diff --git a/unsloth/models/gemma.py b/unsloth/models/gemma.py index 913569b6bd..57eab0d46e 100644 --- a/unsloth/models/gemma.py +++ b/unsloth/models/gemma.py @@ -92,6 +92,7 @@ class FastGemmaRotaryEmbedding(torch.nn.Module): #if self.cos_cached is None: position_ids = torch.arange(self.max_position_embeddings, device=x.device, dtype=torch.int64).unsqueeze(0) inv_freq_expanded = self.inv_freq[None, :, None].float().expand(1, -1, 1) + position_ids_expanded = position_ids[:, None, :].float() freqs = (inv_freq_expanded @ position_ids_expanded).transpose(1, 2) emb = torch.cat((freqs, freqs), dim=-1) self.cos_cached = emb.cos().to(dtype=x.dtype)