Overwrite the `push_to_hub` method in order to force-add the tag "sft" when pushing the model on the Hub. Please refer to `~transform

A helper function to create random tensors on the desired `device` with the desired `dtype`. When passing a list of generators, you can seed each

Record training step statistics. Args: kl_coef (`float`): KL coefficient data (`dict`):

Resize and pad an image to a target resolution while maintaining aspect ratio. Args: image (PIL.Image.Image): The input image.

Run inference on ActivityNet QA DataSet using the Video-ChatGPT model. Args: args: Command-line arguments.

Run inference on ActivityNet QA DataSet using the Video-ChatGPT model. Args: args: Command-line arguments.

Collects the state dict and dump to disk.

Collects the state dict and dump to disk.

Light wrapper around accelerate's register_save_state_pre_hook which is run before saving state

Set RNG seeds for python's `random` module, numpy and torch

Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64.

Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64.

Split the tokens into query and response tokens.

Stack the values of a dict.

Cast all torch.tensors in dict to numpy arrays.

Step the environment forward one turn. Args: history (`TextHistory`): The history to step forward.

Run a PPO optimisation step given a list of queries, model responses, and rewards. Args: queries (List[`torch.LongTensor

Tokenize a single batch element. At this stage, we don't convert to PyTorch tensors yet; we just handle the truncation in case th

Filter a distribution of logits using top-k and/or nucleus (top-p) filtering. Args: logits: logits distribution shape (batch size, v

Train the model for a given number of epochs

Train one PPO minibatch Args: logprobs (`torch.FloatTensor`): Log probabilities of the model, shape [min

Returns true if all generated sequences contain any of the stop strings.