From b1864710c54ad4a0ea9b8eb51dcf31ac5e02be2e Mon Sep 17 00:00:00 2001 From: Daniel Han-Chen Date: Mon, 26 Feb 2024 04:30:29 +1100 Subject: [PATCH] Update gemma.py --- unsloth/models/gemma.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/unsloth/models/gemma.py b/unsloth/models/gemma.py index 4cef4972ac..8dc7a5f3db 100644 --- a/unsloth/models/gemma.py +++ b/unsloth/models/gemma.py @@ -77,7 +77,7 @@ class FastGemmaRotaryEmbedding(torch.nn.Module): 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_cached2 = emb.cos().to(torch.bfloat16) + self.cos_cached2 = freqs self.sin_cached2 = emb.sin().to(torch.bfloat16) def forward(self, x, position_ids, seq_len=None): @@ -106,8 +106,9 @@ class FastGemmaRotaryEmbedding(torch.nn.Module): cos_cached = emb.cos().to(dtype=x.dtype) sin_cached = emb.sin().to(dtype=x.dtype) - print(cos_cached) + print(freqs) print(self.cos_cached2) + raise 1 # return self.cos_cached[:,:length], self.sin_cached[:,:length] return self.cos_cached, self.sin_cached