feat(llama.cpp): guess model defaults from file (#2522)

* wip: guess informations from gguf file

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* update go mod

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Small fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Identify llama3

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Do not try to guess the name, as reading gguf files can be expensive

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Allow to disable guessing

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-06-08 22:13:02 +02:00 committed by GitHub
parent 23b3d22525
commit aae7ad9d73
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 139 additions and 13 deletions

View file

@ -289,6 +289,7 @@ func mergeRequestWithConfig(modelFile string, input *schema.OpenAIRequest, cm *c
config.LoadOptionThreads(threads),
config.LoadOptionContextSize(ctx),
config.LoadOptionF16(f16),
config.ModelPath(loader.ModelPath),
)
// Set the parameters for the language model prediction