Function that computes advantages and returns from rewards using REINFORCE. REINFORCE uses cumulative returns without the GAE (Genera

r""" Only applies gradient checkpointing to trainable layers.

r""" Gets the attributes of the datasets.

r""" Returns an iterator over all elements with their names.

r""" Gets scores after evaluation.

r""" Gets id by element.

r""" Computes the number of special tokens per image.

r""" Generates model's responses given queries.

r""" Returns a logger with the specified name. It it not supposed to be accessed externally.

r""" Gets the model path according to the model name.

r""" Computes the patch size of the vit.

r""" Gets the peak memory usage for the current device (in Bytes).

Return flatten list of scores for each (query,doc) pair Args: query_list: List of N queries doc_list: Nested list of

r""" Computes scores using given reward model. Both inputs and outputs are put on CPU.

r""" Gets reward scores from the API server.

r""" Gets the sequnce lengths in the current batch. e.g. ```python # input [ [1, 1, 2, 2, 2, 0], [1, 2, 2, 3, 3,

r""" Gets the callback for logging to SwanLab.

r""" Gets the template name if the model is a chat model.

r""" Gets current date and time.

r""" Gets training infomation for monitor.

r""" Gets the peft model for the pretrained model with unsloth. Used in training.

r""" Get the vision_feature_select_strategy.

r""" Judges if the model is a vision language model.

r""" An efficient greedy algorithm with binary search for the knapsack problem.

r""" Checks if the path has a tokenized dataset.

Returns a character hash code of arbitrary Python objects.

r""" Infers the optimal dtype according to the model_dtype and device compatibility.

r""" Initializes the adapters. Support full-parameter, freeze and LoRA training. Note that the trainable parameters must be cast to floa

r""" Checks if the GPU or NPU is available.

Walk through all files located under a root path.

Walk through all files located under a root path.

Load data from input JSON file.

r""" Loads dataset_info.json.

r""" Loads peft model with unsloth. Used in both training and inference.

r""" Optionally loads pretrained model with unsloth. Used in training.