theroyallab/tabbyAPI
1
0
Fork 0
mirror of https://github.com/theroyallab/tabbyAPI.git synced 2026-03-14 15:57:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

OAI: Fix model parameter placement

Browse Source 
Accidentally edited the Model Card parameters vs the model load request
ones.

Signed-off-by: kingbri <bdashore3@proton.me>
This commit is contained in:
kingbri
2023-12-17 14:36:28 -05:00
parent 1d0bdfa77c
commit 70fbee3edd
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
OAI/types/model.py
View File

@@ -6,7 +6,7 @@ from gen_logging import LogConfig
class ModelCardParameters(BaseModel):
max_seq_len: Optional[int] = 4096
rope_scale: Optional[float] = 1.0
rope_alpha: Optional[float] = None
rope_alpha: Optional[float] = 1.0
prompt_template: Optional[str] = None
cache_mode: Optional[str] = "FP16"
draft: Optional['ModelCard'] = None
@@ -35,7 +35,7 @@ class ModelLoadRequest(BaseModel):
gpu_split_auto: Optional[bool] = True
gpu_split: Optional[List[float]] = Field(default_factory=list)
rope_scale: Optional[float] = 1.0
rope_alpha: Optional[float] = 1.0
rope_alpha: Optional[float] = None
no_flash_attention: Optional[bool] = False
# low_mem: Optional[bool] = False
cache_mode: Optional[str] = "FP16"