jalr/tabbyAPI-ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Model: Remove num_experts_per_token

Browse source 
This shouldn't even be an exposed option since changing it always
breaks inference with the model. Let the model's config.json handle
it.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
This commit is contained in:
kingbri 2025-03-19 11:52:10 -04:00
parent 698d8339cb
commit 79f9c6e854
6 changed files with 0 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

2
endpoints/core/types/model.py
View file

@ -22,7 +22,6 @@ class ModelCardParameters(BaseModel):
chunk_size: Optional[int] = 2048
prompt_template: Optional[str] = None
prompt_template_content: Optional[str] = None
num_experts_per_token: Optional[int] = None
use_vision: Optional[bool] = False
# Draft is another model, so include it in the card params
@ -114,7 +113,6 @@ class ModelLoadRequest(BaseModel):
chunk_size: Optional[int] = None
prompt_template: Optional[str] = None
vision: Optional[bool] = None
num_experts_per_token: Optional[int] = None
# Non-config arguments
draft_model: Optional[DraftModelLoadRequest] = Field(