-Finance-Gemma-9B
    parameters:
      density: 1.00
      weight: 1.00
  - model: AXCXEPT/EZO-Humanities-9B-gemma-2-it
    parameters:
      density: 1.00
      weight: 1.00
  - model: FuseAI/FuseChat-Gemma-2-9B-Instruct
    parameters:
      density: 1.00
      weight: 1.00
  - model: Rombo-Org/Rombo-LLM-V2.7-gemma-2-9b
    parameters:
      density: 1.00
      weight: 1.00
merge_method: ties
base_model: zelk12/MT2-Gen6-gemma-2-9B
parameters:
  density: 1
  normalize: true
dtype: bfloat16

Sorawiz
/

Gemma-9B-Base