mirror of
https://github.com/mudler/LocalAI
synced 2026-05-04 05:48:43 +00:00
8ccf5b2044
**Description** This PR fixes #1013. It adds `draft_model` and `n_draft` to the model YAML config in order to load models with speculative sampling. This should be compatible as well with grammars. example: ```yaml backend: llama context_size: 1024 name: my-model-name parameters: model: foo-bar n_draft: 16 draft_model: model-name ``` --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|---|---|---|
| .. | ||
| bert | ||
| bloomz | ||
| falcon | ||
| gpt4all | ||
| langchain | ||
| llama | ||
| llama-stable | ||
| rwkv | ||
| transformers | ||