Compute variance of tensor with masked values.

Transform the model name in each model_chunk in each pp stage into the name in inference engine

offload params of models that are not of current pp rank to cpu

pad the tokens such that the total length is a multiple of sp world size Args: unpad_tokens: (total_nnz, ...). Tokens after removing padd

Parses model's answer text into status dictionary. Args: answer_text: Text extracted from model's <answer> tags expected_name

Parses model's answer text into status dictionary. Args: answer_text: Text extracted from model's <answer> tags expected_name

Parses ground truth solution text into status dictionary. Args: solution_text: Formatted solution text from dataset Retu

Parses ground truth solution text into status dictionary. Args: solution_text: Formatted solution text from dataset Retu

Save final accuracy results to a file.

This function sets the global logging format and level. It will be called when import verl

Set pad_token_id to eos_token_id if it is None. Args: tokenizer (transformers.PreTrainedTokenizer): The tokenizer to be set.

Unfold the first n dims as new batch dim

Union two dict. Will throw an error if there is an item not the same object with the same key. Args: dict1: dict2: Returns:

Validate that equation only uses available numbers and each number once.

Performs comprehensive validation of response structure. Args: processed_str: Processed response string from the model R

Performs comprehensive validation of response structure. Args: processed_str: Processed response string from the model R

Compute Categorical entropy loss Args: logits: `(torch.Tensor)` shape: (bs, response_length, vocab_size) eos_mask: `(

Compute entropy when the logits are sharded in tp ranks Args: vocab_parallel_logits: (total_nnz, vocab_size // tp_size) Returns:

Write data to a JSONL file.

We will expand this function gradually based on the available datasets

We will expand this function gradually based on the available datasets

Note that we also return the raw_input_ids so that it can be combined with other chat template

Args: max_number: the maximum number allowed in the arithmetic sequence max_diff: the maximum diff. The actual commo

Character tokenizer for Hugging Face transformers. Args: characters (Sequence[str]): List of desired characters. Any character wh