обновлен формат генерации датасета

This commit is contained in:
Даниил Грабарь
2026-10-22 10:07:05 +10:00
parent 9e551a2ca9
commit 1059b47978
29 changed files with 2230 additions and 468 deletions
+1 -30
View File
@@ -1,7 +1,6 @@
from pathlib import Path
from typing import Annotated, Literal
import yaml
from pydantic import BaseModel, ConfigDict, Field
@@ -31,36 +30,8 @@ LLMConfig = Annotated[
# Generation
class GenerationConfig(ConfigModel):
temperature: float = Field(default=.7,
temperature: float | None = Field(default=None,
ge=.0,
le=2.0)
max_tokens: int = Field(default=4096,
gt=0)
# Runtime
class RuntimeConfig(ConfigModel):
concurrency: int = Field(ge=1, default=1)
# Prompts
class PromptsConfig(ConfigModel):
instructions: str
system: str
user: str
# Application
class AppConfig(ConfigModel):
llm: LLMConfig
generation: GenerationConfig = GenerationConfig()
runtime: RuntimeConfig = RuntimeConfig()
prompts: PromptsConfig
# Loader
def load_config(path: str | Path = "config.yaml") -> AppConfig:
path = Path(path)
with path.open("r", encoding="utf-8") as file:
data = yaml.safe_load(file)
return AppConfig.model_validate(data)