return the Enum class used to enforce list of choices

Use the tool.

Separate the kwargs from the arguments that we support inside `supported_args` and the ones that we don't.

subclass must implement

subclass must implement

This function is only used for single example inference, required to set `create_local_llm` as True.

Find the python print node in the tree.body. Args: body (List[ast.AST]): The body of the AST Returns: List[int]: The index o

process output from vllm e.g., outputs = llm.generate(prompts, sampling_params) for output in outputs: step_gener

This function is used to extract solution from a built tree. It is mainly used for MCTS, but also works for saved tree from step_beam.

Sanitize input to the python REPL. Remove whitespace, backtick & python (if llm mistakes python console as terminal) Args: query: The

process output from vllm e.g., prompts = tree.create_prompt(is_value_only=True) outputs = llm.generate(prompts, sampling_param

process output from vllm e.g., prompts = tree.create_prompt(is_value_only=True) outputs = llm.generate(prompts, sampling_param

r""" Initializes the model. Args: pretrained_model (`transformers.PreTrainedModel`): The model to wrap. I