Files
LocalAI/gallery/gemma.yaml
Richard Palethorpe 969005b2a1 feat(gallery): Speed up load times and clean gallery entries (#9211)
* feat: Rework VRAM estimation and use known_usecases in gallery

Signed-off-by: Richard Palethorpe <io@richiejp.com>
Assisted-by: Claude:claude-opus-4-7[1m] [Claude Code]

* chore(gallery): regenerate gallery index and add known_usecases to model entries

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
2026-05-06 14:51:38 +02:00

43 lines
1.4 KiB
YAML

config_file: |
backend: llama-cpp
context_size: 8192
known_usecases:
- chat
- completion
mmap: true
stopwords:
- <|im_end|>
- <end_of_turn>
- <start_of_turn>
template:
chat: |
{{.Input }}
<start_of_turn>model
chat_message: |-
<start_of_turn>{{if eq .RoleName "assistant" }}model{{else}}{{ .RoleName }}{{end}}
{{ if .FunctionCall -}}
{{ else if eq .RoleName "tool" -}}
{{ end -}}
{{ if .Content -}}
{{.Content -}}
{{ end -}}
{{ if .FunctionCall -}}
{{toJson .FunctionCall}}
{{ end -}}<end_of_turn>
completion: |
{{.Input}}
function: |
<start_of_turn>system
You have access to functions. If you decide to invoke any of the function(s),
you MUST put it in the format of
{"name": function name, "parameters": dictionary of argument name and its value}
You SHOULD NOT include any other text in the response if you call a function
{{range .Functions}}
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
{{end}}
<end_of_turn>
{{.Input -}}
<start_of_turn>model
name: gemma