Return a tensor with the input `shape` as a view into the 1-D data starting at `start_index`.

Slice the DataProto and return a new DataProto object. This is an improved version of direct slicing which returns a DataProtoItem.

Concat a list of DataProto. The batch is concatenated among dim=0. The meta_info is assumed to be identical and will use the first one.

Sleep engine to offload model weights and discard kv cache.

Pop a subset of the DataProto via `batch_keys` and `meta_info_keys` Args: batch_keys (list, optional): a list of strings indicati

move the batch to device Args: device (torch.device, str): torch device Returns: DataProto: the current Data

Create a tool instance. Args: instance_id: The instance id of the tool. Returns: The instance id of the tool

Open an application or file Args: app_or_file_name:str, the name of the application or file to open

Converts a sequence of ids in a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokeniz

Loads all episodes from disk.

Gets height of bounding box.

Gets height of bounding box.

Return current device id based on the device type. Returns: device index

Return the corresponding torch attribute based on the device type string. Returns: module: The corresponding torch device namespace, or to

Tap at screen coordinate (x, y).

Return a tensor with the input `shape` as a view into the 1-D data starting at `start_index`.

Select a subset of the DataProto via batch_keys and meta_info_keys Args: batch_keys (list, optional): a list of strings indicatin

If distributed is initialized, print only on rank 0.

Gets width of bounding box.

Gets width of bounding box.

Context manager for timing code execution. This utility function measures the execution time of code within its context and accumulates the t

Converts a string to a sequence of ids (integer), using the tokenizer and vocabulary. Args: text (`str`, `List[str]` or

Saves the results of an evaluation run. Args: data: The data for the run. completed_tasks: Metadata containing the tuple of completed

Split the batch among dim=0 into chunks. The meta_info is passed to each DataProto after split. Args: chunks (int): the number of

Closes the environment.

Closes the environment.

Repeat the batch data a specified number of times. Args: repeat_times (int): Number of times to repeat the data.

Saves the results of an evaluation run. Args: data: The data for the run. completed_tasks: Metadata containing the tuple of completed

Issues a generic adb command. Example: ~~~~~~~ issue_generic_request(['shell', 'ls'], env) # or issue_generic_request('shell ls', env)

Issues a generic adb command. Example: ~~~~~~~ issue_generic_request(['shell', 'ls'], env) # or issue_generic_request('shell ls', env)

End the current task with a success