| """Hugging Face configuration for MiniCPM-RobotTrack.""" | |
| from typing import Any, Dict, Optional | |
| from transformers.configuration_utils import PretrainedConfig | |
| class MiniCPMRobotTrackConfig(PretrainedConfig): | |
| """Configuration for the MiniCPM-RobotTrack trajectory policy.""" | |
| model_type = "minicpm_robottrack" | |
| has_no_defaults_at_init = True | |
| def __init__( | |
| self, | |
| backbone_config: Optional[Dict[str, Any]] = None, | |
| vision_feature_dim: int = 1536, | |
| history_frames: int = 31, | |
| coarse_tokens_per_frame: int = 4, | |
| fine_tokens_current_frame: int = 64, | |
| num_waypoints: int = 8, | |
| action_dim: int = 3, | |
| max_text_tokens: int = 128, | |
| max_time_steps: int = 4096, | |
| trajectory_dropout: float = 0.4, | |
| xy_scale: float = 2.0, | |
| use_tanh_actions: bool = True, | |
| backbone_dtype: str = "bfloat16", | |
| **kwargs: Any, | |
| ) -> None: | |
| self.backbone_config = dict(backbone_config or {}) | |
| self.vision_feature_dim = int(vision_feature_dim) | |
| self.history_frames = int(history_frames) | |
| self.coarse_tokens_per_frame = int(coarse_tokens_per_frame) | |
| self.fine_tokens_current_frame = int(fine_tokens_current_frame) | |
| self.num_waypoints = int(num_waypoints) | |
| self.action_dim = int(action_dim) | |
| self.max_text_tokens = int(max_text_tokens) | |
| self.max_time_steps = int(max_time_steps) | |
| self.trajectory_dropout = float(trajectory_dropout) | |
| self.xy_scale = float(xy_scale) | |
| self.use_tanh_actions = bool(use_tanh_actions) | |
| self.backbone_dtype = str(backbone_dtype) | |
| self._validate_robot_track_config() | |
| super().__init__(**kwargs) | |
| def _validate_robot_track_config(self) -> None: | |
| if not self.backbone_config: | |
| raise ValueError("backbone_config must contain the bundled MiniCPM configuration") | |
| if self.vision_feature_dim <= 0: | |
| raise ValueError("vision_feature_dim must be positive") | |
| if self.history_frames < 0: | |
| raise ValueError("history_frames cannot be negative") | |
| for name, value in ( | |
| ("coarse_tokens_per_frame", self.coarse_tokens_per_frame), | |
| ("fine_tokens_current_frame", self.fine_tokens_current_frame), | |
| ): | |
| side = int(round(value**0.5)) if value > 0 else 0 | |
| if side * side != value: | |
| raise ValueError(f"{name} must be a positive square number") | |
| if self.num_waypoints < 2: | |
| raise ValueError("num_waypoints must be at least 2") | |
| if self.action_dim != 3: | |
| raise ValueError("actions must use [x, y, yaw] format") | |
| if self.max_text_tokens <= 0 or self.max_time_steps <= 0: | |
| raise ValueError("token and time limits must be positive") | |
| if not 0.0 <= self.trajectory_dropout < 1.0: | |
| raise ValueError("trajectory_dropout must be in [0, 1)") | |
| if self.xy_scale <= 0.0: | |
| raise ValueError("xy_scale must be positive") | |