huggingface

Modules:

Name	Description
data_collator
tokenization_utils
transform

Classes:

Name	Description
SGHFLM	Eval harness model class for evaluating Stained Glass Transforms.

SGHFLM

Bases: HFLM

Eval harness model class for evaluating Stained Glass Transforms.

Parameters:

Name	Type	Description	Default
transform_model_path	str	The path to the Stained Glass Transform.	required
apply_stainedglass	bool	Whether to apply the Stained Glass Transform.	required
args	Any	Additional arguments to pass to the parent class.	()
kwargs	Any	Additional keyword arguments to pass to the parent class.	{}

Methods:

Name	Description
apply_chat_template	Return the context from the chat history because the template is applied in the _encode_pair method.
tok_batch_encode	Encode a batch of strings into input ids and attention masks.

apply_chat_template

apply_chat_template(chat_history: list[dict[str, str]]) -> str

Return the context from the chat history because the template is applied in the _encode_pair method.

Parameters:

Name	Type	Description	Default
chat_history	list[dict[str, str]]	The chat history.	required

Raises:

Type	Description
ValueError	If the chat history is not a single user message.

Returns:

Type	Description
str	The context.

tok_batch_encode

tok_batch_encode(strings: list[str], padding_side: str = 'left', left_truncate_len: int | None = None, truncation: bool = False) -> tuple[torch.Tensor, torch.Tensor]

Encode a batch of strings into input ids and attention masks.

Parameters:

Name	Type	Description	Default
strings	list[str]	The list of strings to encode.	required
padding_side	str	The side to pad the sequences.	'left'
left_truncate_len	int | None	The length to truncate the left side of the sequences.	None
truncation	bool	Whether to truncate the sequences.	False

Returns:

Type	Description
tuple[torch.Tensor, torch.Tensor]	A tuple of input embeddings and attention masks if apply_stainedglass is True, otherwise the input ids and attention masks.