Creates a merge configuration for a linear merge of two models with specified weights.

Creates a merge configuration for a SLERP merge of a model with a base model.

Creates a merge configuration for a TIES merge of two models, with specified weights and densities.

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Creates a draft of a model card using the information available to the `Trainer`. Args: model_name (`str` or `None`, *op

Download video if not already present locally.

Compute the DPO loss for a batch of policy and reference model log probabilities. Args: chosen_logps (`torch.FloatTensor

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for E

Compute the Shannon entropy (in nats) for each row of *logits* without materialising the full soft-max in memory. The batch dimension is

r""" Extracts the shared prompt from a preference data example, where the prompt is implicit within both the chosen and rejected completions.

Compute the generalized Jensen-Shannon Divergence loss for knowledge distillation using F.kl_div. See Eq. (1) of https://huggingface.

Generates sequences from the language model backbone in a way that does not affect padding tokens. Args: lm_backbone (`torch.nn.Modu

r""" A simple wrapper around the `generate` method of the wrapped model. Please refer to the [`generate`](https://huggingface.co/docs/

Generate samples from the model and reference model for the given batch of inputs.

Generate samples from the model and reference model for the given batch of inputs.

Generate samples from the model and reference model for the given batch of inputs.

Generate samples from the model and reference model for the given batch of inputs.

Generate samples from the model and reference model for the given batch of inputs.

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D) scale_factor: the base fo

Returns the activation offloading context manager for the model. All but the last output Linear in every step will be offloaded. If acti

Compute the log probabilities of the given labels under the given logits. Args: logits: Logits of the model (unnormalized). Shape

Compute the log probabilities of the given labels under the given logits. Args: logits: Logits of the model (unnormalized). Shape

Returns the evaluation [`~torch.utils.data.DataLoader`]. Subclass of transformers.src.transformers.trainer.get_eval_dataloader to pr

Get the exponent cap of a value. This is used to cap the exponent of a value to avoid overflow. The formula is : log(value.dtype.max) E.g.

Computes element-wise mean and variance of the tensor across processes. Reference: https://github.com/OpenLMLab/MOSS-RLHF/blob/40b91eb2f2b71b

Returns a binary mask identifying tokens whose entropy exceeds a given quantile threshold. Args: entropies (`torch.Tensor`):

Return a list of indices so that each slice of `batch_size` consecutive indices correspond to elements of similar lengths. To do this, the in

r""" return a callable function that takes in an "instructions" dataset and returns a formatted dataset, based on the tokenizer apply chat tem

Define interpolation function

r""" Check if the example is in a conversational format (from/value). Note that this format isn't recommended. Prefer the ChatML format (role/

Compute the KTO loss for a batch of policy and reference model log probabilities. Args: policy_chosen_logps: Log

Create an instance from the content of `json_path`.

Log `logs` on the various objects watching training, including stored metrics. Args: logs (`dict[str, float]`):

Log `logs` on the various objects watching training, including stored metrics. Args: logs (`dict[str, float]`):

Log `logs` on the various objects watching training, including stored metrics. Args: logs (`dict[str, float]`):

Make dataset and collator for supervised fine-tuning.