Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

Intermediate layer accessor (NOTE: This is a WIP experiment). Inspired by DINO / DINOv2 interface

ViT weight initialization, original timm impl (for reproducibility)

Args: conversations (List[Dict[str, str]]): the conversations with a list of messages. An example is : [ {

Parameters: y: List of tuples representing the message and response pairs. Each message and response should be a string, which may be in

This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, he

Convert the conversation to gradio chatbot format.

Convert the conversation to OpenAI chat completion format.