mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-20 18:45:00 +00:00
chore(autogptq): drop archived backend (#5214)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
8abecb4a18
commit
61cc76c455
23 changed files with 5 additions and 322 deletions
|
@ -268,14 +268,6 @@ yarn_ext_factor: 0
|
|||
yarn_attn_factor: 0
|
||||
yarn_beta_fast: 0
|
||||
yarn_beta_slow: 0
|
||||
|
||||
# AutoGPT-Q settings, for configurations specific to GPT models.
|
||||
autogptq:
|
||||
model_base_name: "" # Base name of the model.
|
||||
device: "" # Device to run the model on.
|
||||
triton: false # Whether to use Triton Inference Server.
|
||||
use_fast_tokenizer: false # Whether to use a fast tokenizer for quicker processing.
|
||||
|
||||
# configuration for diffusers model
|
||||
diffusers:
|
||||
cuda: false # Whether to use CUDA
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue