Get the index (e.g. 2) from the prediction (e.g. 'C')

inject lora into model, and returns lora parameter groups.

inject lora into model, and returns lora parameter groups.

Converts a loaded safetensor file that contains a set of module Loras into Parameters and other information Output is a dictionary of {

Converts a loaded safetensor file that contains a set of module Loras into Parameters and other information Output is a dictionary of {

Helper that gets a list of the model's attention modules. Each module has a `bias` buffer used for causal masking. The Prefix LM conv

Create gt, dt which are list of anns/dets. If use_cats is true only anns/dets corresponding to tuple (img_id, cat_id) will be used.

Tokenize a list of strings.

Accumulate per image evaluation results and store the result in self.eval.

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means y

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

Converts the Lora from multiple pytorch .pt files into a single safetensor file. modelmap is a dictionary of { "module name": (pytor

Converts the Lora from multiple pytorch .pt files into a single safetensor file. modelmap is a dictionary of { "module name": (pytor

Run per image evaluation on given images and store results (a list of dict) in self.eval_imgs.

Returns a list of images with mask on the face parts.

Returns a list of images with mask on the face parts.

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

Get the index (e.g. 2) from the prediction (e.g. 'C')

Get the index (e.g. 2) from the prediction (e.g. 'C')