mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-21 21:54:52 -04:00
Ettore Di Giacinto
c9acb41903
Let the model-provided tokenizer template format Gemma conversations instead of maintaining a shared inline prompt template. Assisted-by: Codex:gpt-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
15 lines
281 B
YAML
15 lines
281 B
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:
|
|
use_tokenizer_template: true
|
|
name: gemma
|