diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index a4b6552160..295d92f629 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -1010,6 +1010,7 @@ class LlamaRotaryEmbedding(torch.nn.Module): pass def forward(self, x, position_ids=None, seq_len=None): + print(x, position_ids, seq_len) # x: [bs, num_attention_heads, seq_len, head_size] if seq_len > self.current_rope_size: self._set_cos_sin_cache(seq_len=seq_len, device=x.device, dtype=x.dtype)