def generate2()

in muse/modeling_transformer_v2.py [0:0]

• 22 lines of code
• 2 McCabe index (conditional complexity)

    def generate2(
        self,
        encoder_hidden_states: torch.FloatTensor,
        cond_embeds: torch.FloatTensor,
        micro_conds: torch.FloatTensor,
        empty_embeds: torch.FloatTensor,
        empty_cond_embeds: torch.FloatTensor,
        input_ids: torch.LongTensor = None,
        negative_embeds: torch.FloatTensor = None,
        negative_cond_embeds: torch.FloatTensor = None,
        temperature=1.0,
        timesteps=18,  # ideal number of steps is 18 in maskgit paper
        guidance_scale=0,
        guidance_schedule=None,
        noise_schedule=cosine_schedule,
        generator: torch.Generator = None,
        return_intermediate=False,
        seq_len=None,
        use_tqdm=None,
        # Legacy: kept for compatibility with pipeline
        topk_filter_thres=None,
        noise_type=None,
        predict_all_tokens=None,