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 2024-02-25 02:25:39 +11:00
commit 045bce2fa5
1 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

11
unsloth/models/gemma.py
View file

@ -72,12 +72,15 @@ class FastGemmaRotaryEmbedding(torch.nn.Module):
self.inv_freq = 1.0 / (
self.base ** (torch.arange(0, self.dim, 2, dtype=torch.int64, device=x.device).float() / self.dim)
)
print(position_ids)
inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1)
position_ids_expanded = position_ids[:, None, :].float()
freqs = (inv_freq_expanded @ position_ids_expanded).transpose(1, 2)
t = torch.arange(self.max_position_embeddings, device="cpu", dtype=torch.int64).float()
freqs = torch.outer(t, self.inv_freq)
emb = torch.cat((freqs, freqs), dim=-1)
# inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -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)
return emb.cos().to(dtype=x.dtype), emb.sin().to(dtype=x.dtype)
pass