x
This commit is contained in:
@@ -0,0 +1,26 @@
|
||||
from typing import List, Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class GenerateRequest(BaseModel):
|
||||
prompt: str
|
||||
max_tokens: int = Field(default=256, ge=1, le=4096)
|
||||
temperature: float = Field(default=0.7, ge=0.0, le=2.0)
|
||||
top_p: float = Field(default=0.95, gt=0.0, le=1.0)
|
||||
repetition_penalty: float = Field(default=1.0, ge=0.5, le=2.0)
|
||||
stop: Optional[List[str]] = None
|
||||
|
||||
|
||||
class GenerateResponse(BaseModel):
|
||||
text: str
|
||||
prompt: str
|
||||
model: str
|
||||
usage_prompt_tokens: int
|
||||
usage_completion_tokens: int
|
||||
usage_total_tokens: int
|
||||
|
||||
|
||||
class HealthResponse(BaseModel):
|
||||
status: str
|
||||
model: str
|
||||
Reference in New Issue
Block a user