Files
NexQuant/rdagent/scenarios/general_model/scenario.py
T
Yuante Li d6ce70b551 feat: add RD-Agent-Quant scenario (#838)
* fix model input shape bug and costeer_model bug

* fix a bug

* fix a bug in docker result extraction

* a system-level optimization

* add a filter of stdout

* update

* add stdout to model

* model training_hyperparameters update

* quant scenario

* update some quant settings

* llm choose action

* Thompson Sampling Bandit for action choosing

* refine both scens

* add trace messages for quant scen

* fix some bugs

* fix some bugs

* update

* update

* update

* fix

* fix

* fix

* update for merge

* fix ci

* fix some bugs

* fix ci

* fix ci

* fix ci

* fix ci

* refactor

* default qlib4rdagent local env downloading

* fix ci

* fix ci

* fix a bug

* fix ci

* fix: align all prompts on template (#908)

* use template to render all prompts

* fix CI

---------

Co-authored-by: Xu Yang <xuyang1@microsoft.com>

* add fin_quant in cli

* fix a bug

* fix ci

* fix some bugs

* refactor

* remove the columns in hypothesis if no value generated in this column

* fix a bug

* fix ci

* fix conda env

* add qlib gitignore

* remove existed qlib folder & install torch in qlib conda

* fix workspace ui in feedback

* align model config in coder and runner in docker or conda

* fix CI

* fix CI

---------

Co-authored-by: Xu Yang <peteryang@vip.qq.com>
Co-authored-by: Xu Yang <xuyang1@microsoft.com>
2025-05-29 16:16:51 +08:00

53 lines
1.6 KiB
Python

from copy import deepcopy
from rdagent.core.experiment import Task
from rdagent.core.scenario import Scenario
from rdagent.utils.agent.tpl import T
class GeneralModelScenario(Scenario):
def __init__(self) -> None:
super().__init__()
self._background = deepcopy(T(".prompts:general_model_background").r())
self._output_format = deepcopy(T(".prompts:general_model_output_format").r())
self._interface = deepcopy(T(".prompts:general_model_interface").r())
self._simulator = deepcopy(T(".prompts:general_model_simulator").r())
self._rich_style_description = deepcopy(T(".prompts:general_model_rich_style_description").r())
@property
def background(self) -> str:
return self._background
@property
def source_data(self) -> str:
raise NotImplementedError("source_data of GeneralModelScenario is not implemented")
@property
def output_format(self) -> str:
return self._output_format
@property
def interface(self) -> str:
return self._interface
@property
def simulator(self) -> str:
return self._simulator
@property
def rich_style_description(self) -> str:
return self._rich_style_description
def get_scenario_all_desc(
self, task: Task | None = None, filtered_tag: str | None = None, simple_background: bool | None = None
) -> str:
return f"""Background of the scenario:
{self.background}
The interface you should follow to write the runnable code:
{self.interface}
The output of your code should be in the format:
{self.output_format}
The simulator user can use to test your model:
{self.simulator}
"""