hub / github.com/FunAudioLLM/ThinkSound / forward

Method forward

ThinkSound/models/transformer_layers.py:230–256 · view source on GitHub ↗

(self, latent: torch.Tensor, clip_f: torch.Tensor, text_f: torch.Tensor,
                global_c: torch.Tensor, extended_c: torch.Tensor, latent_rot: torch.Tensor,
                clip_rot: torch.Tensor)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 3

attentionFunction · 0.85

post_attentionMethod · 0.80

pre_attentionMethod · 0.45

Tested by

no test coverage detected