r""" Computes the sum log probabilities of the labels under given logits if loss_type is not IPO, ORPO or SimPO. Otherwise the averag

r""" Returns the number of trainable parameters and number of all parameters in the model.

r""" Extracts tool message.

r""" Finds all available modules to apply lora or galore.

r""" Runs forward pass and computes the log probabilities.

r""" Computes the log probabilities of the given labels under the given logits. Returns: logps: A tensor of shape (batch_size,) conta

r""" Gets the path to user config.

r""" Freezes vision tower and language model for VLM full/freeze tuning.

r""" Builds batched multimodal inputs for VLMs.

r""" Gets a list of scores of the reward model.

Return the result of gcd() or lcm(), as UnevaluatedExpr f: str - name of function ("gcd" or "lcm") args: List[Expr] - list of function a

r""" Loads saved arguments.

r""" Loads value head parameters from Hugging Face Hub or local disk. Returns: dict with keys `v_head.summary.weight` and `v_head.summary.bia

Exact match of math if and only if: 1. numerical equal: both can convert to float and are equal 2. symbolic equal: both can convert to sy

r""" Replaces the default/reward modules in the model. The model is already unwrapped.

r""" Saves arguments.

r""" EMA implementation according to TensorBoard.

r""" Configures root logger using a stdout stream handler with an explicit format.