ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update gemma.py

Browse source
This commit is contained in:
Daniel Han-Chen 2024-03-05 02:41:56 +11:00
commit 3137392ccf
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
unsloth/models/gemma.py
View file

@ -289,9 +289,9 @@ class GemmaFixedRotaryEmbedding(torch.nn.Module):
timescale = self.base**freq_exponents
positions = torch.arange(self.max_seq_len_cached, device = "cpu", dtype = torch.int64).float()
radians_new = positions[..., None] / timescale[None, None, :]
radians_new = radians_new.squeeze(0)
emb = torch.cat((radians_new, radians_new), dim=-1)
print(emb.shape)
self.register_buffer("cos_cached", emb.cos().to(dtype=dtype, device=device, non_blocking=True), persistent=False)
self.register_buffer("sin_cached", emb.sin().to(dtype=dtype, device=device, non_blocking=True), persistent=False)
pass